CN110263613A - Monitor video processing method and processing device - Google Patents

Abstract

Embodiments of the present invention provide a method and device for monitoring video processing. The method includes: receiving a monitoring video viewing request from a user; in response to the monitoring video viewing request, displaying a monitoring video viewing interface on a user interface; receiving video retrieval information input by a user through the monitoring video viewing interface, wherein the The video retrieval information includes retrieval key information and/or screening conditions, and the key information includes keyword information and/or target picture information; retrieval according to the retrieval information obtains at least one monitoring video; and displaying the at least one monitoring video on the user interface video. Through the scheme provided by the present invention, it is possible to search for comparison records of portraits through screening conditions and key information, and it is also possible to perform trajectory generation and dynamic video playback on target snapshot records to complete the integration of fragmented data, which is convenient for users to intuitively understand Fragmented data is concatenated to present the overall content.

Description

Surveillance video processing method and device

technical field

The invention relates to the field of security technology, in particular to a monitoring video processing method and device.

Background technique

With the advancement of urbanization on a global scale, video surveillance has become relatively popular, and face recognition technology has been widely used in the security industry. The resulting face data is huge, and these huge face data have huge mining value , through the retrieval of face data, the association of individual behavior tracks and snapshot records can be used for data analysis.

At present, face recognition is mainly performed on captured pictures through manual recognition. This method is inefficient and the application of face data is not thorough. More data analysis has not been realized, and more accurate data connections for specific scenarios cannot be given.

Contents of the invention

Embodiments of the present invention provide a monitoring video processing method and device, which can search for portrait comparison records through filtering conditions and key information so that users can view specific details of the portrait comparison records. Furthermore, it can also perform track generation and dynamic video playback on the target snapshot records to complete the integration of fragmented data, so that users can intuitively understand the overall content presented by the series of fragmented data.

The first aspect of the embodiment of the present invention discloses a method for monitoring video processing, the method comprising:

Receiving a user's monitoring video viewing request; in response to the monitoring video viewing request, displaying a monitoring video viewing interface on the user interface; receiving video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval Key information and/or filtering conditions, wherein the key information includes keyword information and/or target picture information; at least one surveillance video is obtained by searching according to the retrieval information; and displaying the at least one surveillance video on a user interface. Among them, it can be understood that the key information can be pictures, files or videos; the filter conditions can be time, place, monitoring equipment identification, matching degree and other conditions, and the user can perform accurate picture or video search according to one or more of the above conditions.

Optionally, the method further includes: determining a target video selected by the user on the user interface, wherein the target video is a video in the retrieved surveillance video; displaying information about the target video, wherein, The information includes the matching degree between the captured human face image in the target video and the human face image in the face database, information of the monitoring equipment that shot the target video, and shooting time. It can be understood that by presenting the matching degree (that is, the similarity between the target picture and the captured picture), collecting the information of the monitoring device and the shooting time of the captured picture, the user can quickly and accurately understand the important information of the captured picture, Thereby improving the user's work efficiency.

Optionally, the method further includes: when receiving a user input command to generate a dynamic trajectory, displaying a candidate video that matches the target face image on the dynamic trajectory display interface; wherein the target human face image The face image in the surveillance video selected by the user; the candidate video selected by the user is determined; the dynamic trajectory is generated according to the candidate video selected by the user. Wherein, the generating the dynamic track according to the candidate video selected by the user includes: generating the dynamic trajectory of the person corresponding to the first human face image according to the first human face image in the candidate video that matches the target human face image track. For example, if a person A appears in the candidate video, and the matching degree between the face of the person A and the target face image is greater than a preset threshold, then the dynamic track of the person A is generated. It can be understood that, by presenting the dynamic trajectory, the user can know the moving information of the target person (such as information such as the direction of movement, the way of movement, etc.), so that the user can judge the intention of the target person more accurately.

Optionally, the method further includes: when receiving the snapshot information for viewing the target video, acquiring a snapshot video that matches the target face image in the target video; The similarity between the image and the target face image is used to sort the captured videos; and the sorted captured videos are displayed at a preset position. It can be understood that, by sorting the similarity, the user can quickly lock the surveillance video with a high matching degree, so as to obtain useful information quickly.

Optionally, the method further includes: determining the target snapshot video selected by the user; the target snapshot video is one of the sorted snapshot videos; in response to a dynamic trajectory generation instruction input by the user, according to the selected The captured video of the above target is used to generate dynamic trajectories. It can be understood that by presenting the dynamic trajectory, the user can understand the movement information of the target person more intuitively.

Optionally, the method further includes: dynamically playing the target snapshot video in response to a dynamic playing instruction input by the user.

Optionally, before receiving the user’s monitoring video viewing request, the method further includes: logging in to the monitoring video processing system according to information input by the user; if the login is successful, importing monitoring equipment information, Portrait information and map information, and set matching rules for face images.

