CN112750301A

CN112750301A - Target object tracking method, device, equipment and computer readable storage medium

Info

Publication number: CN112750301A
Application number: CN201911046440.XA
Authority: CN
Inventors: 曹中胜; 孟凡旗; 项恒光; 魏忱
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2019-10-30
Filing date: 2019-10-30
Publication date: 2021-05-04

Abstract

The embodiment of the invention provides a target object tracking method, a target object tracking device and a computer readable storage medium, wherein the method comprises the following steps: acquiring an initial position of a target object, and obtaining at least two predicted paths taking the initial position as a starting point according to the initial position and road network data, wherein each predicted path comprises at least one monitoring device, and the initial position is the position of the currently tracked target object; determining the priority of each predicted path, wherein the priority of each predicted path is used for indicating the probability of the target object moving from the initial position according to the predicted path; and tracking the target object by utilizing the monitoring equipment on the predicted path according to the priority of each predicted path. According to the scheme provided by the embodiment of the invention, the target is orderly tracked by generating the predicted path and carrying out priority sequencing on the predicted path without manually checking the monitoring video, so that the misjudgment rate of manual prejudgment is reduced.

Description

Target object tracking method, device, equipment and computer readable storage medium

Technical Field

The embodiment of the invention relates to the technical field of video monitoring, in particular to a target object tracking method, a target object tracking device, target object tracking equipment and a computer-readable storage medium.

Background

With the development of investigation technology, video monitoring shows a trend of popularization. In each area of the city, monitoring equipment is distributed, and a plurality of monitoring equipment form a powerful security monitoring system. The dynamic tracking of different areas can be realized through the monitoring data of the monitoring equipment of the security monitoring system.

When an event occurs, it is usually necessary to track the relevant target object of the event. The monitoring data provided by a large amount of monitoring equipment is a precondition for tracking related target objects. Since the target object to be tracked may be moving and the monitoring area of each monitoring device is fixed, it often happens that the target object leaves the monitoring range of a certain monitoring device. In order to continuously track a target object, in the prior art, a monitoring device capable of continuously capturing the target object is generally pre-judged by a worker according to experience, so that the target object is tracked by the monitoring device controlling the pre-judgment. And the monitoring equipment which can continuously capture the target object through manual pre-judgment has a certain false judgment rate.

Disclosure of Invention

The embodiment of the invention provides a target object tracking method, a target object tracking device, target object tracking equipment and a computer readable storage medium, and aims to solve the problem that in the prior art, the target object is tracked through manual pre-judgment, so that the misjudgment rate is high.

In a first aspect, an embodiment of the present invention provides a target object tracking method, including:

acquiring an initial position of a target object, and obtaining at least two predicted paths taking the initial position as a starting point according to the initial position and road network data; each prediction path comprises at least one monitoring device, and the initial position is the position of the currently tracked target object;

determining a priority for each of the predicted paths; wherein the priority of the predicted path is used for indicating the probability of the target object moving from the initial position along the predicted path;

and tracking the target object by utilizing monitoring equipment on the predicted path according to the priority of each predicted path.

In one possible implementation, determining the priority of each of the predicted paths includes:

determining the priority of each predicted path according to the road network data;

or,

acquiring the moving direction of the target object according to the monitoring data of the target object at the initial position; and determining the priority of each predicted path according to the moving direction.

In a possible implementation manner, determining the priority of each predicted path according to the road network data includes:

acquiring the number of path blocking factors in each predicted path according to the road network data; wherein the path obstruction factor is a factor that hinders the target object from passing through the predicted path;

and determining the priority of each predicted path according to the number of the path blocking factors in each predicted path.

determining the priority of each monitoring device according to the road network data;

and determining the priority of each predicted path according to the priority of each monitoring device.

In a possible implementation manner, determining the priority of each predicted path according to the priority of each monitoring device includes:

acquiring target monitoring equipment on each predicted path according to the priority of each monitoring equipment, wherein the target monitoring equipment is the monitoring equipment with the highest priority on the corresponding predicted path;

and determining the priority of each predicted path according to the priority of each target monitoring device, wherein the priority of the target monitoring device is positively correlated with the priority of the corresponding predicted path.

In one possible implementation, the method further includes:

determining related monitoring equipment according to the initial position, and acquiring parameter information of the related monitoring equipment, wherein the monitoring area of each related monitoring equipment comprises the initial position;

sequencing the related monitoring equipment according to the weight of each parameter information to obtain a sequencing result, wherein the sequencing result is used for indicating the effect of the related monitoring equipment on shooting the initial position;

and determining first monitoring equipment according to the sequencing result, and acquiring monitoring data of the first monitoring equipment when the target object is at the initial position.

In a second aspect, an embodiment of the present invention provides a target object tracking apparatus, including:

the acquisition module is used for acquiring an initial position of a target object and acquiring at least two predicted paths taking the initial position as a starting point according to the initial position and road network data; each prediction path comprises at least one monitoring device, and the initial position is the position of the currently tracked target object;

a processing module for determining a priority of each of the predicted paths; wherein the priority of the predicted path is used for indicating the probability of the target object moving from the initial position along the predicted path;

and the tracking module is used for tracking the target object by utilizing the monitoring equipment on the predicted path according to the priority of each predicted path.

