CN114705178A - Target analysis method based on video track and MAC data - Google Patents

Abstract

A target analysis method based on video fusion track and MAC data combines a large amount of monitoring and data acquisition and analysis equipment, and video image structured data application establishes a multidimensional data track database. And analyzing and determining the accurate track of the personnel through multi-dimensional big data and an algorithm, extracting MAC information around the track by combining the track of the personnel, analyzing and determining the MAC address of the target mobile phone. According to the method, the accurate track is precipitated through a large amount of multi-dimensional sensing data, and compared with the reliability of a single-dimensional track, the reliability is higher, and the track is more accurate.

Description

A Target Analysis Method Based on Video Trajectory and MAC Data

technical field

The invention relates to the field of data analysis, in particular to a target analysis method based on video track and MAC data.

Background technique

The MAC address is the physical address solidified in the serial EEPROM on the network card. The identification of the Internet site is used to define the location of the network device. The MAC address of any network device (such as a mobile computer) is unique and cannot be changed. The MAC address is like a resident's ID number is the same.

In view of the fact that the network has been integrated into the lives of most people, how to quickly and effectively identify and track the target MAC is also very important. However, in the existing target analysis technology, the MAC address is not used. Based on this background, the original intention of the present invention is to provide a A target analysis method based on video trajectories and MAC data.

SUMMARY OF THE INVENTION

In view of the above problems, the present invention is proposed to provide a target analysis method based on video track and MAC data that overcomes the above problems or at least partially solves the above problems.

In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

A target analysis method based on video track and MAC data, comprising:

S100. Collect data through a standard data interface based on video resources, geographic information and trajectory information;

S200. Perform structured analysis on the collected data to obtain a multi-dimensional database based on video resources, geographic information and trajectory information;

S300. Draw the coordinates of time and space on the multi-dimensional database to obtain the multi-dimensional trajectory library of the target;

S400. Based on the video trajectory of the target, fuse various trajectories in the multi-dimensional trajectory library to collide with the accurate multi-dimensional trajectory of the target;

S500. Based on the precise target trajectory formed by video tracking, and the MAC address trajectory library obtained by extracting the surrounding MAC addresses of the video, according to the first parameter group, using the trajectory comparison rules of big data analysis, cyclically compare the accuracy of each group Track and MAC track, realize collision analysis of precise track and MAC track;

S600. Using the multi-dimensional front-end perception data gathered in the video image information database, combined with the relevant system personnel information database and the MAC address database, the relationship topology of the data can be realized, and the target can be tracked.

Further, the video resources include at least: networked video resources, networked bayonet resources, social resources, wifi probes and fences.

Further, in S100, the geographic information includes at least: case geographic information, camera and bayonet geographic information, drone aerial photography information, on-site exploration geographic information, and electrical enclosure geographic information.

Further, in S100, the track information at least includes: taxi GPS information, rental car GPS information, bus IC card track information, and mobile phone base station track information.

Further, the specific method of S300 is: by uploading the target face or vehicle, extracting the target face feature value, license plate and behavioral characteristics, based on the data collected by the monitoring equipment, according to the time and place of the target appearance, using the collected multi-dimensional data. The target performs multi-dimensional tracking, analyzes the spatial coordinates of the target in the camera coordinate system, and performs coordinate transformation and calibration through time and space to obtain a set of target motion trajectory points to form a target multi-dimensional trajectory library.

Further, S400 specifically includes: finding the target by viewing the video, forming a video track of the target, and performing collision analysis based on the longitude and latitude information of the video track and the face information, vehicle information, and survey map information in the multi-dimensional trajectory database to form a more complete and accurate image. multidimensional trajectory.

Further, in S500, the first parameter group at least includes: smoothness, distance longitude, matching threshold, correlation interval, and error range.

Further, in S500, the collision analysis of the video track and the MAC track includes: extracting retrieval conditions according to the precise video track, recording the number of occurrences of each MAC address in the coordinate space, according to the collection time, in combination with each MAC address in each The existence of each point in the scene draws the MAC address trajectory to form a possible target MAC address trajectory library.

Further, in S500, the collision analysis of the video track and the MAC track further includes: after the collision analysis of the video track and the MAC track, find out the MAC track route with high track similarity and high time and place matching degree through comparison, and find the MAC track route. The suspected target MAC address information is displayed.

The beneficial effects of the above technical solutions provided by the embodiments of the present invention include at least:

The invention discloses a target analysis method based on video fusion track and MAC data. Based on video resources, geographic information and track information, data is collected through a standard data interface; Multi-dimensional database of resources, geographic information and trajectory information; draw the coordinates of time and space on the multi-dimensional database to obtain the multi-dimensional trajectory library of the target; based on the video trajectory of the target, fuse various trajectories in the multi-dimensional trajectory database to collide with the target's accurate multi-dimensional trajectory ; Based on the precise target trajectory formed by video tracking, and the MAC address trajectory library obtained by extracting the surrounding MAC addresses of the video, according to the first parameter group, using the trajectory comparison rules of big data analysis, cyclically compare each group of video trajectories And MAC trajectory, to achieve accurate trajectory and MAC trajectory collision analysis; using the multi-dimensional front-end perception data aggregated in the video image information database, combined with the relevant system personnel information database and MAC address database, the relationship topology of the data can be realized, and the target can be tracked. Compared with the reliability of the single-dimensional trajectory, the accurate trajectory precipitated by the present invention is more reliable and the trajectory is more accurate.