The second aspect of the present invention discloses a surveillance video processing device, the device comprising:

A receiving unit, configured to receive a monitoring video viewing request from a user;

A display unit, configured to display a surveillance video viewing interface on the user interface in response to the surveillance video viewing request;

The receiving unit is further configured to receive video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval key information and/or filter conditions; wherein the key information includes keyword information and/or target image information;

A retrieval unit, configured to retrieve at least one surveillance video according to the retrieval information;

The display unit is further configured to display the at least one surveillance video on a user interface.

Optionally, the device also includes:

A determining unit, configured to determine a target video selected by the user on the user interface, wherein the target video is a video in the retrieved surveillance video;

The display unit is also used to display the information of the target video, wherein the information includes the matching degree between the captured face image in the target video and the face image in the face database, and the target video is captured. The information of the monitoring equipment and the shooting time.

Optionally, the device also includes:

The display unit is also used to display a video matching the target face image on the dynamic track display interface when receiving a user-input command to generate a dynamic track; wherein, the target face image is a monitoring image selected by the user Face images in the video;

The determination unit is also used to determine the candidate video selected by the user;

A generating unit, configured to generate a dynamic trajectory corresponding to the first human face image according to the first human face image in the candidate video that matches the target human face image.

Optionally, the device also includes:

An acquisition unit, configured to acquire a snapshot video that matches the target face image in the target video when receiving snapshot information for viewing the target video;

A sorting unit, configured to sort the snapped videos according to the similarity between the captured face images in the snapped videos and the target face image;

The display unit is further configured to display the sorted snapshot videos at a preset position.

Optionally, the determining unit is configured to determine the target snapshot video selected by the user; the target snapshot video is one of the sorted snapshot videos;

The generation unit is configured to generate a dynamic trajectory according to the captured video of the target in response to a dynamic trajectory generation instruction input by a user.

Optionally, the device also includes:

The display unit is further configured to dynamically play the target snapshot video in response to a play instruction input by the user.

Optionally, the acquisition unit is also used to log in the monitoring video processing system according to the information input by the user; if the login is successful, import monitoring equipment information, portrait information and map information into the system according to the user's instruction, and set the Matching rules for face images.

The third aspect of the present invention discloses a terminal, including a processor, an input device, an output device, and a memory, and the processor, the input device, an output device, and the memory are connected to each other, wherein the memory is used to store computer programs, and the The computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of the first aspect.

A fourth aspect of the present invention discloses a computer-readable storage medium, the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in any one of the first aspect.

In the solution of the embodiment of the present invention, the monitoring video viewing request of the user is received; in response to the monitoring video viewing request, the monitoring video viewing interface is displayed on the user interface; the video retrieval information input by the user through the monitoring video viewing interface is received, wherein , the video retrieval information includes retrieval key information and/or screening conditions, wherein the key information includes keyword information and/or target picture information; retrieval according to the retrieval information obtains at least one monitoring video; displayed on the user interface The at least one surveillance video. Through the solution provided by the present invention, the portrait comparison record can be searched through filter conditions or key information, so that the user can check the specific details of the portrait comparison record. At the same time, it can generate trajectory for the target capture record, view the captured pictures, and play the video dynamically, so that users can obtain the information of the target person more intuitively.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings that need to be used in the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. Those of ordinary skill in the art can also obtain other drawings based on these drawings without any creative effort.

FIG. 1 is a schematic diagram of an application scenario of a method for monitoring video processing provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of an interface for monitoring video processing provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of another surveillance video processing interface provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of another monitoring video processing interface provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of another monitoring video processing interface provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram of another surveillance video processing interface provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of another monitoring video processing interface provided by an embodiment of the present invention;

FIG. 8 is a schematic diagram of another surveillance video processing interface provided by an embodiment of the present invention;

FIG. 9 is a schematic flowchart of a method for monitoring video processing provided by an embodiment of the present invention;

FIG. 10 is a schematic flowchart of another monitoring video processing method provided by an embodiment of the present invention;

FIG. 11 is a schematic flowchart of another monitoring video processing method provided by an embodiment of the present invention;

FIG. 12 is a schematic structural diagram of a monitoring video processing device provided by an embodiment of the present invention;

FIG. 13 is a schematic diagram of the physical structure of a surveillance video processing device provided by an embodiment of the present invention;

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the embodiment of the present invention. Some examples, but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

The terms "first", "second" and "third" appearing in the specification, claims and drawings of the present invention are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, products or apparatuses.