In a possible implementation manner, the processing module is specifically configured to:

or,

In one possible implementation, the tracking module is further configured to:

In a third aspect, an embodiment of the present invention provides a target object tracking apparatus, including: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the target object tracking method of any one of the first aspects.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the target object tracking method according to any one of the first aspect is implemented.

According to the method, the device and the equipment for tracking the target object and the computer readable storage medium provided by the embodiment of the invention, the initial position of the target object is firstly obtained, at least two predicted paths taking the initial position as a starting point are obtained according to the initial position and road network data, then the priority of each predicted path is determined, and finally the target object is tracked by utilizing the monitoring equipment on the predicted paths according to the priority of each predicted path, so that the monitoring equipment capable of continuously capturing the target object is not required to be manually pre-judged, the target object is orderly tracked by generating the predicted paths and determining the priorities of the predicted paths, the position where the target object is most likely to go can be preferentially inquired, and the false judgment rate of manual pre-judgment can be effectively reduced.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a target object tracking system according to an embodiment of the present invention;

fig. 2 is a schematic flowchart of a target object tracking method according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating obtaining a predicted path according to an embodiment of the present invention;

FIG. 4 is a first schematic diagram illustrating determining a predicted path priority according to road network data according to an embodiment of the present invention;

fig. 5A is a first schematic diagram illustrating determining a priority of a monitoring device according to an embodiment of the present invention;

fig. 5B is a schematic diagram illustrating determining the priority of the monitoring device according to the embodiment of the present invention;

fig. 6 is a schematic diagram of determining the predicted path priority according to the road network data according to the embodiment of the present invention;

FIG. 7 is a diagram illustrating the determination of predicted path priority based on direction of movement according to an embodiment of the present invention;

FIG. 8 is a flowchart illustrating a process of previewing a target object according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of an action trajectory of a target object according to an embodiment of the present invention;

FIG. 10 is a schematic structural diagram of a target tracking device according to an embodiment of the present invention;

fig. 11 is a schematic diagram of a hardware structure of a target object tracking device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 1 is a schematic structural diagram of a target object tracking system according to an embodiment of the present invention, as shown in fig. 1, the target object tracking system includes a plurality of monitoring devices 11, a server 12, and a display 13, where the plurality of monitoring devices 11 are set in different areas according to actual needs, the monitoring devices 11 and the server 12 are connected by a wired or wireless network, and the display 13 and the server 12 are connected by a wired or wireless network. When the event is triggered, the server 12 may obtain the initial position of the target object, generate a plurality of predicted paths according to the initial position of the target object and the road network data, and determine the priority of each predicted path. And finally, performing the dynamic tracking on the target object according to the priority of the predicted path. In this process, the server 12 may call the monitoring video of the monitoring device 11 at any time, and display the monitoring video on the display 13 for the user to preview the target object.

The technical solution of the present invention and how to solve the above technical problems will be described in detail with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Fig. 2 is a schematic flowchart of a target object tracking method according to an embodiment of the present invention, as shown in fig. 2, including:

s21, acquiring an initial position of a target object, and obtaining at least two predicted paths with the initial position as a starting point according to the initial position and road network data; each prediction path comprises at least one monitoring device, and the initial position is the position of the currently tracked target object;

in one area, monitoring equipment may be provided at different locations for monitoring various portions of the area. Each monitoring device has a corresponding monitoring area and a corresponding monitoring angle, and the monitoring areas of the monitoring devices may have partially overlapping portions. When an event is triggered or a target object appears, the target object needs to be subjected to dynamic tracking.

Before tracking a target object, firstly, tracking needs to be triggered, and the tracking triggering mode has various modes, for example, a certain thief steals on the street, and tracking can be triggered after a passerby alarms; for example, a vehicle is photographed on a road in violation of traffic rules, tracking may be triggered, and so forth.

In some embodiments, the tracking manner triggering the target object may be a manner of deploying early warning, for example, when an event is triggered, a possible position where the target object initially appears is obtained through an alarm of another person, so as to track the target object. In some embodiments, the tracking manner of the target object may be triggered by obtaining the related information of the target object, and determining a rough range according to the related information to find a possible position where the target object initially appears.

In the embodiment of the invention, when an event is triggered or a target object appears, corresponding monitoring data can be acquired, and the monitoring data can be displayed in the form of an image or a video. When the monitoring data is in an image form, the monitoring data is specifically a target image containing a target object, namely the target object appears in the target image; when the monitoring data is in a video form, the monitoring data is specifically a target video containing a target object, that is, the target object appears in the target video.

After the monitoring data is obtained, the position where the target object initially appears is obtained according to the monitoring data, wherein the position where the target object initially appears is obtained in various ways, including but not limited to manually specifying the position where the target object initially appears, automatically identifying the position where the target object initially appears according to the monitoring data, obtaining the position where the target object initially appears according to time or early warning, and the like.

Specifically, the manner of manually specifying the position where the target object initially appears is to manually observe the monitoring data and specify the position where the target object initially appears according to the monitoring data. For example, if the monitoring data is a target image, the target image may be directly observed, the surrounding environment where the target object is located in the target image and the position where the monitoring device that captured the target image is located may be determined, that is, the position where the target object initially appears may be substantially determined; and if the monitoring data is the target video, directly observing the target video, judging the surrounding environment of the target in the target video and the position of the monitoring equipment for shooting the target video, and selecting the position where a target object passes as the position where the target object appears at first.

