Track completion method and data processing equipment

Abstract

The invention discloses a track completion method and data processing equipment. The track completion method comprises the following steps: acquiring first alarm information; the first alarm information comprises feature information used for describing the object; according to the feature information of the object, determining a historical track of the object in a first set time period; determining a monitoring area corresponding to each road section included in the historical track; each road section is composed of two adjacent point locations, and each point location is provided with a monitoring device; identifying deployed target monitoring equipment in a target area formed by the monitoring areas corresponding to the road sections; according to the acquired data of the target monitoring equipment, selecting a point location of the target monitoring equipment corresponding to the acquired data greater than the quality threshold as a supplementary track point; and adding the supplementary trajectory points to the historical trajectory, and determining a target historical trajectory of the object. By means of the design, the problem that part of track points in the track are missing can be solved, and then the accuracy and convenience of the track determining process are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a trajectory completion method and a data processing device. Background Art

[0002] In the field of security, obtaining the trajectory of the target person is of guiding significance for analyzing the movement behavior of the target person. However, due to the limitations of manpower, the computing power of data processing equipment, and the deployment of actual monitoring equipment, it may not be possible to obtain the complete trajectory information of the target person in a timely and effective manner, and the lack of information makes it impossible to carry out subsequent work. Therefore, how to obtain the complete trajectory information of the target person is particularly important.

[0003] The trajectory completion method in the related art has high requirements for raw data and needs multi-dimensional data support. Or, it is usually an estimation method, which can only have a good positioning effect on the data of a specific target that has been trained. Once the target person appears newly, the effect is not very good. Summary of the invention

[0004] In an exemplary embodiment of the present application, a trajectory completion method is provided to complete missing trajectory points in a trajectory, thereby improving the accuracy and convenience of the positioning process.

[0005] According to a first aspect of an exemplary embodiment, a trajectory completion method is provided, which can be applied to a data processing device, which can be an electronic device with a data processing function or a server. The trajectory completion method includes at least the following steps:

[0006] Acquire first warning information; wherein the first warning information includes characteristic information for describing the object;

[0007] Determine the historical trajectory of the object within a first set time period according to the characteristic information of the object;

[0008] Determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point;

[0009] In the target area formed by the monitoring areas corresponding to each road section, the deployed target monitoring equipment is identified;

[0010] According to the collected data of the target monitoring device, the point of the target monitoring device corresponding to the collected data greater than the quality threshold is selected as the supplementary trajectory point;

[0011] The supplementary track points are added to the historical track to determine the target historical track of the object.

[0012] According to a second aspect of the exemplary implementation, there is provided a data processing device, the data processing device comprising a data transmission unit and a processor;

[0013] The data transfer unit is configured to perform:

[0014] Acquire first warning information; wherein the first warning information includes characteristic information for describing the object;

[0015] The processor is configured to execute:

[0016] Determine the historical trajectory of the object within a first set time period according to the characteristic information of the object;

[0017] Determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point;

[0018] In the target area formed by the monitoring areas corresponding to each road section, the deployed target monitoring equipment is identified;

[0019] According to the collected data of the target monitoring device, the point of the target monitoring device corresponding to the collected data greater than the quality threshold is selected as the supplementary trajectory point;

[0020] Add the supplementary track points to the history track to determine the target history track of the object:

[0021] According to a third aspect of an exemplary embodiment, a trajectory completion device is provided, the device comprising:

[0022] A data acquisition unit, used to: acquire first warning information; wherein the first warning information includes feature information for describing an object;

[0023] A historical trajectory determination unit, used to: determine the historical trajectory of the object within a first set time period according to the feature information of the object;

[0024] The monitoring area determination unit is used to: determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point;

[0025] The target monitoring device identification unit is used to: identify the deployed target monitoring devices in the target area formed by the monitoring areas corresponding to each road section;

[0026] A trajectory point selection unit is used to: select, according to the collected data of the target monitoring device, the point position of the target monitoring device corresponding to the collected data greater than the quality threshold as a supplementary trajectory point;

[0027] The trajectory completion unit is used to add the supplementary trajectory points to the historical trajectory to determine the target historical trajectory of the object.

[0028] According to a fourth aspect of the exemplary implementation, a computer storage medium is provided, in which computer program instructions are stored. When the instructions are executed on a computer, the computer executes the trajectory completion method of the first aspect.