In order to better understand the monitoring video processing method provided in the embodiment of the present application, the following briefly introduces the monitoring video processing method first. Please refer to FIG. 1 . FIG. 1 is a schematic diagram of an application scenario of a monitoring video processing method provided by an embodiment of the present application. As shown in FIG. 1 , the face recognition system 100 includes a monitoring device 110 , a face dynamic and static comparison server 120 , and a terminal monitoring computer 130 . For example, the monitoring device 110 may be electronic devices such as cameras, capture cameras, smart access control and time attendance devices. It should be pointed out that the camera can provide video streams; the capture machine can provide picture streams including face images; smart access control/time attendance equipment can capture portraits of people entering and leaving the company. Among them, it should be pointed out that the terminal monitoring computer 130 is used to display the images collected by each monitoring device 110, of course, the user can monitor and view them on the computer; The real-time video stream and image stream are analyzed and identified to identify whether the captured portrait is a portrait in the portrait database. The blacklisted portrait will be alerted, and if it is not in the portrait database, it will be marked as a stranger. The monitoring device 110 collects real-time video streams, the face dynamic comparison server 120 analyzes the video streams, performs face recognition, attribute extraction and identity recognition on portraits, and the terminal monitoring computer 130 provides users with monitoring and record viewing functions. In addition, the face recognition system further includes a snapshot database 140 for storing the snapshots collected by the monitoring device 110 . Through the above system, the user can select the map area, monitoring equipment, portrait database, similarity threshold (or called matching threshold, which refers to the similarity between the captured image and the image stored in the portrait database), capture time, monitoring Or access control rules, comparison type and other conditions, filter the portrait comparison record that meets the conditions, or search for the portrait comparison record by image search (portrait can be understood as a face image), the user can view the specific details of the portrait comparison record, the The specific capture time, device location and other information of the capture record, including the capture record of the captured portrait and the viewing of the portrait database record, supports sorting this record by time or similarity, and viewing the target capture record recorded in the portrait database . At the same time, it can generate trajectory for the target snapshot record, view the captured picture, and dynamically play the video, optimize the specific display form of the record retrieval result, and improve the application of face data.

In combination with the above monitoring system, this embodiment provides a specific implementation manner. It should be pointed out that a business system (such as an application program, the business system is a monitoring video processing system) is installed in the above-mentioned terminal monitoring computer, and the user can retrieve and view records on the computer. It is understandable that the face dynamic and static comparison server can analyze and identify the real-time video stream and picture stream, identify whether the captured portrait is a portrait in the portrait database, and mark it as a stranger if it is not in the portrait database. It should be pointed out that the monitoring equipment collects real-time video streams, and the face dynamic comparison server analyzes the video streams, performs face recognition, attribute extraction and identity recognition on portraits, and the business system is installed on the terminal monitoring computer to provide users with records. View and search functions.

Specifically, the user can use the terminal to monitor the computer to perform the following operations:

(1) According to the equipment management, portrait library management, rule management, map management and user management modules of the business system, users can set the filter conditions for record retrieval in detail, including time, location, portrait library, equipment, rule group, threshold, Record the operator's department, comparison type and record operation status. At the same time, it supports users to search for pictures by pictures or enter keywords to search after condition setting.

(2) Support a portrait comparison card to view in chronological (reverse) order and target capture records by similarity (sequential or reverse order), view the capture time of the capture record and the position of the device information on the map, and allow full-screen viewing Capture and record images and download images, and support checking the capture records for trajectory generation. According to the position of the device on the map, the dynamic behavior track of the portrait can be viewed on a daily basis.

(3) Set the comparison type of portrait capture through the business system. For example, stranger alarm, blacklist alarm, etc., through the above paradigm, manpower can be liberated, and there is no need to manually screen the recognition results. Paradigms can be understood as rules set by users. For example, the user sets the first image group and the second image group; the first image group stores people who are known; the second image group stores dangerous elements (such as people wanted by the police).

(4) Record the operation status flag. For example, the status can be: unchecked, checked, confirmed ratio (refers to the successful match between the captured picture and the stored target picture, that is, the user confirms that it is a match), confirmed non-compared (refers to the captured picture and the stored target picture) The picture matching is unsuccessful, that is, the user confirms that the two pictures do not match), and the user is supported to manually confirm (not) the comparison and cancel the (not) comparison. On the basis of portrait recognition, it also supports manual confirmation of the result, which double guarantees the recognition result.

(5) After setting the conditions, the user uploads local pictures or drags and drops pictures on the system interface to search for pictures by picture. The record retrieval results of image search by image are classified by snapshot database and portrait database, and the snapshot database can be sorted by time and similarity; the portrait database results in the search results can be sorted by similarity, and corresponding results can be viewed for their target snapshot records, followed by snapshots The results of the library are the same, and its snapshot records support sorting by time and similarity, generating trajectories and viewing trajectories by day.

Specifically, in a specific implementation of the present invention, after the user logs in to the system, first import monitoring equipment, portrait and map information by editing the equipment management, portrait database management, and map management modules of the business system. Enter the rule management module to set corresponding monitoring/access control tasks and enable rules.

As shown in Figure 2 and Figure 3, the user enters the record retrieval module, enters keywords, and then sets the conditions (the comparison record defaults from near to far in the last 7 days), and the user can confirm (not) compare and cancel the comparison card (not) than in.

As shown in Figure 4, the user clicks on a comparison card to display details, such as the shooting time of the captured picture in the comparison card, the shooting location, information about the monitoring equipment that took the captured picture, etc.

As shown in FIG. 5 , in order to display the details of the captured picture, the user can double-click or use a preset gesture to zoom in on the picture.

As shown in FIG. 6 , the user can select a video record, and then generate a dynamic track corresponding to the video according to the selected video record.

