CN112383751A - Monitoring video data processing method and device, terminal equipment and storage medium - Google Patents
Monitoring video data processing method and device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN112383751A CN112383751A CN202011225551.XA CN202011225551A CN112383751A CN 112383751 A CN112383751 A CN 112383751A CN 202011225551 A CN202011225551 A CN 202011225551A CN 112383751 A CN112383751 A CN 112383751A
- Authority
- CN
- China
- Prior art keywords
- screenshot
- video
- data
- video data
- receiving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/787—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
Abstract
The embodiment of the invention discloses a monitoring video data processing method, a monitoring video data processing device, terminal equipment and a storage medium, wherein a data source distribution diagram corresponding to a target event is generated by receiving position marking operation of a data source corresponding to video data, and the video data is related monitoring data of the target event; receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element on the basis of the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element; acquiring screenshot operation of a playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot; and storing the data source distribution map, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event, so as to realize better analysis effect and communication efficiency of the monitoring video.
Description
Technical Field
The embodiment of the invention relates to the technical field of video data processing, in particular to a monitoring video data processing method, a monitoring video data processing device, terminal equipment and a storage medium.
Background
With the development of social economy, video monitoring plays an increasingly important role in the field of public security video investigation. When the video is used for investigation and case solving service, the video has the functions and aims to comb all information related to cases through video images, reduce the investigation range, determine the investigation direction, expand the investigation means, and finally find and capture the identity of a suspect.
Currently, public security criminal policemen are mostly divided into multiple workers when studying and judging cases. The basic-level public security serves as a 'video operator', collects as many case-related videos as possible around the case basic information, and uploads the management case-related videos through a hard disk or a system in a unified manner; and the police officer serving as the "investigator" checks and compares the case-involved videos one by one to find the suspect, and finally determines the identity of the suspect by combining other technologies and data of the police officer.
The inventor discovers that when the monitoring video data related to a case is analyzed due to the fact that the processed data sources are multiple, the video time is long, the number of participants is large and the like in the process of implementing the existing monitoring video processing, the presentation of data content and the transmission of clues among the participants are obstructed, and the analysis effect and the communication efficiency of the monitoring video are influenced.
Disclosure of Invention
The invention provides a monitoring video data processing method, a monitoring video data processing device, terminal equipment and a storage medium, and aims to solve the technical problems that in the prior art, the presentation of data content and the transmission of clues among participators are obstructed, and the analysis effect and the communication efficiency of a monitoring video are influenced.
In a first aspect, an embodiment of the present invention provides a method for processing surveillance video data, including:
receiving position marking operation of a data source corresponding to video data, and generating a data source distribution diagram corresponding to a target event, wherein the video data is associated monitoring data of the target event;
receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element on the basis of the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element;
acquiring screenshot operation of a playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot;
and storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
Wherein the screenshot operation is a complete screenshot operation or a partial screenshot operation;
corresponding to the complete screenshot operation, the acquiring screenshot operation of the playing picture of the video data to generate a video screenshot and generate a content label of the video screenshot includes:
acquiring a complete screenshot operation of a playing picture of the video data;
extracting a data frame corresponding to a current playing picture of the video data to be stored as a complete video screenshot;
receiving a type selection operation corresponding to the complete video screenshot, the type selection operation being used to confirm a behavior type tag of the complete video screenshot;
combining the behavior type tag and the corresponding timestamp of the data frame into a content tag of the complete video screenshot;
corresponding to the local screenshot operation, the acquiring screenshot operation of the playing picture of the video data to generate a video screenshot and generate a content label of the video screenshot includes:
acquiring local screenshot operation of a playing picture of the video, and receiving a content label instruction corresponding to the local screenshot operation;
and storing the image data of the image area determined by the local screenshot operation as a local video screenshot, and using a content label confirmed by the content label instruction as a content label of the local video screenshot.
Wherein, the method further comprises:
and receiving a relation label instruction to establish the relation labels among the content labels.
Wherein the local screenshot operation comprises a vehicle screenshot operation;
and receiving a content label instruction for confirmation on a license plate image recognition result of the playing picture by the content label corresponding to the vehicle screenshot operation.
Wherein, the method further comprises:
acquiring a behavior tag type and a timestamp of at least one complete video screenshot;
and inquiring a corresponding association record in an association database corresponding to the behavior tag type according to the timestamp.
Wherein, the method further comprises:
and responding to an original browsing instruction of the complete video screenshot, playing video data corresponding to the complete video screenshot, and starting playing from a time stamp corresponding to the complete video screenshot.