And automatically identifying the position where the target object initially appears according to the monitoring data by acquiring the time and the place corresponding to the monitoring data. For example, the monitoring data is a target image or a target video, when the monitoring device shoots the target image or the target video, corresponding time information exists, the position information of the monitoring device can be acquired, and the position where the target object initially appears can be basically determined according to the time information and the position information of the monitoring device.

The mode of obtaining the position where the target object initially appears according to the event or the early warning is that the target object needs to be tracked when the event is triggered, and the position where the target object initially appears is determined according to the position triggered by the event. For example, when a theft event occurs on a street, people around the theft event on the street alarm, obtain the location where the target object first appears based on the place where the theft event occurred, which is provided by the alarm, and so on.

The above-mentioned manner of acquiring the position where the target object initially appears is merely an example, and the actual acquisition manner is not particularly limited herein.

It should be noted that, in the embodiment of the present invention, the initial position of the target object is not equal to the position where the target object initially appears, the initial position of the target object referred to in the embodiment of the present invention refers to the position where the target object is currently tracked, if the target object is tracked by the historical monitoring data, the time corresponding to the initial position is the past historical time, and if the target object is tracked by the real-time monitoring book, the time corresponding to the initial position is the current time. Accordingly, the tracking of the target object in the embodiment of the present invention may be tracking the moving path of the target object that has already occurred, or tracking a part of the moving path of the target object that has already occurred and tracking another part of the moving target object, or tracking the target object in real time, or even predictively tracking the place where the target object will go.

In the embodiment of the present invention, the initial position of the target object indicates a position where the target object is tracked by the monitoring device, and tracking the target object in each step is to first acquire a position of the currently tracked target object, that is, an initial position, then track a next position of the target object, and then repeat the tracking process with the next position of the target object as a new initial position.

After the initial position of the target object is obtained, at least two predicted paths with the initial position as a starting point need to be obtained according to the initial position and the road network data, where each predicted path includes at least one monitoring device, and the process will be described below with reference to fig. 3.

Fig. 3 is a schematic diagram of obtaining a predicted path according to an embodiment of the present invention, as shown in fig. 3, a map of an area, where the area includes a plurality of roads, a plurality of buildings, and the like. Meanwhile, a plurality of monitoring devices are installed in different places of the area, and the area monitored by each monitoring device is different.

After the event is triggered, the target object to be tracked is an adult 31, and the position where the adult 31 initially appears is acquired as a position a, at this time, at least two predicted paths with the position a as a starting point are generated according to the position a and road network data, and each predicted path includes at least one monitoring device.

There are various ways to generate the predicted route from the initial position and the road network data, and for example, if it is known that the adult 31 is a criminal and needs to escape when an event is triggered, and there is only one riding place B around the position a, a plurality of predicted routes can be generated with the position a as a starting point and the position B as an end point, and the predicted routes can reach the riding place. Three predicted paths from point a to point B are shown in fig. 3. In practice, since the adult 31 does not necessarily go to the point B, predicted paths in other directions may be generated, and generation of each predicted path may be determined in combination with road network data in the vicinity of the target object.

S22, determining the priority of each predicted path; wherein the priority of the predicted path is used for indicating the probability of the target object moving from the initial position along the predicted path;

after obtaining a plurality of predicted paths, the priority of each predicted path is further determined, the higher the priority is, the more likely the target object passes through the predicted path is indicated, and the lower the priority is, the less likely the target object passes through the predicted path is indicated. After the predicted paths are subjected to priority ranking, the target objects can be orderly tracked according to different directions in a targeted manner, so that resources can be saved, and the target objects can be quickly tracked.

And S23, tracking the target object by using the monitoring equipment on the predicted path according to the priority of each predicted path.

Optionally, the tracking of the target object is to model the monitoring data acquired by the monitoring device and then compare the modeled monitoring data with the target model to perform tracking. The target model may be a model obtained by the server through modeling according to monitoring data of one of the monitoring devices, for example, the monitoring device at the initial position of the target object sends a monitoring image or a monitoring video including the target object to the background server, so that the background server models the target object to obtain the target model. Optionally, the target model may also be input into the server in advance, so that each monitoring device can track the target object by using the target model.

For example, if the target object is a suspicious person, the target model may be a human body model or a human face model. For example, according to the monitoring data containing the suspicious person, the feature information of the suspicious person can be obtained, including the height, body type, clothes color, hair style, leg length, shoulder width and other structural features of the suspicious person, and a human body model related to the suspicious person can be established according to the structural features. If the front face of the suspicious person is captured in the monitoring data, a face model related to the suspicious person can be established according to the front face information of the suspicious person, and the related information of the suspicious person is further determined. For another example, if the target object is a vehicle, the target model may be a vehicle model, and for example, according to the monitoring data including the vehicle, the feature information of the vehicle, including the length, width, color, and license plate of the vehicle, can be obtained, and a vehicle model related to the vehicle can be established according to the above features.

After the target model is obtained, firstly, the monitoring data of each monitoring device on the prediction path with the highest priority is obtained, modeling is carried out on the object in the monitoring data of the monitoring device to obtain a model, and then the model is matched with the target model. If the matching similarity exceeds a certain value, the two objects are considered to be the same object, which indicates that the track of the target object is tracked in the predicted path, and at this time, the monitoring device which has tracked the target object on the predicted path can be used as a starting point to continue the tracking process. If the matching similarity is lower than a certain value, it indicates that the trace of the target object is not tracked in the predicted path, and at this time, the similar tracking process is continued on the predicted path of the next priority until the trace of the target object is found.