As shown in Figure 7 and Figure 8, the user enters the record retrieval module, uploads or drags pictures locally to search by picture, and then sets the conditions to view the pictures stored in the portrait library and the snapshot library, and the pictures in the snapshot library It can be sorted by time and similarity, and it supports viewing the map information and capture time of captured devices.

As shown in Figure 9, Figure 9 is a schematic flowchart of a method for monitoring video processing provided in the embodiment of the present application, the method for monitoring video processing includes the following steps:

S201. Determine the filtering conditions set by the user; determine the key information input by the user, wherein the key information is a keyword or a target picture; perform a search according to the filtering conditions and key information to obtain multiple snapshot records;

The above features can be understood as: setting filter conditions, and obtaining multiple snapshot records through keyword search or image search.

Wherein, the key information includes keyword information and/or target image information;

Wherein, the filter conditions include time, location, portrait database, equipment, rule group, threshold, record operator department, comparison type and record operation status. After logging in to the system, the user can set the filter conditions for record retrieval in detail—retrieval items, priority and sub-priority retrieval order, etc. For example, the filter condition may be a time period, such as the last three days or the last seven days, or a specific date. For example, the filtering condition can be the serial number of the monitoring device. Certainly, the filter condition may be a combination of multiple conditions, and the condition includes time, location, similarity threshold, etc., which is not limited here.

The snapshot records are displayed in the form of comparison cards. The comparison card can include target pictures, snapped pictures, and similarity information. For example, it can also include time, place, character information (such as clothing color), weather, etc.

Among them, you can search for pictures by uploading or dragging pictures locally.

Among them, image retrieval by image search can be realized by uploading images locally or dragging images to a designated area. The filter conditions include time, location, portrait library, device, rule group, threshold, record operator department, comparison type and record operation status. In the filter conditions, the time item is presented in the form of a time period. For example, if you select the capture recording time period as: 2019-4-16 12:00:00 to 2019-4-16 15:00:00, the location item, portrait library item, You can select more than one record operator department item and equipment item. The equipment item is to select the surveillance camera. The rule group item is to select a rule group from several rule groups set by the system. The threshold value item is to measure the similarity of the picture Limit, for example, if the limit similarity is higher than 60%, the corresponding selection threshold is 60%, and the comparison type items include whitelist comparison, stranger warning, non-living attack, password attack, whitelist exception and blacklist warning Six Type, the snapshot record is displayed as a comparison card on the search result page, and the record operation status items include four types: unchecked, checked, confirmed compared and confirmed not compared, and supports users to manually confirm (un)matched and compared cards in the comparison In canceling (not) comparing, on the basis of portrait recognition, it also supports manual confirmation of the results, and double guarantees the recognition results.

Among them, after the surveillance camera collects the face video and face picture, the face comparison server will analyze the collected face video and face picture, extract features and identify the identity, and make the face picture according to the features of the face picture. Set up corresponding feature tags, feature tags include appearance features, such as: black hair, big eyes, earrings, etc., if the identity information of the portrait in the face picture is recognized, its identity information including name, age, occupation, etc. can also be used as The feature tags are associated with the face pictures, and then the collected face pictures are imported into the system’s snapshot database. When searching through keywords, the system obtains the corresponding search results by matching feature tags and keywords. Keywords such as : Zhang San (name), middle-aged man (age), security guard (occupation), yellow hair (appearance), etc. In addition, the user can also import the target face picture into the portrait library, so that the pictures in the snapshot library can be matched with the pictures in the portrait library.

It can be seen that the search conditions are set comprehensively, which can provide users with a more accurate search environment, without manual screening of recognition results, which greatly reduces the workload.

Key words—retrieve based on the personal information of the person you want to search (because the portrait library is imported, the corresponding pictures will be equipped with personal information and appearance characteristics, such as name, age, gender, occupation, etc., such as cleaners ( Cleaning staff) (characterized by specific clothing and cleaning tools, as well as specific working hours), middle-aged, Zhang Hao, appearance characteristics - such as yellow hair, thick eyebrows, high cheekbones, etc.

S202. Determine a target snapshot record selected by the user from the plurality of snapshot records; and display the selected target snapshot record.

In short, it is to select a snapshot record from the plurality of snapshot records to view.

Among them, the user can view the snapshot information of the snapshot record and the generated behavior track. The snapshot information includes the capture time of the snapshot record, the location of the device displayed on the map, and so on.

Wherein, the user can confirm (not) compare and cancel (not) compare the cards.

The comparison types are divided into six types: whitelist comparison, stranger warning, non-living attack, password attack, whitelist abnormality, and blacklist warning - freeing manpower and eliminating the need to manually screen the recognition results.

There are four record operation states: unchecked, checked, confirmed compared, confirmed not compared, support users to manually confirm (not) compared and cancel (not) compared, and also support manual confirmation of results on the basis of portrait recognition, Double guarantee identification result.