Wherein, the method further comprises:
extracting feature data of at least one video screenshot;
and performing target query in a target data storage area based on the characteristic data.
In a second aspect, an embodiment of the present invention provides a surveillance video data processing apparatus, including:
the system comprises a position marking unit, a data source distribution diagram generating unit and a data source analyzing unit, wherein the position marking unit is used for receiving position marking operation on a data source corresponding to video data and generating a data source distribution diagram corresponding to a target event, and the video data is related monitoring data of the target event;
the track generation unit is used for receiving position nodes of the mobile elements in the video data on a map interface and generating the mobile tracks of the mobile elements on the basis of the map interface according to the receiving time sequence of the position nodes, wherein the receiving time sequence of the position nodes corresponds to the shooting time sequence of the mobile elements;
the screenshot marking unit is used for acquiring screenshot operation of a playing picture of the video data to generate a video screenshot and generate a content label of the video screenshot;
and the data storage unit is used for storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
Wherein the screenshot operation is a complete screenshot operation or a partial screenshot operation;
corresponding to the complete screenshot operation, the screenshot marking unit comprises:
the complete screenshot module is used for acquiring complete screenshot operation of a playing picture of the video data;
the data frame extraction module is used for extracting a data frame corresponding to a current playing picture of the video data to be stored as a complete video screenshot;
a type tag module, configured to receive a type selection operation corresponding to the complete video screenshot, where the type selection operation is used to confirm a behavior type tag of the complete video screenshot;
a complete tag module for combining the behavior type tag and the corresponding timestamp of the data frame into a content tag of the complete video screenshot;
corresponding to the local screenshot operation, the screenshot marking unit comprises:
the local screenshot module is used for acquiring local screenshot operation of a playing picture of the video and receiving a content label instruction corresponding to the local screenshot operation;
and the local label module is used for storing the image data of the image area determined by the local screenshot operation as a local video screenshot and taking a content label confirmed by the content label instruction as a content label of the local video screenshot.
Wherein, the device still includes:
and the relation label unit is used for receiving a relation label instruction so as to establish the relation labels among the content labels.
Wherein the local screenshot operation comprises a vehicle screenshot operation;
and receiving a content label instruction for confirmation on a license plate image recognition result of the playing picture by the content label corresponding to the vehicle screenshot operation.
Wherein, the device still includes:
the complete screenshot obtaining unit is used for obtaining the behavior tag type and the timestamp of at least one complete video screenshot;
and the associated record query unit is used for querying the corresponding associated record in the associated database corresponding to the behavior tag type according to the timestamp.
Wherein, the device still includes:
and the video data playing unit is used for responding to an original browsing instruction of the complete video screenshot, playing the video data corresponding to the complete video screenshot, and starting playing from the time stamp corresponding to the complete video screenshot.
Wherein, the device still includes:
the characteristic extraction unit is used for extracting the characteristic data of at least one video screenshot;
and the target query unit is used for performing target query in the target data storage area based on the characteristic data.
In a third aspect, an embodiment of the present invention provides a terminal device, where the terminal device includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the surveillance video data processing method according to any one of the first aspects.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the surveillance video data processing method according to any one of the first aspect.
According to the monitoring video data processing method, the monitoring video data processing device, the terminal equipment and the storage medium, a data source distribution diagram corresponding to a target event is generated by receiving position marking operation of a data source corresponding to video data, wherein the video data are related monitoring data of the target event; receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element on the basis of the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element; acquiring screenshot operation of a playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot; and storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event. The presentation of a large amount of monitoring video data contents is better displayed, and a better analysis effect and communication efficiency of the monitoring video are obtained.
Drawings
Fig. 1 is a flowchart of a monitoring video data processing method according to an embodiment of the present invention;
fig. 2 is a flowchart of a monitoring video data processing method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a surveillance video data processing apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a terminal device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are for purposes of illustration and not limitation. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a monitoring video data processing method according to an embodiment of the present invention. The surveillance video data processing method provided in the embodiments may be executed by a surveillance video data processing device, the surveillance video data processing device may be implemented by software and/or hardware, and the surveillance video data processing device may be formed by two or more physical entities or may be formed by one physical entity. For example, the surveillance video data processing device may be a cell phone, an industrial control computer, or the like.
Specifically, referring to fig. 1, the method for processing surveillance video data specifically includes:
step S101, receiving position marking operation of a data source corresponding to video data, and generating a data source distribution diagram corresponding to a target event, wherein the video data is related monitoring data of the target event.