[0029] In the embodiment of the present application, based on the historical trajectory of the object within the first set time period, the monitoring areas corresponding to the various road sections included in the historical trajectory are determined in the face of the fact that the historical trajectory may be relatively sparse or some trajectory points are missing, and the monitoring areas corresponding to the various road sections may constitute the target area. The target monitoring equipment deployed in the target area is identified, and then based on the collected data of the target monitoring equipment, the points of the target monitoring equipment corresponding to the collected data greater than the quality threshold are selected as supplementary trajectory points, and the supplementary trajectory points are added to the historical trajectory to obtain a complete trajectory, which is called the target historical trajectory. Compared with the trajectory completion method in the related art, it does not require a large amount of data support, and in the completion process, the collected data of the target monitoring equipment in the target area where the object may appear is taken into account, thereby improving the accuracy and operability of the estimated completion. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0031] Figure 1 An application scenario diagram of a trajectory completion method provided by an embodiment of the present application is exemplarily shown;

[0032] Figure 2 A flowchart of a trajectory completion method provided by an embodiment of the present application is exemplarily shown;

[0033] Figure 3 A schematic diagram of a motion prediction area provided by an embodiment of the present application is exemplarily shown;

[0034] Figure 4 A schematic diagram of a prediction path provided by an embodiment of the present application is exemplarily shown;

[0035] Figure 5 A schematic diagram of a monitoring area provided by an embodiment of the present application is exemplarily shown;

[0036] Figure 6A schematic diagram of a target area provided in an embodiment of the present application is exemplarily shown;

[0037] Figure 7 A schematic diagram of a target historical trajectory provided by an embodiment of the present application is exemplarily shown;

[0038] Figure 8 A flowchart for determining a real-time trajectory provided by an embodiment of the present application is exemplarily shown;

[0039] Fig. 9 The following is a schematic diagram showing the structure of a trajectory completion device provided in an embodiment of the present application;

[0040] Fig.10 A structural diagram of a data processing device provided in an embodiment of the present application is exemplified. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0042] For ease of understanding, the terms involved in the embodiments of the present application are explained below:

[0043] (1) Monitoring equipment, including high-definition acquisition equipment and ordinary cameras. High-definition acquisition equipment can directly capture high-definition images, while ordinary cameras usually capture videos or images with lower resolution.

[0044] (2) Point: The location of the data collection point. A monitoring device is deployed at each point, and the location of the monitoring device that photographs the object is used as the location of the object at the time of photography.

[0045] (3) Object: refers to the target whose trajectory needs to be determined, which can be a person, a vehicle, or other moving objects.

[0046] In the field of security, obtaining the trajectory of the target person is of guiding significance for analyzing the movement behavior of the target person. However, due to the limitations of manpower, the computing power of data processing equipment, and the deployment of actual monitoring equipment, it may not be possible to obtain the complete trajectory information of the target person in a timely and effective manner, and the lack of information makes it impossible to carry out subsequent work. Therefore, how to obtain the complete trajectory information of the target person is particularly important.

[0047] The trajectory completion method in the related art has high requirements for raw data and needs multi-dimensional data support. Or, it is usually an estimation method, which can only have a good positioning effect on the data of a specific target that has been trained. Once the target person appears newly, the effect is not very good.

[0048] Normally, a high-definition acquisition device can shoot objects within a certain range around it, and the position of the high-definition acquisition device that can shoot the object is used as a trajectory point to obtain the trajectory of the object. However, due to the high cost of high-definition acquisition devices, a number of ordinary cameras are usually deployed between two high-definition acquisition devices. The ordinary cameras usually capture videos or images with low resolution. The data processing device cannot determine in real time whether the acquisition data of the ordinary camera is the acquisition data of the object. It takes a certain amount of time to analyze the acquisition data of the ordinary camera to determine whether the object is included. Therefore, in the process of determining the historical trajectory, it is usually determined whether the position of the high-definition acquisition device is used as a trajectory point based on the acquisition data of the high-definition acquisition device. In this process, since the acquisition data of the ordinary camera is not taken into account, the missing of trajectory points may occur, and the sparse trajectory affects the accuracy of the trajectory of the determined object.

[0049] To this end, an embodiment of the present application provides a trajectory completion method, which determines the monitoring area corresponding to each road section between two high-definition acquisition devices, and then determines the supplementary trajectory points in the target area constituted by the monitoring areas of each road section, and adds the supplementary trajectory points to the original historical trajectory to obtain a complete trajectory. In this process, in the target area constituted by the monitoring areas corresponding to each road section, the deployed target monitoring devices are identified, and in the acquisition data of the target monitoring devices, the points of the target monitoring devices corresponding to the acquisition data greater than the quality threshold are selected as supplementary trajectory points; then the supplementary trajectory points are added to the historical trajectory to obtain the target historical trajectory points of the object. It does not require a large amount of data support, nor is it limited to determining the trajectory of known objects.

[0050] After introducing the design ideas of the embodiments of the present application, the following briefly introduces the application scenarios to which the technical solutions of the embodiments of the present application can be applied. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present application and are not limited. In specific implementation, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

[0051] refer to Figure 1 , shows an application scenario diagram of a trajectory completion method, Figure 1 In the figure, 11 is a monitoring device, 12 is a data processing device, and the data processing device is shown by taking a server as an example.

[0052] To further illustrate the technical solution provided by the embodiment of the present application, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiment of the present application provides the method operation steps shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiment of the present application.