The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the attached image:

FIG. 1 is a flowchart of a target analysis method based on video track and MAC data in Embodiment 1 of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

In order to solve the problems existing in the prior art, an embodiment of the present invention provides a target analysis method based on video track and MAC data.

Example 1

This embodiment discloses a target analysis method based on video track and MAC data, as shown in Figure 1, including:

S100. Collect data through a standard data interface based on video resources, geographic information and trajectory information; specifically, the video resources at least include: networked video resources, networked bayonet resources, social resources, wifi probes and fences. Geographical information includes at least: geographic information of the case, geographic information of cameras and bayonet, aerial photography information of drones, geographic information of on-site exploration, and geographic information of electric enclosures. The track information at least includes: taxi GPS information, rental car GPS information, bus IC card track information, and mobile phone base station track information.

S200. Carry out structured analysis on the collected data to obtain a multi-dimensional database based on video resources, geographic information and trajectory information; Resource point, WIFI fence probe), realize data aggregation, unified interface service, realize data retrieval (time, location, portrait, etc.) through the system, through structured analysis, multi-dimensional data (face, vehicle, video, etc.) in video images , MAC, etc.) are stored in the database according to the standard data format required by the relevant departments, and the system is required to support multi-dimensional retrieval and data analysis and comparison.

S300. Draw the coordinates of time and space on the multi-dimensional database to obtain the multi-dimensional trajectory library of the target; in this embodiment, the specific method of S300 is: by uploading the target face or vehicle, extracting the target face feature value, license plate and behavior Features, based on the data collected by the monitoring equipment, according to the time and place of the target appearance, use the collected multidimensional data to track the target in multiple dimensions, analyze the spatial coordinates of the target in the camera coordinate system, and perform coordinate transformation through time, space, etc. And proofreading, get the target motion trajectory point set, forming a target multi-dimensional trajectory library.

S400. Based on the video trajectory of the target, fuse various trajectories in the multi-dimensional trajectory library to collide with the accurate multi-dimensional trajectory of the target. In this embodiment, S400 specifically includes: finding the target by viewing the video, forming a video track of the target, and performing collision analysis based on the longitude and latitude information of the video track and the face information, vehicle information, and survey map information in the multi-dimensional trajectory database, and forming More perfect and accurate multi-dimensional trajectory.

S500. Based on the precise target trajectory formed by video tracking, and the MAC address trajectory library obtained by extracting the surrounding MAC addresses of the video, according to the first parameter group, using the trajectory comparison rules of big data analysis, cyclically compare the accuracy of each group Track and MAC track, realize collision analysis of precise track and MAC track;

In this embodiment, the collision analysis of the video track and the MAC track includes: extracting retrieval conditions according to the precise video track, recording the number of occurrences of each MAC address in the coordinate space, and combining with the time of collection according to each MAC address in each The existence of each point in the scene draws the MAC address trajectory to form a possible target MAC address trajectory library.

In S500 of this embodiment, the collision analysis between the video track and the MAC track further includes: after the collision analysis between the video track and the MAC track, find out the MAC track route with high track similarity and high time and place matching degree through comparison. to find out the suspected target MAC address information.

S600. Using the multi-dimensional front-end perception data gathered in the video image information database, combined with the relevant system personnel information database and the MAC address database, the relationship topology of the data can be realized, and the target can be tracked. Specifically, based on the precise target trajectory formed by video tracking, and the MAC address trajectory library obtained by extracting the surrounding MAC addresses of the video, according to smoothness, distance longitude, matching threshold, correlation interval, and error range, the trajectory using big data analysis Compare the rules, cyclically compare each group of video tracks and MAC tracks, and realize the collision analysis of the video track and the MAC track. destination MAC address information.

A target analysis method based on video fusion track and MAC data disclosed in this embodiment, based on video resources, geographic information and track information, collects data through a standard data interface; Multi-dimensional database of video resources, geographic information and trajectory information; draw the coordinates of time and space on the multi-dimensional database to obtain the multi-dimensional trajectory library of the target; based on the video trajectory of the target, integrate various trajectories in the multi-dimensional trajectory library to collide with the target to obtain accurate multi-dimensional Track; based on the precise target track formed by video tracking, and the MAC address track library obtained by extracting the surrounding MAC addresses of the video, according to the first parameter group, using the track comparison rules of big data analysis, cyclically compare each group of videos Track and MAC track to achieve collision analysis of precise track and MAC track; use the multi-dimensional front-end perception data gathered in the video image information database, combined with the relevant system personnel information database and MAC address database to realize the data relationship topology and track the target. . Compared with the reliability of the single-dimensional trajectory, the accurate trajectory precipitated by the present invention is more reliable and the trajectory is more accurate.