In the video data analysis process based on the target event, video data collected by a camera in the occurrence place and the occurrence time period of the target event are collected integrally, and then the collected data are screened manually. A simple screening method is to discard the video data without the content related to the target event and to retain the video data with the content related to the target event. Another complicated screening method is to discard video data that obviously has no content related to the target event, retain video data that may have content related to the target event and mark the video data with suspicion (for example, pending, suspected, and possible), and mark the video data that obviously has content related to the target event with certainty. The video data retained after screening can be copied to a separate folder for storage, or the original storage state of the video data can be maintained, and meanwhile, the association relationship between the target event and the corresponding video data is established, so that the corresponding video data can be directly viewed through the association relationship when the video data is analyzed. Of course, the association relationship may further set a literal expression for describing the general content in the management list of the target event. The viewing of the video data is realized in a data interaction interface, in the data interaction interface, most areas are used as video playing areas for displaying the video data, a control for receiving instructions is displayed in the area at the periphery of the video playing areas, and when the control is triggered, corresponding instructions, such as screenshot, marking, map displaying and the like, are executed. Of course, part of the control can also be displayed at the top of the video playing area during video playing, and the control is also used for receiving instructions.
On the basis of data screening, each data source corresponding to the video data related to the target event is subjected to position marking operation, and a data source distribution diagram for the target event is generated based on the position marking operation. The data source corresponding to the video data is the corresponding camera, and the data source distribution diagram is actually the distribution diagram corresponding to the position of the camera. The data source distribution map may be specifically presented based on map marks, may be presented in the form of a statistical graph, or may be presented in the form of a statistical table. On the basis of the data source distribution graph, comprehensive statistics can be performed on the data source distribution graph corresponding to a plurality of target events, namely on the basis of performing camera position marking on a single target event, statistics on a certain camera or a certain region is performed.
Step S102, receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element based on the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element.
When a certain target event is analyzed based on a plurality of video data, people or vehicles related to the target event need to be tracked, and the conventional processing mode is that a moving track is manually drawn according to the watching content and the watching progress in the process of watching the video, so that the track is inconvenient to adjust and update. In the scheme, the node receiving the position on the map interface can be an address name input according to video content or a position selected on a map, and certainly, if the two modes are adopted, the time when the mobile element appears at the address and is collected by video data is required to be input as reference information of the receiving time sequence of the position node, so that the shooting time sequence of the mobile element is determined. In addition, the receiving position confirmation instruction confirms that the position node needs to be generated based on the content of the currently played video data, and at this time, the data source of the currently played video data can be read to obtain the position node and the corresponding shooting time as the reference information of the receiving time sequence.
The receiving time sequence in the scheme is not a time sequence for marking the position nodes, but a time sequence of the appearance of the moving target in each position node, and the sequence is unrelated to the viewing sequence and the operation sequence of the user. For example, if the user marks that the moving element appears at the place A at 9:20, the place C at 10:03 and the place B at 9:46 on the same day in turn, based on the three position nodes, the moving track of the moving element is A → B → C, and the reason for the marking sequence is only because the viewing sequence is different.
And S103, acquiring screenshot operation of the playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot.
In the specific screenshot operation, the method is mainly divided into a complete screenshot operation and a partial screenshot operation. The complete screenshot operation realizes the screenshot of the whole frame image, and is mainly in the whole frame image. It should be noted that, for a frame of image, the screenshot may be performed on the whole frame, or the screenshot may be performed on a part of the content in the frame, that is, more than one screenshot operation may be performed on one frame of image, and a plurality of partial content may be respectively corresponding to the screenshot, so that a plurality of partial screenshot operations are performed.
The screenshot operation is a complete screenshot operation or a partial screenshot operation;
corresponding to the full screenshot operation, the step S103 includes:
acquiring a complete screenshot operation of a playing picture of the video data;
extracting a data frame corresponding to a current playing picture of the video data to be stored as a complete video screenshot;
receiving a type selection operation corresponding to the complete video screenshot, the type selection operation being used to confirm a behavior type tag of the complete video screenshot;
and combining the behavior type tag and the corresponding timestamp of the data frame into a content tag of the complete video screenshot.