[0053] Combine the following Figure 1 The application scenario shown is shown in Figure 2 The flowchart of a trajectory completion method is shown to illustrate the technical solution provided by the embodiment of the present application. The trajectory completion method can be applied to a data processing device, which can be an electronic device with data processing function or a server. The trajectory completion method includes at least the following steps:

[0054] S201: A data processing device obtains first alarm information.

[0055] The first warning information includes characteristic information for describing the object.

[0056] S202: The data processing device determines the historical trajectory of the object within a first set time period according to the feature information of the object.

[0057] S203: The data processing device determines the monitoring area corresponding to each road section included in the historical trajectory.

[0058] Each road section consists of two adjacent points, and a monitoring device is deployed at each point.

[0059] S204: In the target area constituted by the monitoring areas corresponding to the respective road sections, the data processing device identifies the deployed target monitoring devices.

[0060] S205: The data processing device selects, based on the collected data of the target monitoring device, points of the target monitoring device corresponding to the collected data that is greater than a quality threshold as supplementary trajectory points.

[0061] S206: The data processing device adds the supplementary trajectory points to the historical trajectory to determine the target historical trajectory of the object.

[0062] In the embodiment of the present application, based on the historical trajectory of the object within the first set time period, the monitoring areas corresponding to the various road sections included in the historical trajectory are determined in the face of the fact that the historical trajectory may be relatively sparse or some trajectory points are missing, and the monitoring areas corresponding to the various road sections may constitute the target area. The target monitoring equipment deployed in the target area is identified, and then based on the collected data of the target monitoring equipment, the points of the target monitoring equipment corresponding to the collected data greater than the quality threshold are selected as supplementary trajectory points, and the supplementary trajectory points are added to the historical trajectory to obtain a complete trajectory, which is called the target historical trajectory. Compared with the trajectory completion method in the related art, it does not require a large amount of data support, and in the completion process, the collected data of the target monitoring equipment in the target area where the object may appear is taken into account, thereby improving the accuracy and operability of the estimated completion.

[0063] In S202, in order to determine where the object has appeared, the data processing device can determine the historical trajectory of the object within a first set time period based on the characteristic information of the object. Optionally, the positions of the various trajectory points constituting the historical trajectory are the positions of the monitoring device that photographed the object within the first set time period. In a specific example, the first set time period can be the N days before the current moment, and N can be, for example, 1, 2, or 3.

[0064] Exemplarily, the process of the data processing device determining the historical trajectory of the object within the first set time period can be implemented through steps A1-A2:

[0065] A1: The data processing device obtains a location information set and a collection time set of each monitoring device that collects feature information of the object within a first set time period.

[0066] Among them, N is taken as 1 for example. In the past day, for example, 100 monitoring devices have photographed the object, then the data processing device obtains 100 location information of these 100 monitoring devices, and the combination of these 100 location information is called a location information set. These 100 location information are the 100 trajectory points of the object in the first set time period. Under normal circumstances, the monitoring equipment that can capture the characteristic information of the object includes a high-definition acquisition device and the captured image can reflect the characteristic information of the object. For example, although it is a high-definition acquisition device, the captured image quality is very poor or it is a partial image of the object, so the position of the high-definition acquisition device cannot be used as a trajectory point. In addition, ordinary cameras mostly capture video streams or have low resolutions. Therefore, in the process of determining historical trajectories, the monitoring equipment involved usually does not include ordinary cameras.

[0067] A2: The data processing device determines the historical trajectory of the object within a set time period based on the location information set, the collection time set and the road network information.

[0068] The road network information is the road traffic network information of the roads where each monitoring device that collected the characteristic information of the object within a set time period is located. For example, if the 100 monitoring devices are all in Laoshan District, Qingdao City, the road network information here can be the road traffic network information of Laoshan District. In actual application, the road network information can also directly use the road traffic network information of the entire city.

[0069] Optionally, the data processing device can generate a historical trajectory within the past day based on the 100 trajectory points and the corresponding 100 collection times and road network information.

[0070] Regarding S203, usually, the aforementioned 100 monitoring devices are all high-definition acquisition devices and the images captured can reflect the characteristic information of the object. However, in the actual application process, the historical trajectory of the object also includes two other types of monitoring devices, one of which is a high-definition acquisition device but the image of the object captured is unavailable, and the other type of monitoring device is an ordinary camera. Therefore, after obtaining the historical trajectory, in order to improve the effect, the historical trajectory needs to be supplemented, and the historical trajectory is supplemented according to the collection data of these two types of monitoring devices.

[0071] Optionally, the historical trajectory is composed of multiple trajectory points, each of which can be called a point position, and two adjacent point positions can form a road section, and the sections are connected in sequence to form the historical trajectory.

[0072] There are usually other monitoring devices between two monitoring devices on each road section. In order to find other monitoring devices, we first determine the area near these two monitoring devices that the object may pass through. Taking a road section as an example, we will explain the process of determining the monitoring area corresponding to the road section. The monitoring area is the area that the object may pass through when it is active on this road section.