Since the tracking of the target object is to track a subsequent possible passing area at the initial position, it is necessary to acquire the monitoring data of the monitoring device on the predicted path within a preset time period. For example, if the time when the target object appears at the initial position is 2019, 7, 3 am 8 am, the time for acquiring the monitoring data of the monitoring device on the predicted path should be after 2019, 7, 3 am 8 am, and the specific preset time period may be determined comprehensively according to the distance between the initial position and the monitoring device in combination with the road network data, which is not particularly limited herein.

In the embodiment of the present invention, the monitoring data of the monitoring device may obtain historical monitoring data, may also be real-time monitoring data, and may also be historical and real-time monitoring data. For example, if the event is triggered and is one hour before the current time, the time when the target object appears at the initial position is one hour before, and the target object disappears after the initial position appears for a second half hour, the position of the target object needs to be tracked in a time period from the time when the target object appears at the initial position to a later half hour, the time period is an elapsed time period, and the acquired monitoring data is historical monitoring data. And tracking the target object when the event is triggered, wherein the acquired monitoring data of the monitoring equipment is real-time monitoring data, namely, the target object is tracked in real time. If the event triggering is half an hour before the current time, and the target object needs to be tracked from the event triggering to the half hour of the current time and from the current time to the subsequent half hour, historical monitoring data is acquired from the event triggering to the half hour of the current time, and real-time monitoring data is acquired from the current time to the subsequent half hour.

The method for tracking the target object, provided by the embodiment of the invention, comprises the steps of firstly obtaining an initial position of the target object, obtaining at least two predicted paths taking the initial position as a starting point according to the initial position and road network data, then determining the priority of each predicted path, and finally tracking the target object according to the priority of each predicted path and monitoring equipment on the predicted path, wherein the tracking is realized without manually checking a monitoring video, and meanwhile, the target object is sequentially tracked by determining the priority of the predicted path, so that the target object can be preferentially inquired according to the most probable position of the target object, the efficiency is higher, and the false rate of manual pre-judgment is effectively reduced.

The priorities of the predicted paths are sequenced in sequence, the target object can be sequentially tracked, and monitoring video tracking of monitoring equipment on each predicted path does not need to be acquired at the same time each time. The acquisition of the priority of the predicted path in the embodiment of the invention at least comprises two main modes.

The first main way is to determine the priority of each predicted path according to the road network data.

The road network data mainly includes road data, road attachment data, traffic flow data, building data, and the like. The road data mainly refers to various roads, including a highway, a main road, a secondary road and the roads thereof, wherein the center of the highway is provided with a central separation strip which is provided with a plurality of motor vehicle lanes for vehicles to run on the roads with higher running speed; the main road mainly refers to a main road connecting each subarea of a city, and mainly has a traffic function, and the running speed of vehicles on the main road is lower than that of vehicles on an express way; the secondary main road mainly refers to a road which plays a role in traffic collection and distribution of the main road and each subarea, and the running speed of vehicles on the secondary main road is generally slightly lower than that of the vehicles on the main road; the branch mainly refers to a connecting road between the secondary main road and the street road, and also comprises various bicycle lanes, sidewalks and the like.

The data of the road subsidiary facilities mainly refer to various traffic markings, signs and traffic lights, including the traffic markings of various roads in various areas, the arrangement intervals of the traffic lights, and the like. From the data of the road attachment, it is possible to acquire what rule the various vehicles or pedestrians need to comply with on different roads, how to travel, and the like.

The traffic flow data needs to be acquired in real time, and the existing traffic flow can be roughly predicted according to the historical traffic flow. The traffic flow data can reflect different pedestrian flow sizes in different regions. The building data reflects the buildings in various areas, including buildings such as homes, parks, office buildings, hotels, etc.

From the road network data, roads, buildings, and other types of road traffic data and the like in an area can be acquired.

In some embodiments, the priority of each predicted path is determined according to the road network data by first obtaining the number of path blocking factors in each predicted path according to the road network data, wherein the path blocking factors are factors that prevent the target object from passing through the predicted path; then, the priority of each predicted path is determined according to the number of blocking factors in each predicted path.

The path obstruction factors may not be exactly the same for different target objects. For example, when the target object is a person, possible path obstruction factors include, but are not limited to, a highway, a viaduct, a city circle, and the like, and when the target object is a vehicle, possible path obstruction factors include, but are not limited to, a sidewalk, a building, a river through which no-traffic roads pass, and the like.

Fig. 4 is a first schematic diagram illustrating determining a priority of a predicted path according to road network data according to an embodiment of the present invention, where an initial position of a target object is at a point O and the target object is a person, as shown in fig. 4, three predicted paths starting from the point O are shown in fig. 4, and the three predicted paths are a first predicted path, a second predicted path, and a third predicted path, respectively.