Generally, the full screenshot operation is mainly used for extracting behavior information related to a target event. For example, the target event is a theft event, and when a certain frame is shot to start theft or a stolen object transfer occurs in a certain frame, the frames can be marked for subsequent emphasis analysis of the video segment started thereby. At this time, the complete screenshot operation can be triggered through a control or a shortcut key corresponding to the complete screenshot operation, and a data frame corresponding to the currently played picture is extracted from the data frame and stored separately to obtain a complete video screenshot.
Corresponding to the partial screenshot operation, the step S103 includes:
acquiring local screenshot operation of a playing picture of the video, and receiving a content label instruction corresponding to the local screenshot operation;
and storing the image data of the image area determined by the local screenshot operation as a local video screenshot, and using a content label confirmed by the content label instruction as a content label of the local video screenshot.
Generally, the local screenshot operation is mainly used for recording element information related to the target event in a highlight mode. In contrast to the association of the full video screenshot with the behavior type in the target event, the partial video screenshot corresponds to the element information in the target event, and the element information mainly refers to people (e.g., suspects, victims) and things (e.g., vehicles, dirt) appearing in the target event. When important people or objects appear in the playing picture, a partial image area in the playing picture can be selected through local screenshot operation, the image upper protective clothing in the partial image area is stored as a local video screenshot, and on the basis of responding to the local screenshot operation, a content label instruction is received to confirm a content label of the local video screenshot. The setting of the content tab and the setting type of the operation type may be selected from the set tabs or may be a custom input.
And S104, storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
And correspondingly generating a data source distribution diagram, a moving track and a video screenshot on the basis of the position marking operation, the position node receiving operation and the screenshot operation, wherein the derived information is used as key information which possibly plays a key role in processing a target event in the associated video data, and the derived information is stored by taking the event as a unit in the scheme.
If a plurality of users take the hands to check the video data corresponding to one target event, the first user can mark the video data according to the set standard, and when the subsequent users continue to check the video data corresponding to the target event, the combing result obtained by the previous user can be quickly obtained according to the standard. Even without the set marking criteria, the previous combing result can be confirmed by a simple hand-off with the previous user, thereby quickly taking over the subsequent combing of the same target event. After the video data of the whole target event are combed, the information is convenient to summarize and exchange, and the cooperative processing of the video data of the same target event and the rapid sharing analysis of the processing result by multiple people are realized.
In the above, a data source distribution map corresponding to a target event is generated by receiving a position marking operation on a data source corresponding to video data, where the video data is associated with monitoring data of the target event; receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element on the basis of the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element; acquiring screenshot operation of a playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot; and storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event. The presentation of a large amount of monitoring video data contents is better displayed, and a better analysis effect and communication efficiency of the monitoring video are obtained.
Example two
Fig. 2 is a flowchart of a monitoring video data processing method according to a second embodiment of the present invention. The present embodiment is embodied on the basis of the above-described embodiments.
Specifically, referring to fig. 2, the method for processing surveillance video data provided in this embodiment specifically includes:
step S201, receiving a position marking operation for a data source corresponding to the video data, and generating a data source distribution map corresponding to the target event.
On the basis of each target event, comprehensive statistics can be performed on a data source distribution graph corresponding to target time within a time period, which data sources or data sources within which geographic range are associated with more target events is judged, and therefore, a management strategy is optimized for the geographic range, and a normal order is maintained, for example, patrol is enhanced, early warning analysis on video data from the geographic range is improved, more cameras are added as data sources, and the like.
Step S202, receiving position nodes of the mobile elements in the video data on a map interface, and generating the mobile tracks of the mobile elements on the basis of the map interface according to the receiving time sequence of the position nodes.
The data interaction interface can be realized in a multi-user operation mode, namely, a plurality of users access video data of the same target time relevance degree and carry out related marking under the same standard. When the multi-user cooperative operation is carried out, the position nodes marked by all users are received in real time, and corresponding time parameters also need to be input when each user marks the position nodes. Because the time parameters come from the same time axis, even if a plurality of users randomly access the video data to perform screenshot marking, the moving track can still be accurately generated due to the time sequence confirmed by the same time axis.
Step 203, obtaining a screenshot operation of the playing image of the video data to generate a video screenshot, and generating a content label of the video screenshot.
In the process of implementing the screenshot, more specific labels can be available. For example, original screenshots of case-involved videos are used for storing video screenshots of key actions in the case making process. The video picture contains key information such as time, place and the like, and key nodes can be quickly found when the video needs to be browsed again subsequently.