[0073] Exemplarily, the process of determining the monitoring area corresponding to a road section can be implemented through steps B1-B3:

[0074] B1: The data processing device determines the predicted movement area of ​​the object on the road section according to the position information of the starting point and the ending point of the road section, the predicted speed of the object when moving on the road section, and the movement duration.

[0075] Among them, the road section is L 1 Indicates that the starting point of the road section is K 1 Indicates that the end point is J 1 Indicates; the object is in L 1 The predicted speed during movement is V 1 Indicates the duration of exercise by △T 1 Indicates. Exercise duration △T 1 Represented as road segment L1 Monitoring equipment C deployed at the starting point 1 The first time t of data collection for the object 1 , and the monitoring equipment C deployed at the end point of the road section 2 The second time t at which data is collected from the object 2 time difference.

[0076] Optionally, determining the motion prediction area of ​​the object in the road section may be achieved through steps B11-B12:

[0077] B11: Based on a geospatial algorithm, the data processing device determines a first monitoring area according to the location information of the starting point of the road section, the predicted speed of the object when moving on the road section, and the duration of the movement, and determines a second monitoring area according to the location information of the ending point of the road section, the predicted speed of the object when moving on the road section, and the duration of the movement.

[0078] Among them, according to any point, and the movement speed and movement duration of the target object as input, the possible movement range of the target object can be determined by applying the geospatial algorithm. 1 The position information of the starting point, the predicted speed V of the object when it moves on the road section 1 And the exercise duration △T 1 , determine the first monitoring area F 1 ; According to the end point of the road section J 1 The location information of the end point and the predicted speed V of the object when it moves on the road section 1 And the exercise duration △T 1 , determine the second monitoring area F 2 .

[0079] B12: The data processing device determines an intersection area of ​​the first monitoring area and the second monitoring area as a motion prediction area of ​​the object on the road section.

[0080] Among them, the first monitoring area F 1 and the second monitoring area F 2 are all areas where the object may pass through. Therefore, in order to improve the positioning accuracy, the data processing device sets the first monitoring area F 1 and the second monitoring area F 2 The intersection area of ​​the object is taken as the intersection area of ​​the object on the road section L 1 motion prediction area, that is, the object has a high probability of appearing in the motion prediction area.

[0081] Figure 3 A schematic diagram of a motion prediction area provided in an embodiment of the present application, wherein 31 is a first monitoring area F 1, 32 Second monitoring area F 2 , 33 is the motion prediction area, 34 is the starting point K 1 , 35 is the end point J 1 .

[0082] Optionally, the predicted speed of the object when moving on the road segment can be determined as follows:

[0083] The data processing device determines the predicted speed of the object when it moves on the road section according to the movement time of the object on the road section, the predicted movement distance on the road section and the set parameters.

[0084] Still L 1 For example, the predicted speed V 1 =n 1 *(S 1 / △T 1 ), where in section L 1 The predicted movement distance is S 1 , set the parameter to n 1 , on section L 1 The exercise duration is △T 1 Among them, the predicted movement distance S 1 K is the starting point 1 and end point J 1 The straight-line distance between them, or, based on the starting point K 1 , J 1 The distance determined by the road network information can be found in K 1 and J 1 When the distance between the two is not a straight line, the distance between them can be determined more accurately. Set the parameter n 1 It is used to represent the predicted motion mode of the object, where the predicted motion mode is, for example, walking, running, cycling, etc. The setting parameters are different for different predicted motion modes.

[0085] B2: The data processing device searches for at least one monitoring device in the motion prediction area.

[0086] In the motion prediction area, at least one monitoring device is deployed. In the actual application process, the monitoring device found may include road section L 1 Monitoring equipment deployed at the starting point or road section L 1 Monitoring equipment deployed at the termination point. Figure 3 , 36 is the monitoring device in the motion prediction area. In this example, the number of monitoring devices in the motion detection area is 4.

[0087] B3: The data processing device determines the monitoring area corresponding to the road section according to the location information of the starting point of the road section, the location information of the ending point and the location information of at least one monitoring device.

[0088] Continue to refer Figure X The implementation process of determining the monitoring area corresponding to the road section is described through steps B31-B32:

[0089] B31: The data processing device determines the predicted path information of the object corresponding to the road section based on the location information of the starting point and the ending point of the road section, the location of at least one monitoring device, and the road network information.

[0090] Among them, at least one monitoring device takes four ABCD as an example, then according to the road section L 1 The starting point K 1 , the location a of monitoring device A and the road network information can determine the predicted path p 1 ; According to section L 1 The starting point K 1 , the location b of monitoring device B and the road network information can determine the predicted path p 2 ; According to section L 1 The starting point K 1 , the location c of the monitoring device C and the road network information can determine the predicted path p 3 ; According to section L 1 The starting point K 1 , the location d of the monitoring device D and the road network information can determine the predicted path p 4 . Figure 4 A schematic diagram of a prediction path provided in an embodiment of the present application.

[0091] B32: The data processing device determines a monitoring area corresponding to the road section according to at least one path represented by the predicted path information.