After the three predicted paths are generated, priorities of the three predicted paths need to be determined, and optionally, the priority of each predicted path is determined by obtaining the number of path blocking factors in each predicted path. In fig. 4, the first predicted route includes five monitoring devices, which are a1, B1, C1, D1 and E1, respectively, and on the route from B1 to C1, there is a road construction area 41 where any passage of people and vehicles is prohibited, so that on the first predicted route, the road construction area 41 is a route obstruction factor. The second predicted route includes five monitoring devices, a2, B2, C2, D2 and E2, and on the route from B2 to C2, there is a construction zone 43 where any passage of people and vehicles is prohibited, so on the second predicted route, the construction zone 43 is a route obstruction factor. Meanwhile, if there is a river 42 on the route from C2 to D2 and there is no bridge or other facility on the river through which the target object can pass, the target object cannot pass through the river 42 directly, and the river 42 is also a route blocking factor. Five monitoring devices, namely A3, B3, C3, D3 and E3 are also included on the third predicted path, and no factors obstructing the passage of the target object are included on the third predicted path. In summary, the number of path blocking factors on the first predicted path is 1, the number of path blocking factors on the second predicted path is 2, and the number of path blocking factors on the third predicted path is 0.

The priority of each predicted path is determined according to the number of path blocking factors on each predicted path, and optionally, the priority is negatively related to the number of path blocking factors, that is, the higher the number of path blocking factors is, the lower the priority is. Among the three predicted paths in fig. 4, the third predicted path has the smallest number of path blocking factors and the highest priority, and is followed by the first predicted path and the second predicted path.

Therefore, when the target object is tracked, firstly, the monitoring devices on the third prediction path are called, whether the target object has a trace is checked, if the target object is tracked on a certain monitoring device on the third prediction path, for example, the monitoring device A3, a new prediction path is generated by taking the position of the target object under the monitoring device A3 as an initial position to continue tracking, and if the target object is not tracked on the third prediction path with the highest priority, the tracking is performed on the first prediction path and the second prediction path in sequence according to the descending order of priority. When the target object is tracked according to the monitoring device, the target model in the above embodiment may still be matched with the model established in the monitoring data.

In other embodiments, the determining the priority of each predicted path according to the road network data is performed by determining the priority of each monitoring device according to the road network data, and then determining the priority of each predicted path according to the priority of each monitoring device.

There are various ways to determine the priority of each monitoring device according to the road network data.

One possible implementation manner is to obtain the distance between each monitoring device and the initial position of the target object according to the road network data to determine the priority of each monitoring device. When the monitoring device is closer to the initial position, the monitoring area of the monitoring device is also in the vicinity of the initial position, so that the monitoring device closer to the initial position is more likely to monitor the target object than the monitoring device farther from the initial position under similar conditions, as will be described below with reference to fig. 5A.

Fig. 5A is a schematic diagram of determining priorities of monitoring devices according to an embodiment of the present invention, where as shown in fig. 5A, an initial position of a target object is at a point O, and there are multiple monitoring devices around the point O, and two of the monitoring devices, which are monitoring device a and monitoring device B, are illustrated in fig. 5A. In fig. 5A, a monitoring device a and a monitoring device B are taken as an example, where a distance between the monitoring device a and an initial position is 100 meters, a distance between the monitoring device B and the initial position is 200 meters, a monitoring area of the monitoring device a is a first monitoring area 51, and a monitoring area of the monitoring device B is a second monitoring area 52.

It can be seen that when the target object moves in the sector area with the angle a as shown in fig. 5A, the target object passes through the first monitoring area 51 and is monitored by the monitoring device a. When the target object moves in the sector area with the angle B as shown in fig. 5A, the target object passes through the second monitoring area 52 and is monitored by the monitoring device B. Since the monitoring device a is closer to the initial position than the monitoring device B, the probability that the monitoring device a monitors the target object is higher than that of the monitoring device B under other similar conditions, and the priority of the monitoring device a is higher than that of the monitoring device B at this time.

In addition to the above, there is also a possible implementation manner that the determination is comprehensively performed according to the road network data, the type of the target object, and the monitoring area of the monitoring device. After the monitoring devices are installed, the corresponding monitoring areas are fixed, for example, some monitoring devices are monitoring areas of a crossroad, some monitoring devices are monitoring areas of buildings such as hospitals and supermarkets, and some monitoring devices are monitoring areas of parks. Then, the priority of the monitoring equipment is preliminarily determined by combining the monitoring area of each monitoring equipment of the road network data and the type of the target object.

For example, when the target object is a person, the priority of the monitoring device whose monitoring area is an area such as a sidewalk or a building is higher than the priority of the monitoring device whose monitoring area is a road or an overhead bridge. When the target object is a vehicle, the priority of the monitoring equipment of which the monitoring area is an area such as various roadways is higher than that of the monitoring equipment of which the monitoring area is an area such as a building. If there are a plurality of monitoring devices in the similar monitoring area, the determination can be further combined with other information.

Fig. 5B is a schematic diagram of determining priorities of monitoring devices according to an embodiment of the present invention, where as shown in fig. 5B, an initial position of a target object is at a point O, and a plurality of monitoring devices, namely, a monitoring device a, a monitoring device B, a monitoring device C, and a monitoring device D, are arranged around the point O. The first monitoring area 501 of the monitoring device a is an unmanned zebra crossing, the second monitoring area 502 of the monitoring device B is a part of a road, the third monitoring area 503 of the monitoring device C is a hospital, and the fourth monitoring area 504 of the monitoring device D is a park.

When the target object is a person, since the possibility that the person goes to an intersection or a road of the unmanned zebra crossing is much smaller than the possibility of going to a hospital or a park, the priority of the monitoring devices C and D is higher than that of the monitoring devices a and B at this time. If the priorities of the monitoring devices C and D are to be further determined, the priorities may be determined in combination with other manners. For example, the priorities of the monitoring device C and the monitoring device D may be obtained by obtaining the distances from the monitoring device C and the monitoring device D to the initial position O according to the road network data.