For another example, the suspect human appearance feature image screenshot is used for screenshot of clear human appearance features of the person involved in the case. In the video picture, the number of the possibly appeared personnel is large, and the relation among the personnel such as the perpetrator, the victim, the fellow and the like is marked through screenshot, so that the cooperative investigation of multiple people is facilitated. In addition, key personnel in the picture may not see the whole appearance clearly due to factors such as monitoring angles, light rays and positions, and the like, and the relatively clear appearance features can be captured, so that the wearing features of the suspect can be rapidly extracted by using a structuring technology, and the like to perform big data retrieval and analysis.
Specifically aiming at the face characteristics of the suspect, the clear face of the person involved in the case in the video picture can be captured. At the present stage, public security big data is developed quite mature, and once a clear human face can be captured in a video picture, the method can be basically equal to solving a case. The identity of the suspect can be quickly confirmed by the face recognition technology.
And the screenshot of the involved transportation means is that the screenshot of the key involved transportation means appearing in the video picture is carried out. For example, if the number plate number can be seen in the screenshot, the checkpoint snapshot on the trunk road is retrieved to find the parking track of the vehicle and even the identity of the owner of the vehicle; if the characteristics of the non-motor vehicles can be clearly seen in the screenshot, all the peripheral videos can be analyzed and retrieved by utilizing a vehicle structuring technology, and clues are provided for case detection. Particularly for vehicle screenshot operation, after finishing screenshot of a vehicle, the corresponding content tag can be directly confirmed from a list of license plate recognition results, and if necessary, a vehicle description, such as a vehicle for which behavior link in a target time, can be further added on the basis of the selected license plate recognition result.
Additionally, there are screenshots of touching/discarding items, which are used to screen certain items in the video that were touched by the key character, or to screen discarding items. For example, the video shoots the articles such as cigarette ends and mineral water bottles discarded by the involved personnel, and the field investigation personnel can be guided to extract fingerprints or DNA from the articles, so that effective information is provided for identity confirmation.
Other examples are screenshots of the communication tool, especially screenshots of actions of calling a telephone by a person involved in a case in a video picture.
If necessary, screenshots of the tracking place, namely screenshots of the places where the suspected persons enter and exit can be also taken. Such screenshots may direct scout personnel to conduct a lead look-up of personnel, video or check-in systems of the relevant venue. For example, if a suspected person enters an internet cafe or a hotel, the scope of the suspected person can be narrowed down by the registration system of the internet cafe or the hotel.
And S204, storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
Step S205, receiving a relation label instruction to establish a relation label between the content labels.
And the relation label instruction is used for establishing the incidence relation among the object elements along with the deep mining of the information so as to visually express and view the relation among the individuals, thereby forming a complete event context.
And S206, acquiring the behavior tag type and the time stamp of at least one complete video screenshot.
And step S207, inquiring a corresponding association record in an association database corresponding to the behavior tag type according to the timestamp.
For example, for a behavior tag of a call, a subsequent investigation staff can make a query request to the technical investigation part according to the time and the place of the call, and analyze the contact object or content of the involved staff through the data of the peripheral base station.
And S208, responding to the original browsing instruction of the complete video screenshot, playing the video data corresponding to the complete video screenshot, and starting playing from the time stamp corresponding to the complete video screenshot.
The processing process of the monitoring video data related to the target event may not be a one-step process, the monitoring video data may need to be checked for many times when the analysis of one target event is completed, especially for the monitoring video data of the key segment, information needs to be extracted repeatedly, and in order to improve the playing efficiency of the key segment, the playing can be started from a specific moment quickly through the timestamp of the corresponding record of the complete video screenshot. That is, the timestamp records not only a time parameter, but also a specific playing node of the surveillance video data from which the complete video screenshot is recorded, and the corresponding surveillance video data can be directly accessed through the timestamp and played from the specific playing node.
And S209, extracting the characteristic data of at least one video screenshot.
And step S210, performing target query in a target data storage area based on the characteristic data.
On the basis of processing the monitoring video data, comprehensive analysis can be further performed by combining with other image data, specifically, the obtained video screenshot is taken as a sample to perform reference of other related data, for example, whether a certain vehicle is a stolen vehicle recorded on a case or not is inquired, whether a certain face image is matched with an image recorded in a missing population database or not is inquired, and the like.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a surveillance video data processing apparatus according to a third embodiment of the present invention. Referring to fig. 3, the surveillance video data processing apparatus includes: a position marking unit 310, a trajectory generating unit 320, a screenshot marking unit 330, and a data storage unit 340.