It is understood that the specific order or hierarchy of steps in the disclosed processes is an example of a sample approach. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy presented.

In the foregoing Detailed Description, various features are grouped together in a single embodiment for the purpose of simplifying the disclosure. This method of disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, present invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the Detailed Description, with each claim standing on its own as a separate preferred embodiment of this invention.

Those skilled in the art will also appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments herein may be implemented as electronic hardware, computer software, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, however, such implementation decisions should not be interpreted as a departure from the scope of the present disclosure.

The steps of a method or algorithm described in connection with the embodiments herein may be directly embodied in hardware, a software module executed by a processor, or a combination thereof. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium may reside in an ASIC. The ASIC may be located in the user terminal. Of course, the processor and the storage medium may also exist in the user terminal as discrete components.

For a software implementation, the techniques described in this application may be implemented in modules (eg, procedures, functions, etc.) that perform the functions described in this application. These software codes may be stored in a memory unit and executed by a processor. The memory unit may be implemented within the processor or external to the processor, in which case it is communicatively coupled to the processor via various means, as is known in the art.

The above description includes examples of one or more embodiments. Of course, it is not possible to describe all possible combinations of components or methods in order to describe the above embodiments, but one of ordinary skill in the art will recognize that further combinations and permutations of the various embodiments are possible. Accordingly, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of the appended claims. Furthermore, with respect to the term "comprising," as used in the specification or claims, the word is encompassed in a manner similar to the term "comprising," as if "comprising," were construed when used as a conjunction in the claims. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or."

Claims (9)

1. A target analysis method based on video track and MAC data is characterized by comprising the following steps:

s100, collecting data through a standard data interface based on video resources, geographic information and track information;

s200, performing structured analysis on the acquired data to obtain a multi-dimensional database based on video resources, geographic information and track information;

s300, drawing time and space coordinates of the multi-dimensional database to obtain a multi-dimensional track database of the target;

s400, fusing various tracks in a multi-dimensional track library to collide with an accurate multi-dimensional track of a target based on the video track of the target;

s500, performing cyclic comparison on each group of accurate tracks and MAC tracks by using track comparison rules of big data analysis according to a first parameter group based on an accurate target track formed by video tracking and an MAC address track library obtained by extracting peripheral MAC addresses of the video, so as to realize collision analysis of the accurate tracks and the MAC tracks;

s600, relational topology of data can be achieved by means of the multi-dimensional front-end sensing data gathered in the video image information base and the combination of the related system personnel information base and the MAC address base, and tracking of the target is achieved.

2. The method for target analysis based on video track and MAC data as claimed in claim 1, wherein in S100, the video resources at least include: networking video resources, networking bayonet socket resources, social resources, wifi probe and rail.

3. The method for target analysis based on video track and MAC data as claimed in claim 1, wherein in S100, the geographic information at least includes: case geographic information, camera and bayonet geographic information, unmanned aerial vehicle aerial photography information, field exploration geographic information and electric enclosure geographic information.

4. The method for analyzing a target according to claim 1, wherein in S100, the track information at least includes: taxi GPS information, leasing car GPS information, bus IC card track information and mobile phone base station track information.

5. The method for analyzing the target based on the video track and the MAC data as claimed in claim 1, wherein the specific method of S300 is: the method comprises the steps of extracting a target face characteristic value, a license plate and a behavior characteristic by uploading a target face or a vehicle, carrying out multidimensional tracking on a target by utilizing collected multidimensional data according to the time and the place of the target based on data collected by monitoring equipment, analyzing the space coordinate of the target under a camera coordinate system, carrying out coordinate transformation and proofreading through time, space and the like to obtain a target motion track point set, and forming a target multidimensional track library.

6. The method for target analysis based on video track and MAC data as claimed in claim 1, wherein S400 specifically includes: the target is found by checking the video to form a video track of the target, and collision analysis is carried out on the longitude and latitude information of the video track, the face information, the vehicle information and the survey map information in the multidimensional track library to form a more perfect and accurate multidimensional track.

7. The method of claim 1, wherein in S500, the first parameter set at least comprises: smoothness, distance longitude, matching threshold, correlation interval, error range.

8. The method for analyzing the target based on the video track and the MAC data as claimed in claim 1, wherein in S500, the collision analysis of the video track and the MAC track comprises: extracting retrieval conditions according to the accurate video track, recording the occurrence frequency of each MAC address in a coordinate space, and drawing the MAC address track according to the acquisition time and the existence condition of each MAC address in each point of each scene to form a possible target MAC address track library.

9. The method for analyzing the target based on the video track and the MAC data as claimed in claim 1, wherein the collision analysis of the video track and the MAC track in S500 further comprises: after the collision analysis of the video track and the MAC track, the MAC track route with high track similarity and high time and place matching degree is found out through comparison, and suspected target MAC address information is found out.

Images