When the target object is a vehicle, since the possibility that the vehicle goes to a road is much higher than that to a hospital or a park, the priority of the monitoring devices a and B is higher than that of the monitoring devices C and D at this time. If the priorities of the monitoring devices a and B are to be further determined, the priorities may be determined according to the distances between the monitoring devices a and B and the initial position O, and also according to the characteristics of the monitoring areas of the monitoring devices a and B. As shown in fig. 5B, the intersection at the first monitoring area 501 of the monitoring device a is a more important traffic lane in the nearby area, and there are multiple paths from the point O to the intersection, while the road at the second monitoring area 502 of the monitoring device B is only a common road, and the priority of the monitoring device a is higher than that of the monitoring device B.

The above manner for determining the priority of each monitoring device is only an example, and is not a limitation on the manner of obtaining the priority, where the determination of the priority of each monitoring device may be implemented by any one of the above methods, or by a combination of several methods.

After the priority of each monitoring device is obtained, the priority of each predicted path needs to be determined according to the priority of each monitoring device. Fig. 6 is a schematic diagram of determining the priority of the predicted path according to the road network data according to the embodiment of the present invention, as shown in fig. 6, the point O is an initial position of the target object, and four predicted paths are generated from the starting point of the point O, and are a first predicted path, a second predicted path, a third predicted path, and a fourth predicted path, respectively. Three monitoring devices A1, B1 and C1 are shared on the first prediction path, three monitoring devices A2, B2 and C2 are shared on the second prediction path, three monitoring devices A3, B3 and C3 are shared on the third prediction path, and three monitoring devices A4, B4 and C4 are shared on the fourth prediction path.

In the embodiment of the invention, the priority of each monitoring device is determined by acquiring the priority of each monitoring device. One possible implementation manner is that firstly, the monitoring device with the highest priority on each predicted path is obtained as the target monitoring device on the predicted path, and then the priority of each predicted path is determined according to the priority of each target monitoring device, wherein the priority of the target monitoring device is positively correlated with the priority of the corresponding predicted path.

A method of determining the priority of each monitoring device around the initial location is shown in the examples of fig. 5A and 5B, and thus the priority of each monitoring device around the initial location is known. Taking fig. 6 as an example, in the first predicted path, it is assumed that the priorities of the three monitoring devices are a1, B1, and C1 in order from high to low, and therefore the monitoring device a1 is a target monitoring device on the first predicted path. In the second predicted path, the priorities of the three monitoring devices are a2, B2 and C2 in the order from high to low, so that the monitoring device a2 is a target monitoring device on the second predicted path. In the third predicted path, the priorities of the three monitoring devices are A3, B3 and C3 in the order from high to low, so that the monitoring device A3 is a target monitoring device on the third predicted path. In the fourth predicted path, the priorities of the three monitoring devices are a4, B4 and C4 in the order from high to low, so that the monitoring device a4 is a target monitoring device on the fourth predicted path.

And then acquiring the priorities of the four target monitoring devices A1, A2, A3 and A4, and determining the priority sequence of the corresponding predicted path according to the priorities of the four target monitoring devices. For example, the priorities of the four target monitoring devices a1, a2, A3 and a4 are a1, a4, a2 and A3 in sequence from high to low, then it is determined on which predicted path the four target monitoring devices a1, a4, a2 and A3 are respectively located, the first predicted path where the monitoring device a1 is located is taken as the predicted path of the first priority, the fourth predicted path where the monitoring device a4 is located is taken as the predicted path of the second priority, the second predicted path where the monitoring device a2 is taken as the predicted path of the third priority, and the third predicted path where the monitoring device A3 is located is taken as the predicted path of the fourth priority, so that the priorities of the target monitoring devices are positively correlated with the priorities of the corresponding predicted paths, and therefore the priorities of the four predicted paths are the first predicted path, the fourth predicted path, the priorities of the fourth predicted path are sequentially from high to low, And a third prediction path.

When the target object is tracked, the monitoring device a1 with the highest priority of the target monitoring device is found first, then the first predicted path corresponding to the monitoring device a1 is determined, and finally the monitoring data of the monitoring device on the first predicted path is obtained to track the target object. If the target object is not tracked on the first predicted path, determining the monitoring device a4 with the priority behind the monitoring device a1, further determining a fourth predicted path corresponding to the monitoring device a4, and acquiring monitoring data of the monitoring device on the fourth predicted path to track the target object, and so on.

If monitoring devices with the same priority in the four target monitoring devices, for example, the monitoring device a1 and the monitoring device a4 are the monitoring devices with the highest priority in the first predicted path and the fourth predicted path, respectively, and the priorities of the monitoring device a1 and the monitoring device a4 are the same, at this time, the priorities of the monitoring device B1 in the first predicted path and the monitoring device B4 in the fourth predicted path may be compared, and the priorities of the first predicted path and the fourth predicted path may be determined according to the priorities of the monitoring device B1 and the monitoring device B4, where the monitoring device B1 is the monitoring device with the priority next to the monitoring device a1 in the first predicted path, and the monitoring device B4 is the monitoring device with the priority next to the monitoring device a4 in the fourth predicted path.