The position marking unit 310 is configured to receive a position marking operation on a data source corresponding to video data, and generate a data source distribution map corresponding to a target event, where the video data is associated with monitoring data of the target event; a track generating unit 320, configured to receive, at a map interface, a position node of a mobile element in the video data, and generate a moving track of the mobile element based on the map interface according to a receiving timing sequence of the position node, where the receiving timing sequence of the position node corresponds to a shooting timing sequence of the mobile element; a screenshot marking unit 330, configured to obtain a screenshot operation on a playing screen of the video data to generate a video screenshot, and generate a content tag of the video screenshot; and a data storage unit 340, configured to store the data source distribution map, the movement track, the video screenshot, and the corresponding content tag in a storage area corresponding to the target event.
On the basis of the embodiment, the screenshot operation is a complete screenshot operation or a partial screenshot operation;
corresponding to the full screenshot operation, the screenshot marking unit 330 includes:
the complete screenshot module is used for acquiring complete screenshot operation of a playing picture of the video data;
the data frame extraction module is used for extracting a data frame corresponding to a current playing picture of the video data to be stored as a complete video screenshot;
a type tag module, configured to receive a type selection operation corresponding to the complete video screenshot, where the type selection operation is used to confirm a behavior type tag of the complete video screenshot;
a complete tag module for combining the behavior type tag and the corresponding timestamp of the data frame into a content tag of the complete video screenshot;
corresponding to the partial screenshot operation, the screenshot marking unit 330 includes:
the local screenshot module is used for acquiring local screenshot operation of a playing picture of the video and receiving a content label instruction corresponding to the local screenshot operation;
and the local label module is used for storing the image data of the image area determined by the local screenshot operation as a local video screenshot and taking a content label confirmed by the content label instruction as a content label of the local video screenshot.
On the basis of the above embodiment, the apparatus further includes:
and the relation label unit is used for receiving a relation label instruction so as to establish the relation labels among the content labels.
On the basis of the above embodiment, the local screenshot operation includes a vehicle screenshot operation;
and receiving a content label instruction for confirmation on a license plate image recognition result of the playing picture by the content label corresponding to the vehicle screenshot operation.
On the basis of the above embodiment, the apparatus further includes:
the complete screenshot obtaining unit is used for obtaining the behavior tag type and the timestamp of at least one complete video screenshot;
and the associated record query unit is used for querying the corresponding associated record in the associated database corresponding to the behavior tag type according to the timestamp.
On the basis of the above embodiment, the apparatus further includes:
and the video data playing unit is used for responding to an original browsing instruction of the complete video screenshot, playing the video data corresponding to the complete video screenshot, and starting playing from the time stamp corresponding to the complete video screenshot.
On the basis of the above embodiment, the apparatus further includes:
the characteristic extraction unit is used for extracting the characteristic data of at least one video screenshot;
and the target query unit is used for performing target query in the target data storage area based on the characteristic data.
The monitoring video data processing device provided by the embodiment of the invention is contained in monitoring video data processing equipment, can be used for executing the monitoring video data processing method provided by any embodiment, and has corresponding functions and beneficial effects.
Example four
Fig. 4 is a schematic structural diagram of a terminal device according to a fourth embodiment of the present invention, where the terminal device is a specific hardware presentation scheme of the foregoing surveillance video data processing device. As shown in fig. 4, the terminal device includes a processor 410, a memory 420, an input means 430, an output means 440, and a communication means 450; the number of the processors 410 in the terminal device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430, the output device 440 and the communication device 450 in the terminal equipment may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 4.
The memory 420 serves as a computer-readable storage medium, and may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the surveillance video data processing method in the embodiment of the present invention (e.g., the position marking unit 310, the trajectory generating unit 320, the screenshot marking unit 330, and the data storage unit 340 in the surveillance video data processing apparatus). The processor 410 executes various functional applications and data processing of the terminal device by executing software programs, instructions and modules stored in the memory 420, that is, implements the above-described monitoring video data processing method.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to a terminal device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the terminal device. The output device 440 may include a display device such as a display screen.
The terminal equipment comprises a monitoring video data processing device, can be used for executing any monitoring video data processing method, and has corresponding functions and beneficial effects.