[0092] Figure 5 A schematic diagram of a monitoring area provided in an embodiment of the present application, wherein according to p 1 、p 2 、p 3 and p 4 These four paths determine the section L 1 The starting point K 1 and end point J 1 and p 1 、p 2 、p 3 and p 4 The largest closed area formed by these four paths is section L. 1 The corresponding monitoring area 51.

[0093] In S204, the data processing device identifies the deployed target monitoring devices in the target area constituted by the monitoring areas corresponding to the respective road sections.

[0094] In the above embodiment, a road section of the historical track is taken as an example to illustrate the monitoring area corresponding to the road section. However, the historical track includes multiple road sections, so the combination of monitoring areas corresponding to each road section can constitute the target area. Figure 6 A schematic diagram of a target area provided in an embodiment of the present application, the target area is composed of three areas corresponding to three road sections, and the three road sections are respectively the section composed of point 1 and point 2, the section composed of point 2 and point 3, and the section composed of point 3 and point 4.

[0095] In the target area, search for target monitoring devices deployed in the target area. These target monitoring devices are either high-definition acquisition devices but the images collected in the past day are unavailable, or ordinary cameras but the images collected in the past day are unavailable, or the collected data is video data, the video data is not processed in time or the processed images are unavailable.

[0096] In S205, the data processing device selects the point of the target monitoring device corresponding to the collected data greater than the quality threshold as the supplementary trajectory point based on the collected data of the target monitoring device.

[0097] Since only the data of high-definition acquisition devices are usually used in the process of determining historical trajectories. However, in the process of searching for supplementary trajectory points, the data processing device re-evaluates the quality of the acquisition data of each target monitoring device based on the acquisition data of the target monitoring device in the target area, and uses the set algorithm to re-evaluate the quality of the acquisition data of each target monitoring device, and uses the point of the target monitoring device corresponding to the acquisition device whose quality is greater than the quality threshold as the supplementary trajectory point. Alternatively, there is also a situation where, for video data that has not been processed in time, it is structured and processed, and then the quality of the obtained image is judged to determine whether it can be used as a supplementary trajectory point.

[0098] In step S206 , the supplementary track point is added to the historical track to determine the target historical track of the object.

[0099] Optionally, the supplementary trajectory point is added to the historical trajectory according to the position relationship between the position of the supplementary trajectory point and the trajectory point in the historical trajectory point to obtain the target historical trajectory of the object.

[0100] In the above embodiment, based on the historical trajectory, supplementary trajectory points are searched and added to the historical trajectory to obtain a more dense trajectory as the target historical trajectory. The target historical trajectory has more trajectory points than the historical trajectory, which can better help determine the location of the object.

[0101] Optional, Figure 7 A schematic diagram of a target historical trajectory provided in an embodiment of the present application, wherein the dotted line is the original historical trajectory, the dotted line is the supplementary trajectory composed of supplementary trajectory points, and the combination of the two is the target historical trajectory.

[0102] In order to locate the object in real time, the real-time trajectory of the object can also be determined. Figure 8 A flowchart for determining a real-time trajectory provided in an embodiment of the present application, Figure 8 At least the following steps are included:

[0103] S801: The data processing device obtains the latest point information in the target historical trajectory of the object.

[0104] The latest point information in the target historical track of the object can be the position of the track point in the original historical track, or the position of the newly added supplementary track point in the target historical track. Figure 6 , taking the former as an example, the latest point information is the point information of point 4.

[0105] S802: The data processing device determines a set of predicted points according to the point information and a set prediction model.

[0106] Optionally, the prediction model can be set based on the historical position information of a set number of objects, for example, obtained through neural network training. The position information of the latest point, point 4, is used as the input of the set model, and the output is a set of predicted points, that is, the position where the object may appear next can be output as the predicted point.

[0107] In addition, the data processing device can obtain the collected data of the monitoring equipment deployed at each point in the prediction point set in real time.

[0108] S803: If the data processing device detects the second alarm information, when the alarm point information in the second alarm information belongs to the predicted point set, the alarm point information is used as a trajectory point to update the target historical trajectory.

[0109] Among them, if the second alarm information is detected, and the second alarm information includes alarm point information, when the alarm point information belongs to the predicted point set, the alarm point information can be added to the target historical trajectory as a trajectory point to update the target historical trajectory.

[0110] In addition, if the second alarm information is not detected within the second set time period, in order to reduce the data processing pressure of the data processing device, the collection data of the monitoring device deployed at each prediction point in the prediction point set can be stopped. In actual applications, monitoring devices may no longer be deployed at these points.

[0111] S804: The data processing device applies the latest point information in the updated target historical trajectory to re-execute the step of predicting the point set until the stop condition is met to obtain the real-time trajectory.

[0112] For example, if the point represented by the alarm point information included in the second alarm information is represented by point 5, then point 5 is applied to continue to execute the steps of the predicted point set until the set stop condition is met. The set stop condition here can be a time condition or a number condition. The time condition is, for example, until which moment, and the number condition can be a certain number of loop executions. With such a design, the last updated trajectory is called a real-time trajectory. The real-time trajectory includes each updated trajectory point.