In a possible example, selecting a snapshot record from the multiple snapshot records to view includes: sorting the multiple snapshot records by similarity or time in the snapshot library, and selecting a snapshot record from the multiple snapshot records Snapshot records, view the snapshot information, snapshot pictures, dynamic videos and dynamic tracks of the snapshot records.

It can be seen that in this example, the viewable content of the search results is rich, the page settings are reasonable, and the relevant information of the snapshot record can be quickly found, and the user experience is good.

In a possible example, the selecting a snapshot record from the multiple snapshot records to view includes: sorting the multiple snapshot records according to similarity in the portrait library, and selecting a snapshot record from the multiple snapshot records Capture records, view the target capture records of the capture records, sort the target capture records by similarity or time, select the final capture record from the sorted target capture records, and view the capture information of the final capture records , Dynamic trajectory.

Keyword search can only be searched in the snapshot library. Search by image can choose to search in the portrait library or snapshot library. The search result of the portrait library is the capture information and dynamic track of the snapshot record, and the search result of the snapshot library is the snapshot record. The snapshot information, snapshot pictures, dynamic videos and dynamic tracks of the

It can be seen that the two search methods of keyword search and image search fully cover the user's search needs, and there are many search and filter options, and the screening is clear. By filtering out unqualified records, you can quickly locate the target capture record, and provide portrait library and snapshot There are two types of databases for users to search and choose, and the sub-library display is more conducive to user judgment and meets multi-user scenarios.

Optionally, displaying the selected target capture record includes: displaying capture information, snapshot pictures, dynamic videos and dynamic tracks of the selected target capture record.

Optionally, determining a target snapshot record selected by the user from the plurality of snapshot records includes: determining a first snapshot record selected by the user from the plurality of snapshot records, and presenting a A target snapshot record, using the target snapshot record selected by the user as a target snapshot record.

Optionally, before determining the filter conditions set by the user, the method further includes: logging into the system according to the information input by the user; if the login is successful, importing monitoring equipment, portraits and map information into the system according to the user's instruction , and set the corresponding rules.

Optionally, the dynamic track is generated according to the position of the monitoring device on the map and the time of the snapshot record, or is generated according to the selected snapshot record.

For example, if N pictures are captured and M pictures selected by the user are determined, then a dynamic trajectory is generated according to the selected M pictures. Wherein, N and M are positive integers, and N is not less than M. Among them, after the user logs in to the system, the corresponding monitoring equipment, portrait and map information are imported through the system's equipment management, portrait database management and map management modules, and then the corresponding monitoring/access control tasks are set through the rule management module to enable rules.

Select M snapshot records from the plurality of snapshot records to generate.

Optionally, the snapshot record is presented in the form of a comparison card; wherein the comparison card includes the target picture, the snapshot picture, and the similarity between the target picture and the snapshot picture.

Optionally, the key information is a target picture;

The retrieval is performed according to the screening conditions and key information to obtain multiple snapshot records, including:

determining a first snapshot set according to the filtering conditions;

determining a candidate picture in the first snapshot set whose similarity with the target picture is greater than a preset similarity; wherein, the number of the candidate pictures is multiple;

The candidate pictures are sorted according to preset rules to obtain multiple snapshot records.

For example, if the filter condition is a time period (such as 3 days), then the first snapshot collection is the pictures taken in the past 3 days, and it is determined that the similarity between the first snapshot collection and the target picture is greater than the preset similarity degree of pictures (for example, determine the pictures whose similarity with the target picture in the first shooting set is greater than 80%), sort the candidate pictures according to the preset rules to obtain multiple candidate pictures, wherein the preset rules can be The candidate pictures are sorted according to the similarity value from high to low to obtain multiple snapshot records.

In summary, by using the technical solution provided by the present invention, the filter conditions set by the user are determined; the key information input by the user is determined, wherein the key information is a keyword or a target picture; Retrieving to obtain a plurality of snapshot records; determining a target snapshot record selected by the user from the plurality of snapshot records. Through the solution provided by the present invention, the portrait comparison record can be searched through filtering conditions and key information, and the user can check the specific details of the portrait comparison record. Furthermore, it can also perform track generation and dynamic video playback on the target snapshot records to complete the integration of fragmented data, so that users can intuitively understand the overall content presented by the series of fragmented data.

Please refer to FIG. 10. FIG. 10 is a schematic flowchart of a method for monitoring video processing provided by an embodiment of the present invention, including the following steps:

S301. Perform system login according to the information input by the user;

Wherein, the information input by the user may be an account password or the like. The user's instruction may be voice input, keyboard or mouse input, or gesture input.

It can be understood that the available system is a business system, that is, a surveillance video processing system.

S302. If the login is successful, import monitoring equipment information, portrait information and map information into the system according to the user's instruction, and set corresponding rules; obtain multiple snapshot records through keyword search or image search.

Wherein, the corresponding rule is a matching rule of a face image, such as a matching threshold or a similarity threshold.

S303. Obtain a plurality of snapshot records through keyword search or image search, and display the snapshot records in a preset manner.