EXAMPLE five
Embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for processing surveillance video data, the method including:
receiving position marking operation of a data source corresponding to video data, and generating a data source distribution diagram corresponding to a target event, wherein the video data is associated monitoring data of the target event;
receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element on the basis of the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element;
acquiring screenshot operation of a playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot;
and storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the surveillance video data processing method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the monitoring video data processing apparatus, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A surveillance video data processing method, comprising:
receiving position marking operation of a data source corresponding to video data, and generating a data source distribution diagram corresponding to a target event, wherein the video data is associated monitoring data of the target event;
receiving a position node of a mobile element in the video data on a map interface, and generating a moving track of the mobile element on the basis of the map interface according to a receiving time sequence of the position node, wherein the receiving time sequence of the position node corresponds to a shooting time sequence of the mobile element;
acquiring screenshot operation of a playing picture of the video data to generate a video screenshot, and generating a content label of the video screenshot;
and storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
2. The method of claim 1, wherein the screenshot operation is a full screenshot operation or a partial screenshot operation;
corresponding to the complete screenshot operation, the acquiring screenshot operation of the playing picture of the video data to generate a video screenshot and generate a content label of the video screenshot includes:
acquiring a complete screenshot operation of a playing picture of the video data;
extracting a data frame corresponding to a current playing picture of the video data to be stored as a complete video screenshot;
receiving a type selection operation corresponding to the complete video screenshot, the type selection operation being used to confirm a behavior type tag of the complete video screenshot;
combining the behavior type tag and the corresponding timestamp of the data frame into a content tag of the complete video screenshot;
corresponding to the local screenshot operation, the acquiring screenshot operation of the playing picture of the video data to generate a video screenshot and generate a content label of the video screenshot includes:
acquiring local screenshot operation of a playing picture of the video, and receiving a content label instruction corresponding to the local screenshot operation;
and storing the image data of the image area determined by the local screenshot operation as a local video screenshot, and using a content label confirmed by the content label instruction as a content label of the local video screenshot.
3. The method of claim 1, further comprising:
and receiving a relation label instruction to establish the relation labels among the content labels.
4. The method of claim 2, wherein the partial screenshot operation comprises a vehicle screenshot operation;
and receiving a content label instruction for confirmation on a license plate image recognition result of the playing picture by the content label corresponding to the vehicle screenshot operation.
5. The method of claim 2, further comprising:
acquiring a behavior tag type and a timestamp of at least one complete video screenshot;
and inquiring a corresponding association record in an association database corresponding to the behavior tag type according to the timestamp.
6. The method of claim 2, further comprising:
and responding to an original browsing instruction of the complete video screenshot, playing video data corresponding to the complete video screenshot, and starting playing from a time stamp corresponding to the complete video screenshot.
7. The method of claim 1, further comprising:
extracting feature data of at least one video screenshot;
and performing target query in a target data storage area based on the characteristic data.
8. A surveillance video data processing apparatus, comprising:
the system comprises a position marking unit, a data source distribution diagram generating unit and a data source analyzing unit, wherein the position marking unit is used for receiving position marking operation on a data source corresponding to video data and generating a data source distribution diagram corresponding to a target event, and the video data is related monitoring data of the target event;
the track generation unit is used for receiving position nodes of the mobile elements in the video data on a map interface and generating the mobile tracks of the mobile elements on the basis of the map interface according to the receiving time sequence of the position nodes, wherein the receiving time sequence of the position nodes corresponds to the shooting time sequence of the mobile elements;
the screenshot marking unit is used for acquiring screenshot operation of a playing picture of the video data to generate a video screenshot and generate a content label of the video screenshot;
and the data storage unit is used for storing the data source distribution diagram, the moving track, the video screenshot and the corresponding content label into a storage area corresponding to the target event.