[0113] For example, the trajectory information of each trajectory point in the target historical trajectory and real-time trajectory includes the location information of the monitoring equipment deployed at each trajectory point, as well as the collected data of the object collected by each monitoring equipment. This design allows you to quickly obtain information such as the image of the object at a certain trajectory point when viewing the trajectory, such as whether it is wearing a mask or glasses, or the specific behavior in the current image. A complete trajectory can ensure the effectiveness of control or tracking.

[0114] like Fig. 9 As shown, based on the same inventive concept, an embodiment of the present application provides a trajectory completion device, which includes a data acquisition unit 91, a historical trajectory determination unit 92, a monitoring area determination unit 93, a target monitoring device identification unit 94, a trajectory point selection unit 95 and a trajectory completion unit 96.

[0115] The data acquisition unit 91 is used to: acquire first warning information; wherein the first warning information includes characteristic information for describing the object;

[0116] A historical track determination unit 92 is used to determine the historical track of the object within a first set time period according to the feature information of the object;

[0117] The monitoring area determination unit 93 is used to: determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point;

[0118] The target monitoring device identification unit 94 is used to: identify the deployed target monitoring devices in the target area formed by the monitoring areas corresponding to each road section;

[0119] The track point selection unit 95 is used to select, according to the collected data of the target monitoring device, the point position of the target monitoring device corresponding to the collected data greater than the quality threshold as the supplementary track point;

[0120] The trajectory completion unit 96 is used to add the supplementary trajectory points to the historical trajectory to determine the target historical trajectory of the object.

[0121] In an optional implementation, the historical trajectory determination unit 92 is specifically configured to:

[0122] Acquire a set of location information of each monitoring device that has collected feature information of the object within a first set time period;

[0123] The historical trajectory of the object within a first set time period is determined based on the location information set and the road network information; wherein the road network information is the road traffic network information of the roads where each monitoring device that collected the characteristic information of the object within the set time period is located.

[0124] In an optional implementation manner, the monitoring area determination unit 93 is specifically configured to determine the monitoring area corresponding to any road section in the following manner:

[0125] Determine the predicted motion area of ​​the object on the road section according to the position information of the starting point and the ending point of the road section, the predicted speed of the object when moving on the road section, and the motion duration; wherein the motion duration is the time difference between the first time when the monitoring equipment deployed at the starting point of the road section collects data on the object and the second time when the monitoring equipment deployed at the ending point of the road section collects data on the object;

[0126] Finding at least one monitoring device within the motion prediction area;

[0127] A monitoring area corresponding to the road section is determined according to the position information of the starting point of the road section, the position information of the ending point and the position information of at least one monitoring device.

[0128] In an optional implementation manner, the monitoring area determination unit 93 is specifically configured to:

[0129] Based on the geospatial algorithm, a first monitoring area is determined according to the location information of the starting point of the road section, the predicted speed of the object when moving on the road section, and the movement duration; and a second monitoring area is determined according to the location information of the ending point of the road section, the predicted speed of the object when moving on the road section, and the movement duration;

[0130] An intersection area of ​​the first monitoring area and the second monitoring area is determined as a motion prediction area of ​​the object on the road section.

[0131] In an optional implementation manner, the monitoring area determination unit 93 is specifically configured to:

[0132] Determine predicted path information of an object corresponding to the road section according to location information of a starting point and an ending point of the road section, a location of at least one monitoring device, and road network information;

[0133] According to at least one path represented by the predicted path information, a monitoring area corresponding to the road section is determined.

[0134] In an optional implementation, the monitoring area determination unit 93 is specifically configured to determine the predicted speed of the object when it moves on the road section by:

[0135] Determine the predicted speed of the object when it moves on the road section according to the movement time of the object on the road section, the predicted movement distance on the road section and the set parameters;

[0136] Among them, the predicted movement distance is the straight-line distance between the position information of the starting point and the position information of the ending point, or the distance determined based on the position information of the starting point, the position information of the ending point and the road network information; the setting parameters are used to represent the predicted movement mode of the object.

[0137] In an optional implementation, the system further includes a real-time trajectory determination unit, configured to:

[0138] Get the latest point information in the target historical trajectory of the object;

[0139] Determine a set of prediction points according to the latest point information and a set prediction model; wherein the set model is obtained according to historical point information of a set number of objects;

[0140] If the second warning information is detected, when the warning point information in the second warning information belongs to the predicted point set, the warning point information is used as a trajectory point to update the target historical trajectory;

[0141] In the updated target historical trajectory, the steps of predicting the point set are re-executed using the latest point information until the stop condition is met, thereby obtaining a real-time trajectory; wherein the real-time trajectory includes each updated trajectory point.

[0142] In an optional implementation, after determining the predicted point set according to the latest point information and the set prediction model, the real-time trajectory determination unit is further used to:

[0143] If no alarm information is detected within the second set time period, the receiving of the collected data of the monitoring equipment deployed at each prediction point in the prediction point set is stopped.