Wherein, the multiple snapshot records are sorted by similarity or time in the snapshot library, and the sorted snapshot pictures are displayed.

In addition, according to the user's instruction, the snapshot can be zoomed in and displayed, and a dynamic trajectory can be generated.

Through the solution provided by the present invention, it is possible to search for the portrait comparison record by means of image search, and the user can check the specific details of the portrait comparison record. At the same time, it can generate the trajectory of the target capture record so that the user can understand the content of the picture more intuitively, thereby improving the user experience and operation efficiency. It should be noted that, for the specific implementation process of each step of the method shown in FIG. 10 , reference may be made to the specific implementation process described in the above method, and will not be described here again.

The method for processing the surveillance video shown in FIG. 11 will be described in detail below.

Please refer to FIG. 11. FIG. 11 is a schematic flowchart of a method for monitoring video processing provided by an embodiment of the present invention, including the following steps:

S401. Receive a monitoring video viewing request from a user;

It can be understood that when the user logs into the video surveillance system, he can request to view the surveillance video by clicking on a preset icon.

S402. In response to the surveillance video viewing request, display a surveillance video viewing interface on the user interface;

S403. Receive video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval key information and/or filter conditions; wherein the key information includes keyword information and/or target image information ;

For example, the filter condition of the search may be a time period, a selected monitoring device, or a location. For example, the retrieval key information can be the face picture dragged to the preset position by the user, or the face picture selected by the user in the portrait library, or the information input by the user, such as name, gender, etc.

S404, perform retrieval according to the retrieval information to obtain at least one surveillance video;

S405. Display the at least one surveillance video on a user interface.

In a possible implementation of the present invention, the face is captured by a monitoring device or a capture device; face comparison is performed in real time; the time when the face image is captured, the corresponding capture device information, and the successfully compared portrait database are recorded The face image information in it forms a ratio card. Set filter conditions, search for snapshot records by keyword search or image search, view the comparison card of a certain snapshot record, and click the snapshot library to view the snapshot records and play dynamic video for them. Draw and view snapped pictures, and display dynamic trajectories; view by portrait library, you can view the target snapshot records of portraits in the portrait library and the behavior track generation and dynamic display of the snapshot records. In short, the monitoring system provided by the present invention supports multi-condition screening of face capture records and viewing by portrait library/snapshot library. According to the face comparison results of multiple monitoring devices, the behavior track generation, Dynamically display tracks, view snapped pictures and play dynamic videos.

In addition, optionally, after at least one surveillance video is displayed, further operations may be performed on the video selected by the user according to the user's instruction, such as displaying information about the video selected by the user. Specifically, the method includes: determining the target video selected by the user on the user interface, wherein the target video is a video in the retrieved surveillance video; displaying information about the target video, wherein the The information includes the matching degree between the captured face image in the target video and the face image in the face database, the information of the monitoring device that shot the target video, and the shooting time. It is understandable that when the user selects the target video, the system directly displays the information that the user usually cares about, which facilitates the improvement of the user's work efficiency and the user's experience.

Optionally, the system (that is, the surveillance video processing system) can also support information mining of surveillance videos, for example, generating corresponding dynamic tracks for videos selected by users. Specifically, the method includes: when receiving a user input command to generate a dynamic trajectory, displaying a candidate video that matches the target face image on the dynamic trajectory display interface; wherein the target human face image is the user's The face image in the selected surveillance video; determine the candidate video selected by the user; generate a dynamic trajectory according to the candidate video selected by the user. Wherein, the generating the dynamic track according to the candidate video selected by the user includes: generating the dynamic trajectory of the person corresponding to the first human face image according to the first human face image in the candidate video that matches the target human face image track. Through the aforementioned technical solution, the user can intuitively perceive the moving information of the target person, such as the moving direction, moving intention, and the like. For example, you can determine the initial position and end position of the captured characters in the video, and then describe how the captured characters move from the initial position to the end position, such as walking in a straight line, or walking in an S-curve, etc. This is not an example.

Further, in order to facilitate the user to locate the target person as soon as possible, the related videos may be sorted by similarity, that is, the surveillance videos are displayed in descending order of similarity. Wherein, the method includes: when receiving the snapshot information for viewing the target video, acquiring a snapshot video matching the target face image in the target video; sorting the snapped videos according to the similarity of the target face images; and displaying the sorted snapped videos at a preset position. In addition, it can be understood that dynamic trajectory generation can also be performed for the captured video. Specifically, the method includes: determining the target snapshot video selected by the user; the target snapshot video is one of the sorted snapshot videos; in response to a dynamic trajectory generation instruction input by the user, according to the target Capture video to generate dynamic trajectory. It can be understood that the target snapshot video can be 1 frame, then a dynamic trajectory of the snapshot video can be generated by dynamically connecting multiple snapshot videos. It is understandable that dynamic trajectories can often present more content than snapshots.

Further, the method further includes: dynamically playing the target snapshot video in response to a dynamic playing instruction input by the user. In addition, according to the user's instruction, the target snapshot video can be displayed at the position specified by the user.