9. A terminal device, characterized in that the terminal device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the surveillance video data processing method as recited in any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the surveillance video data processing method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011225551.XA CN112383751A (en) | 2020-11-05 | 2020-11-05 | Monitoring video data processing method and device, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011225551.XA CN112383751A (en) | 2020-11-05 | 2020-11-05 | Monitoring video data processing method and device, terminal equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112383751A true CN112383751A (en) | 2021-02-19 |
Family
ID=74578344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011225551.XA Pending CN112383751A (en) | 2020-11-05 | 2020-11-05 | Monitoring video data processing method and device, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112383751A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255477A (en) * | 2021-05-08 | 2021-08-13 | 深圳市安软科技股份有限公司 | Comprehensive management system and method for pedestrian video images |
| CN114003672A (en) * | 2021-10-22 | 2022-02-01 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for processing road dynamic event |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103237201A (en) * | 2013-04-28 | 2013-08-07 | 江苏物联网研究发展中心 | Case video studying and judging method based on social annotation |
| CN103955494A (en) * | 2014-04-18 | 2014-07-30 | 大唐联智信息技术有限公司 | Searching method and device of target object and terminal |
| CN104185073A (en) * | 2014-08-04 | 2014-12-03 | 北京奇虎科技有限公司 | Method and client for playing video by selecting corresponding video progress through picture |
| CN107194006A (en) * | 2017-06-19 | 2017-09-22 | 深圳警翼智能科技股份有限公司 | A kind of video features structural management method |
| WO2020114128A1 (en) * | 2018-12-06 | 2020-06-11 | 西安光启未来技术研究院 | Map drawing method and apparatus, storage medium and electronic apparatus |
-
2020
- 2020-11-05 CN CN202011225551.XA patent/CN112383751A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103237201A (en) * | 2013-04-28 | 2013-08-07 | 江苏物联网研究发展中心 | Case video studying and judging method based on social annotation |
| CN103955494A (en) * | 2014-04-18 | 2014-07-30 | 大唐联智信息技术有限公司 | Searching method and device of target object and terminal |
| CN104185073A (en) * | 2014-08-04 | 2014-12-03 | 北京奇虎科技有限公司 | Method and client for playing video by selecting corresponding video progress through picture |
| CN107194006A (en) * | 2017-06-19 | 2017-09-22 | 深圳警翼智能科技股份有限公司 | A kind of video features structural management method |
| WO2020114128A1 (en) * | 2018-12-06 | 2020-06-11 | 西安光启未来技术研究院 | Map drawing method and apparatus, storage medium and electronic apparatus |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255477A (en) * | 2021-05-08 | 2021-08-13 | 深圳市安软科技股份有限公司 | Comprehensive management system and method for pedestrian video images |
| CN114003672A (en) * | 2021-10-22 | 2022-02-01 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for processing road dynamic event |
| CN114003672B (en) * | 2021-10-22 | 2023-04-07 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for processing road dynamic event |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2760211C2 (en) | Analytical recognition system | |
| US20220092881A1 (en) | Method and apparatus for behavior analysis, electronic apparatus, storage medium, and computer program | |
| CN111131902B (en) | Method for determining target object information and video playing equipment | |
| WO2019104949A1 (en) | Residential entrance access control system which achieves human big data acquisition and analysis | |
| CN109033440A (en) | A kind of video investigation multidimensional trajectory analysis method | |
| CN110263613A (en) | Monitor video processing method and processing device | |
| US20210357678A1 (en) | Information processing method and apparatus, and storage medium | |
| CN111222373B (en) | Personnel behavior analysis method and device and electronic equipment | |
| WO2020114138A1 (en) | Information associated analysis method and apparatus, and storage medium and electronic device | |
| EP3479270B1 (en) | Incident response analytic maps | |
| CN108540752B (en) | Method, device and system for identifying target object in video monitoring | |
| CN104320638A (en) | Intelligent integrated monitoring and controlling system and surveillance video processing method | |
| CN111090777B (en) | Video data management method, management equipment and computer storage medium | |
| CN112383751A (en) | Monitoring video data processing method and device, terminal equipment and storage medium | |
| CN114093014A (en) | Graph code correlation strength calculation method, device, equipment and storage medium | |
| CN109492604A (en) | Faceform's characteristic statistics analysis system | |
| CN110442742A (en) | Retrieve method and device, processor, electronic equipment and the storage medium of image | |
| CN107426442A (en) | The information gathering of mobile phone full system type pictorial and recognition of face analyses and comparison system and application method | |
| CN103177436A (en) | Method, system, computer program product and recording medium for object tracking | |
| CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
| US20210089784A1 (en) | System and Method for Processing Video Data from Archive | |
| CN111767432B (en) | Co-occurrence object searching method and device | |
| CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
| CN111026909B (en) | Method for supplementing public security investigation data set based on self-timer tremble sound view | |
| CN111291087A (en) | Information pushing method and device based on face detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 306, zone 2, building 1, Fanshan entrepreneurship center, Panyu energy saving technology park, No. 832 Yingbin Road, Donghuan street, Panyu District, Guangzhou City, Guangdong Province Applicant after: Jiadu Technology Group Co.,Ltd. Address before: Room 306, zone 2, building 1, Fanshan entrepreneurship center, Panyu energy saving technology park, No. 832 Yingbin Road, Donghuan street, Panyu District, Guangzhou City, Guangdong Province Applicant before: PCI-SUNTEKTECH Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210219 |
|
| RJ01 | Rejection of invention patent application after publication |