Optionally, the priority of the predicted path is determined, and may be determined according to the moving direction of the target object, in addition to the road network data. Specifically, a first monitoring device is determined according to an initial position, and a target object is located in a monitoring area of the first monitoring device; acquiring the moving direction of a target object in the monitoring area of the first monitoring equipment according to the monitoring data of the first monitoring equipment; the priority of each predicted path is determined according to the moving direction. This will be explained below with reference to fig. 7.

Fig. 7 is a schematic diagram of determining priorities of predicted paths according to a moving direction according to an embodiment of the present invention, as shown in fig. 7, a point O is an initial position of a target object, and a total of four predicted paths are generated with the point O as a starting point, where the four predicted paths are a first predicted path, a second predicted path, a third predicted path, and a fourth predicted path, and at this time, the priorities of the predicted paths need to be determined. The method of the embodiment of the invention is to determine the first monitoring device according to the initial position O point of the target object, wherein the monitoring range of the first monitoring device is the first monitoring area 71 shown in fig. 7.

Because the monitoring devices in the area are linked, and the monitoring area of each monitoring device is known, the mode of determining the first monitoring device according to the O point may be that at least one monitoring device is determined according to the position of the O point, wherein the monitoring area of each monitoring device in the at least one monitoring device includes the O point, and then one monitoring device is selected as the first monitoring device from the at least one monitoring device.

After the first monitoring device is determined, the monitoring video of the first monitoring device is obtained, and the moving direction of the target object in the first monitoring area 71 is obtained. In fig. 7, it is obtained that the target object moves from O 'to O point under the first monitoring area 71, and the moving direction is a direction of a line from O' to O point. At this time, the closer to the direction of the line connecting O' to point O, the higher the priority of the predicted path. In fig. 7, the highest priority is the second predicted path, which is next to the third predicted path, and the second predicted path is the third predicted path, which is next to the third predicted path, and the fourth predicted path is the lowest priority.

When the target object is tracked in the movement direction, in order to observe the movement direction of the target object more clearly, the embodiment of the invention further provides a method for previewing the monitoring data of the target object. Fig. 8 is a schematic flowchart of a process of previewing target object monitoring data according to an embodiment of the present invention, as shown in fig. 8, including:

s81, determining related monitoring equipment according to the initial position, and acquiring parameter information of the related monitoring equipment, wherein the monitoring area of each related monitoring equipment comprises the initial position;

the related monitoring devices are monitoring devices capable of shooting the initial position, so that when the target object passes through the initial position, each related monitoring device can shoot the trace of the target object. However, since the installation information of each monitoring device is different, the effect of shooting the initial position is also different, and therefore, a monitoring device with a better effect needs to be selected and the monitoring video thereof needs to be called to check the track of the target object according to the parameter information of each relevant monitoring device.

In the embodiment of the present invention, the parameter information includes, but is not limited to, a distance between the initial position and the relevant monitoring device, an orientation of the relevant monitoring device, a shooting angle of the relevant monitoring device, and a definition of a shooting picture of the relevant monitoring device, and the monitoring device with a better angle is further selected to preview the target object according to the parameter information.

S82, sequencing the related monitoring equipment according to the weight of each parameter information to obtain a sequencing result, wherein the sequencing result is used for indicating the effect of the related monitoring equipment on shooting the initial position;

s83, determining a first monitoring device according to the sorting result, and acquiring the monitoring data of the first monitoring device when the target object is at the initial position.

For example, when the target object is located at the initial position, ten related monitoring devices capable of monitoring the initial position are provided, the distances of the ten related monitoring devices from the initial position are different, the angles of shooting the initial position are different, the orientations of the monitoring devices are different, and the definition of the shot pictures is different. For example, if the initial positions of the monitoring devices 1 and 2 are the same, but the monitoring device 1 is closer to the initial position than the monitoring device 2 is to the initial position, the priority of the monitoring device 1 is higher than that of the monitoring device 2, because the effect is better than that of the monitoring device 2 when the monitoring device 1 which is closer to the initial position is to the initial position under the same condition. When the parameter information is different, corresponding weight can be set for the parameter information, and then the priority of the related monitoring equipment is calculated to obtain the sequencing result. And determining the first monitoring equipment with the highest priority according to the sequencing result, and then acquiring the monitoring video of the first monitoring equipment to preview the target object when the target object is at the initial position. When the target object goes to the next location, the first monitoring device may be redetermined for previewing.

Meanwhile, when each initial position is obtained, the corresponding position of the map can be marked, an enclosure can be formed by taking the position of the target object as the center, and when the target object moves, the enclosure is updated in real time and displayed on the map, so that the action track of the target object is obtained. Fig. 9 is a schematic diagram of an action trajectory of a target object according to an embodiment of the present invention, as shown in fig. 9, where an initial position of a currently tracked target object is an O point, and then three predicted paths are generated with the O point as a starting point, where each predicted path has a plurality of monitoring devices. After the target object is tracked according to the priority of each predicted path, the target object is tracked to the monitoring area of the monitoring device 91 on the second predicted path, and then a point a at a certain position of the target object under the monitoring device 91 is taken as a new initial position to generate four new predicted paths with the point a as a starting point. By tracking the new four predicted paths with point a as the starting point, if the target object is tracked to the monitoring area of the monitoring device 92 on the first predicted path, the tracking process will be continued with a point B at a certain position of the target object under the monitoring device 92 as the new initial position.