In addition, it can be understood that, before receiving the user’s monitoring video viewing request, the method further includes: logging into the system according to the information input by the user; if the login is successful, importing monitoring equipment information, portrait Information and map information, and set the corresponding rules.

It should be noted that, for the specific implementation process of each step of the method shown in FIG. 11 , reference may be made to the specific implementation process described in the above method, and will not be described here again.

For example, the above solution or system can be applied to scenarios such as security deployment or community monitoring. For example, when the police and other personnel arrest suspects, they can view the capture records of each surveillance system. After being screened by record retrieval and other conditions, the relevant records can generate behavior tracks and dynamic videos, helping the police quickly obtain behavior information of suspects and determine action plans for quick implementation. arrest. For another example, the system can assist security guards, residents, or ordinary people to find the missing elderly and children quickly by searching images and filtering conditions to find the lost behavior route when the old and young are lost at home. For another example, when analyzing user behavior in supermarkets, it can be combined with user portrait capture record analysis, and by filtering restrictions such as equipment, location, time, etc., record retrieval and viewing can be performed for each shopping area, combined with user trajectory and dynamic video viewing Adjust the location and quantity of commodities in supermarkets in a targeted manner to achieve the purpose of increasing sales. For example, it can be divided into groups—the elderly, women, students, etc., and the consumption habits and purchasing power of each group can be analyzed based on the recorded results, such as what women tend to buy, the frequency of buying, and the quantity—to better formulate promotional strategies , and the adjustment position and quantity mentioned earlier—you can find out the approximate sales associated with the product.

Please refer to FIG. 12 . FIG. 12 is a schematic structural diagram of a surveillance video processing device provided by an embodiment of the present invention. Among them, as shown in Figure 12, an embodiment of the present invention provides a monitoring video processing device 500, wherein the device can be a smart phone, tablet computer, smart wearable device, video processing server, monitoring device and other electronic equipment. The device 500 includes:

A receiving unit 501, configured to receive a user's monitoring video viewing request;

The display unit 502 is configured to display a monitoring video viewing interface on the user interface in response to the monitoring video viewing request;

The receiving unit 501 is also configured to receive video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval key information and/or filter conditions; wherein the key information includes keyword information and /or target image information;

A retrieval unit 503, configured to retrieve at least one surveillance video according to the retrieval information;

The display unit 502 is further configured to display the at least one surveillance video on a user interface.

Optionally, the surveillance video processing apparatus 500 further includes a determining unit 504;

The determining unit 504 is configured to determine the target video selected by the user on the user interface, wherein the target video is a video in the retrieved surveillance video; the display unit 502 is configured to display information of the target video, wherein , the information includes the matching degree between the captured face image in the target video and the face image in the face database, the information of the monitoring device that shot the target video, and the shooting time.

Optionally, the surveillance video processing apparatus 500 further includes a generating unit 505;

The display unit 502 is configured to display a candidate video matching the target face image on the dynamic track display interface when receiving a user-input command to generate a dynamic track; wherein the target face image is selected by the user Face images in surveillance video;

A determining unit 504, configured to determine a candidate video selected by the user;

The generation unit 505 is configured to generate a dynamic track according to the candidate video selected by the user.

Wherein, the generating the dynamic track according to the candidate video selected by the user includes: generating the dynamic trajectory of the person corresponding to the first human face image according to the first human face image in the candidate video that matches the target human face image track.

Optionally, the surveillance video processing device 500 also includes an acquisition unit 506 and a sorting unit 507;

An acquisition unit 506, configured to acquire a snapshot video that matches the target face image in the target video when receiving snapshot information for viewing the target video;

A sorting unit 507, configured to sort the snapped videos according to the similarity between the captured face image in the snapped video and the target face image;

The display unit 502 is configured to display and display the sorted snapshot videos at a preset position.

Optionally, the determining unit 504 is further configured to determine the target snapshot video selected by the user; the target snapshot video is one of the sorted snapshot videos; the generating unit 505 is configured to respond to user input The dynamic track generating instruction is used to generate a dynamic track according to the captured video of the target.

Optionally, the display unit 502 is configured to dynamically play the target snapshot video in response to a dynamic play instruction input by the user.

Acquisition unit 506 is also used to log in the monitoring video processing system according to the information input by the user; if the login is successful, then import monitoring equipment information, portrait information and map information into the system according to the user's instruction, and set the matching rules of the face image .

Wherein, the above-mentioned units may be used to execute the methods described in the above-mentioned embodiments. For a specific description, refer to the description of the embodiments, and details are not repeated here.

Please refer to FIG. 13. FIG. 13 is a schematic structural diagram of a surveillance video processing device provided in an embodiment of the present application. As shown in FIG. 13, the electronic device 600 includes a processor 610, a memory 620, an input device 630, an output device 640 and One or more programs 621, wherein the one or more programs 621 are stored in the above-mentioned memory 620 and configured to be executed by the above-mentioned processor 610, when the one or more programs 621 are executed, the processor 610 performs the following operations:

Receive the user's surveillance video viewing request;

In response to the monitoring video viewing request, displaying a monitoring video viewing interface on the user interface;

Receiving video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval key information and/or filter conditions; wherein the key information includes keyword information and/or target image information;

Retrieving according to the retrieval information to obtain at least one surveillance video;

Displaying the at least one surveillance video on a user interface.