[0144] In an optional implementation, the trajectory information of each trajectory point in the historical trajectory and the real-time trajectory of the target includes the location information of the monitoring equipment deployed at each trajectory point, and the collection data of the object collected by each monitoring equipment.

[0145] Since the device is the device in the method in the embodiment of the present application, and the principle of solving the problem by the device is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0146] like Fig.10 As shown, based on the same inventive concept, an embodiment of the present application provides a data processing device, which includes: a processor 1001 and a data transmission unit 1002.

[0147] The data transmission unit 1002 is configured to perform:

[0148] Acquire first warning information; wherein the first warning information includes characteristic information for describing the object;

[0149] The processor 1001 is configured to execute:

[0150] Determine the historical trajectory of the object within a first set time period according to the characteristic information of the object;

[0151] Determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point;

[0152] In the target area formed by the monitoring areas corresponding to each road section, the deployed target monitoring equipment is identified;

[0153] According to the collected data of the target monitoring device, the point of the target monitoring device corresponding to the collected data greater than the quality threshold is selected as the supplementary trajectory point;

[0154] The supplementary track points are added to the historical track to determine the target historical track of the object.

[0155] In an optional implementation, the processor 1001 is specifically configured to execute:

[0156] Acquire a set of location information of each monitoring device that has collected feature information of the object within a first set time period;

[0157] The historical trajectory of the object within a first set time period is determined based on the location information set and the road network information; wherein the road network information is the road traffic network information of the roads where each monitoring device that collected the characteristic information of the object within the set time period is located.

[0158] In an optional implementation, the processor 1001 is specifically configured to execute:

[0159] Determine the predicted motion area of ​​the object on the road section according to the position information of the starting point and the ending point of the road section, the predicted speed of the object when moving on the road section, and the motion duration; wherein the motion duration is the time difference between the first time when the monitoring equipment deployed at the starting point of the road section collects data on the object and the second time when the monitoring equipment deployed at the ending point of the road section collects data on the object;

[0160] Finding at least one monitoring device within the motion prediction area;

[0161] A monitoring area corresponding to the road section is determined according to the position information of the starting point of the road section, the position information of the ending point and the position information of at least one monitoring device.

[0162] In an optional implementation, the processor 1001 is specifically configured to execute:

[0163] Based on the geospatial algorithm, a first monitoring area is determined according to the location information of the starting point of the road section, the predicted speed of the object when moving on the road section, and the movement duration; and a second monitoring area is determined according to the location information of the ending point of the road section, the predicted speed of the object when moving on the road section, and the movement duration;

[0164] An intersection area of ​​the first monitoring area and the second monitoring area is determined as a motion prediction area of ​​the object on the road section.

[0165] In an optional implementation, the processor 1001 is specifically configured to execute:

[0166] Determine predicted path information of an object corresponding to the road section according to location information of a starting point and an ending point of the road section, a location of at least one monitoring device, and road network information;

[0167] According to at least one path represented by the predicted path information, a monitoring area corresponding to the road section is determined.

[0168] In an optional implementation, the processor 1001 is specifically configured to execute:

[0169] Determined based on the object's movement time on the road section, the predicted movement distance on the road section, and set parameters;

[0170] Among them, the predicted movement distance is the straight-line distance between the position information of the starting point and the position information of the ending point, or the distance determined based on the position information of the starting point, the position information of the ending point and the road network information; the setting parameters are used to represent the predicted movement mode of the object.

[0171] In an optional implementation, the processor 1001 is further configured to execute:

[0172] Get the latest point information in the target historical trajectory of the object;

[0173] Determine a prediction point set according to the point information and a set prediction model; wherein the set model is obtained according to historical point information of a set number of objects;

[0174] If the second warning information is detected, when the warning point information in the second warning information belongs to the predicted point set, the warning point information is used as a trajectory point to update the target historical trajectory;

[0175] In the updated target historical trajectory, the steps of predicting the point set are re-executed using the latest point information until the stop condition is met, thereby obtaining a real-time trajectory; wherein the real-time trajectory includes each updated trajectory point.

[0176] In an optional implementation, after determining the predicted point set according to the point information and the set prediction model, the processor 1001 is further configured to execute:

[0177] If no alarm information is detected within the second set time period, the receiving of the collected data of the monitoring equipment deployed at each prediction point in the prediction point set is stopped.

[0178] In an optional implementation, the trajectory information of each trajectory point in the historical trajectory and the real-time trajectory of the target includes the location information of the monitoring equipment deployed at each trajectory point, and the collection data of the object collected by each monitoring equipment.

[0179] The embodiment of the present application further provides a computer storage medium, in which computer program instructions are stored. When the instructions are executed on a computer, the computer executes the steps of the above-mentioned trajectory completion method.