When each initial position is obtained, a surrounding circle is generated around the initial position, for example, a first surrounding circle 911 is formed when the target object is tracked at the O point, a second surrounding circle 912 is formed when the target object is tracked at the a point, a third surrounding circle 913 is formed when the target object is tracked at the B point, and so on. The enclosure may be a circle formed by centering on an initial position where the target object is located, or may have another shape, which is not particularly limited in the embodiment of the present invention. The moving trajectory of the target object from point O to point B can be obtained by connecting the positions of the target object, for example, connecting OA and AB in fig. 9.

Furthermore, according to the monitoring video of the target object in the moving process, the internet of things data, the public security data and the like, the identity of the target object, the risk index of the target object, the surrounding situation of the target object and the like can be obtained, and then the target object is reported to be treated. The embodiment of the invention can also install a high-altitude sensing device at a higher position in a larger area, wherein the high-altitude sensing device comprises a high-definition camera and can monitor a larger range, thereby realizing preview in the larger area.

Especially, when the target object is a criminal, a public security officer can check the tracking condition of the target object through terminal equipment such as a mobile phone, and a plurality of policemen form a system after registering at a server side, so that information interaction can be performed. After receiving the police condition or the alarm (namely event triggering), the command center on-duty personnel push the alarm to a patrol policeman in a specified range near the place where the target suspect appears through a mobile police app of the mobile phone, and the policeman starts an emergency response to implement capture after receiving the alarm through the app.

Meanwhile, the server automatically enters an intelligent tracking flow, deployment and control are carried out through related pictures of the target object, all monitoring devices and all idle calculation power around the appearance range of the target object are called to the enclosure of deployment and control by using the resource scheduling platform, video structuring processing is carried out on the high-definition monitoring devices, and full-point deployment and control are carried out.

And if the target object triggers the deployment and control, receiving an alarm through the mobile police app and pushing the alarm to the target object to trigger patrol polices in a specified range around the deployment and control and polices which have entered a capture state before, and performing accurate capture in the deployment and control range.

If the target object triggers an alarm within the deployment and control range, the alarm is also pushed to policemen near the triggering alarm range and the prior policemen through the police app. Finally, the temporarily invoked idle computing resources may be returned to the computing resource pool.

The target object tracking method provided by the embodiment of the invention comprises the steps of firstly obtaining the initial position of a target object, obtaining at least two predicted paths taking the initial position as a starting point according to the initial position and road network data, then determining the priority of each predicted path, and finally tracking the target object according to the priority of each predicted path and monitoring equipment on the predicted path.

Fig. 10 is a schematic structural diagram of a target object tracking apparatus according to an embodiment of the present invention, as shown in fig. 9, including an obtaining module 101, a processing module 102, and a tracking module 103, where:

the obtaining module 101 is configured to obtain an initial position of a target object, and obtain at least two predicted paths using the initial position as a starting point according to the initial position and road network data; each prediction path comprises at least one monitoring device, and the initial position is the position of the currently tracked target object;

the processing module 102 is configured to determine a priority of each of the predicted paths; wherein the priority of the predicted path is used for indicating the probability of the target object moving from the initial position along the predicted path;

the tracking module 103 is configured to track the target object by using the monitoring device on the predicted path according to the priority of each predicted path.

In a possible implementation manner, the processing module 102 is specifically configured to:

or,

In a possible implementation manner, the tracking module 103 is further configured to:

The apparatus provided in the embodiment of the present invention may be used to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.

Fig. 11 is a schematic diagram of a hardware structure of a target object tracking device according to an embodiment of the present invention, and as shown in fig. 11, the data processing device includes: at least one processor 111 and a memory 112. Wherein the processor 111 and the memory 112 are connected by a bus 113.

Optionally, the model determination further comprises a communication component. For example, the communication component may include a receiver and/or a transmitter.

In particular implementations, the at least one processor 111 executes computer-executable instructions stored by the memory 112 to cause the at least one processor 111 to perform the target object tracking method as described above.

For a specific implementation process of the processor 111, reference may be made to the above method embodiments, which implement principles and technical effects similar to each other, and details of this embodiment are not described herein again.

In the embodiment shown in fig. 11, it should be understood that the Processor may be a Central Processing Unit (CPU), other general-purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the target object tracking method as described above is implemented.

The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.

The division of the units is only a logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions 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

1. A target object tracking method, comprising:

2. The method of claim 1, wherein determining the priority of each of the predicted paths comprises:

or,

3. The method of claim 2, wherein determining a priority for each of said predicted paths based on said road network data comprises:

4. The method of claim 2, wherein determining a priority for each of said predicted paths based on said road network data comprises:

5. The method of claim 4, wherein determining the priority of each of the predicted paths based on the priority of each of the monitoring devices comprises:

6. The method according to any one of claims 1-5, further comprising:

7. A target object tracking device, comprising:

8. The apparatus of claim 7, wherein the processing module is specifically configured to:

or,

9. The apparatus of claim 8, wherein the processing module is specifically configured to:

10. The apparatus of claim 8, wherein the processing module is specifically configured to:

11. The apparatus of claim 10, wherein the processing module is specifically configured to:

12. The apparatus of any of claims 7-11, wherein the tracking module is further configured to:

13. A target object tracking apparatus, comprising:

at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the target object tracking method of any of claims 1-6.

14. A computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a processor, implement the target object tracking method of any one of claims 1-6.