Optionally, the processor also performs the following operations:

determining a target video selected by the user on the user interface, wherein the target video is a video in the retrieved surveillance video;

Displaying the information of the target video, wherein the information includes the matching degree between the captured face image in the target video and the face image in the face database, information of the monitoring equipment that shot the target video, and shooting time.

Optionally, the processor also performs the following operations:

When receiving the command that the user enters to generate the dynamic track, the candidate video that matches the target face image is displayed on the dynamic track display interface; wherein, the target face image is the face in the surveillance video selected by the user image;

Determine the candidate video selected by the user;

Generate dynamic trajectories based on candidate videos selected by the user.

Wherein, the generating the dynamic track according to the candidate video selected by the user includes: generating the dynamic trajectory of the person corresponding to the first human face image according to the first human face image in the candidate video that matches the target human face image track

Optionally, the processor also performs the following operations:

When receiving the capture information for viewing the target video, obtain a capture video matching the target face image in the target video;

sorting the snapped videos according to the similarity between the snapped face images in the snapped videos and the target face image;

The sorted snapshot videos are displayed at a preset position.

Optionally, the processor also performs the following operations:

Determine the target snapshot video selected by the user; the target snapshot video is a video in the sorted snapshot videos;

In response to a dynamic trajectory generation instruction input by a user, a dynamic trajectory is generated according to the captured video of the target.

Optionally, the processor further performs the following operation: dynamically play the target snapshot video in response to a dynamic play instruction input by the user.

Optionally, before receiving the user’s monitoring video viewing request, the processor also performs the following operations: log in to the system according to the information input by the user; if the login is successful, import monitoring equipment information, portrait Information and map information, and set the corresponding rules.

In addition, it should be pointed out that, for relevant explanations of this embodiment, reference may be made to the contents of the foregoing embodiments.

In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or can be Integrate into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes. .

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still understand the foregoing The technical solutions recorded in each embodiment are modified, or some of the technical features are replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A surveillance video processing method, characterized in that the method comprises: Receive the user's surveillance video viewing request; In response to the monitoring video viewing request, displaying a monitoring video viewing interface on the user interface; Receiving video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval key information and/or filter conditions; wherein the key information includes keyword information and/or target image information; Retrieving according to the retrieval information to obtain at least one surveillance video; Displaying the at least one surveillance video on a user interface. 2. The method according to claim 1, characterized in that the method further comprises: determining a target video selected by the user on the user interface, wherein the target video is a video in the retrieved surveillance video; Displaying the information of the target video, wherein the information includes the matching degree between the captured face image in the target video and the face image in the face database, information of the monitoring equipment that shot the target video, and shooting time. 3. The method according to claim 2, wherein the method further comprises: When receiving the command that the user enters to generate the dynamic track, the video that matches the target face image is displayed on the dynamic track display interface; wherein, the target face image is the face image in the surveillance video selected by the user; Determine the candidate video selected by the user; A dynamic trajectory corresponding to the first human face image is generated according to the first human face image in the candidate video that matches the target human face image. 4. The method according to claim 2, characterized in that the method further comprises: When receiving the capture information for viewing the target video, obtain a capture video matching the target face image in the target video; sorting the snapped videos according to the similarity between the snapped face images in the snapped videos and the target face image; The sorted captured videos are displayed at a preset position. 5. method according to claim 4, is characterized in that, described method also comprises: Determine the target snapshot video selected by the user; the target snapshot video is a video in the sorted snapshot videos; In response to a dynamic trajectory generation instruction input by a user, a dynamic trajectory is generated according to the captured video of the target. 6 . The method according to claim 5 , further comprising: dynamically playing the target snapshot video in response to a playback instruction input by a user. 7. The method according to any one of claims 1 to 6, characterized in that, before receiving the user's monitoring video viewing request, the method further comprises: logging into the monitoring video processing system according to the information input by the user; if If the login is successful, the monitoring equipment information, portrait information and map information will be imported to the system according to the user's instructions, and the matching rules for face images will be set. 8. A surveillance video processing device, characterized in that the device comprises: A receiving unit, configured to receive a monitoring video viewing request from a user; A display unit, configured to display a surveillance video viewing interface on the user interface in response to the surveillance video viewing request; The receiving unit is further configured to receive video retrieval information input by the user through the monitoring video viewing interface, wherein the video retrieval information includes retrieval key information and/or filter conditions; wherein the key information includes keyword information and/or target image information; A retrieval unit, configured to retrieve at least one surveillance video according to the retrieval information; The display unit is further configured to display the at least one surveillance video on a user interface. 9. A terminal, characterized in that it includes a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory are connected to each other, wherein the memory is used to store computer programs, and the The computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1-7. 10. A computer-readable storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1-7.