[0180] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0181] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0182] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0183] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0184] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A trajectory completion method, It is characterized in that include: Acquire first warning information; wherein the first warning information includes characteristic information for describing an object; Determining a historical trajectory of the object within a first set time period according to the feature information of the object; Determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point; In the target area formed by the monitoring areas corresponding to each road section, the deployed target monitoring equipment is identified; According to the collected data of the target monitoring device, the point of the target monitoring device corresponding to the collected data greater than the quality threshold is selected as a supplementary trajectory point; The supplementary trajectory point is added to the historical trajectory to determine a target historical trajectory of the object.

2. The method according to claim 1, It is characterized in that The determining, based on the feature information of the object, a historical trajectory of the object within a first set time period includes: Acquire a location information set and a collection time set of each monitoring device that collects feature information of the object within the first set time period; The historical trajectory of the object within the first set time period is determined based on the location information set, the collection time set and the road network information; wherein the road network information is the road traffic network information of the roads where each monitoring device that collected the characteristic information of the object within the first set time period is located.

3. The method according to claim 1, It is characterized in that Determine the monitoring area corresponding to any road section in the following way: Determine the predicted motion area of ​​the object on the road section according to the position information of the starting point and the ending point of the road section, the predicted speed of the object when moving on the road section, and the motion duration; wherein the motion duration is a first time for the monitoring device deployed at the starting point of the road section to collect data from the object, and a second time for the monitoring device deployed at the ending point of the road section to collect data from the object; Searching for at least one monitoring device within the motion prediction area; The monitoring area corresponding to the road section is determined according to the position information of the starting point of the road section, the position information of the ending point and the position information of the at least one monitoring device.

4. The method according to claim 3, It is characterized in that The step of determining the predicted motion area of ​​the object on the road section according to the position information of the starting point and the ending point of the road section, the predicted speed and the motion duration of the object when the object moves on the road section, comprises: Based on a geospatial algorithm, a first monitoring area is determined according to the location information of the starting point of the road section, the predicted speed of the object when moving on the road section, and the movement duration; and a second monitoring area is determined according to the location information of the ending point of the road section, the predicted speed of the object when moving on the road section, and the movement duration; An intersection area of ​​the first monitoring area and the second monitoring area is determined as a motion prediction area of ​​the object on the road section.

5. The method according to claim 3, It is characterized in that The determining the monitoring area corresponding to the road section according to the location information of the starting point of the road section, the location information of the ending point and the location information of the at least one monitoring device includes: Determine predicted path information of the object corresponding to the road section according to the location information of the starting point and the ending point of the road section, the location of the at least one monitoring device, and the road network information; According to at least one path represented by the predicted path information, a monitoring area corresponding to the road section is determined.

6. The method according to any one of claims 3 to 5, It is characterized in that The predicted speed of the object when moving on the road section is determined by: Determining a predicted speed of the object when it moves on the road section according to a movement duration of the object on the road section, a predicted movement distance of the road section, and set parameters; Among them, the predicted movement distance is the straight-line distance between the position information of the starting point and the position information of the ending point, or the distance determined based on the position information of the starting point, the position information of the ending point and the road network information; the set parameters are used to represent the predicted movement mode of the object.

7. The method according to claim 1, It is characterized in that The method further comprises: Obtain the latest point information in the target historical trajectory of the object; Determine a set of predicted points according to the latest point information and a set prediction model; wherein the set model is obtained according to a set number of historical point information of the objects; If the second warning information is detected, in the case where the warning point information in the second warning information belongs to the predicted point set, the warning point information is used as a trajectory point to update the target historical trajectory; In the updated target historical trajectory, the step of predicting the point set is re-executed using the latest point information until the stop condition is met, thereby obtaining a real-time trajectory; wherein the real-time trajectory includes each updated trajectory point.

8. The method according to claim 7, It is characterized in that After determining the predicted point set according to the point information and the set prediction model, the method further includes: If no alarm information is detected within the second set time period, the receiving of the collected data of the monitoring equipment deployed at each prediction point in the prediction point set is stopped.

9. The method according to any one of claims 1 to 5 and 7 to 8, It is characterized in that The trajectory information of each trajectory point in the target historical trajectory and the real-time trajectory includes the location information of the monitoring device of each trajectory point and the collection data of the object collected by each monitoring device.

10. A data processing device, It is characterized in that including a data transmission unit and a processor; The data transmission unit is configured to perform: Acquire first warning information; wherein the first warning information includes characteristic information for describing an object; The processor is configured to perform: Determining a historical trajectory of the object within a first set time period according to the feature information of the object; Determine the monitoring area corresponding to each road section included in the historical trajectory; wherein each road section is composed of two adjacent points, and a monitoring device is deployed at each point; In the target area formed by the monitoring areas corresponding to each road section, the deployed target monitoring equipment is identified; According to the collected data of the target monitoring device, the point of the target monitoring device corresponding to the collected data greater than the quality threshold is selected as a supplementary trajectory point; The supplementary trajectory point is added to the historical trajectory to determine a target historical trajectory of the object.

Images