A cross-terminal target continuous tracking method and a tracking system

Abstract

The application relates to a cross-terminal target continuous tracking method and a tracking system. The method comprises the following steps: determining a tracking object in image data sent back by a first terminal according to obtained instructions; establishing a feature area with the tracking as the center and identifying other objects in the feature area to obtain reference objects; judging the association relationship between the reference objects and the tracking object; searching for the reference objects in image data sent back by a second terminal, determining a search range according to the position of the second terminal when the reference objects exist in the image data sent back by the second terminal; searching for the tracking objects in the search range; matching the tracking objects and suspected tracking objects belonging to the same moving track; and recording the suspected tracking objects matched successfully as the tracking objects. The cross-terminal target continuous tracking method and the tracking system disclosed by the application realize the continuous tracking of the target by matching between different terminals, and further realize the continuous position management of personnel in a coverage range.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a cross-terminal target continuous tracking method and tracking system. BACKGROUND

[0002] Intelligent construction site management refers to the integrated management of personnel, equipment, environment and construction of the construction site through the collection of various means, to realize the centralized display and intelligent analysis of information, and to ensure the progress of the project, the safety of the project and the risk control.

[0003] In a complex construction site with collaborative production, personnel need to be managed as a whole, one purpose being safety management, for example, during collaborative work, rapid personnel determination and personnel evacuation can be carried out, and it can also play a role in personnel search.

[0004] The commonly used method at present is to rely on cameras to obtain images, but the coverage of the camera is limited, and there are difficulties in searching for personnel, personnel positioning and continuous tracking, mainly due to factors such as image clarity, difficulty in cross-camera recognition, and lack of personnel model basic information. Once there is a blind area of the camera, the target is lost. SUMMARY

[0005] The present application provides a cross-terminal target continuous tracking method and tracking system, which realizes the continuous tracking of the target by matching between different terminals, and further realizes the continuous position management of personnel in the coverage range.

[0006] The above-mentioned purpose of the present application is realized by the following technical scheme:

[0007] In a first aspect, the present application provides a cross-terminal target continuous tracking method, comprising:

[0008] According to the obtained instruction, the tracking object is determined in the image data sent back by the first terminal;

[0009] A feature area is established around the tracking object, and other objects in the feature area are identified to obtain a reference object;

[0010] The association relationship between the reference object and the tracking object is judged;

[0011] The reference object is searched in the image data sent back by the second terminal, and when the reference object exists in the image data sent back by the second terminal, the search range is determined according to the position of the second terminal;

[0012] The tracking object is searched in the search range, and a suspected tracking object is found;

[0013] generating a movement track of the tracking object using the tracking object and the suspected tracking object and excluding part of the suspected tracking objects using the movement track;

[0014] matching the tracking object and the suspected tracking object belonging to the same movement track;

[0015] recording the suspected tracking object matched successfully as the tracking object.

[0016] In a possible implementation manner of the first aspect, judging the association relationship between the reference object and the tracking object comprises:

[0017] obtaining the body action and the face orientation change of the tracking object and the body action and the face orientation change of the reference object;

[0018] judging the spatial association of the body action or the face orientation change of the tracking object and the body action or the face orientation change of the reference object and counting the association times;

[0019] when the times are greater than or equal to the allowed times, determining that the reference object and the tracking object have the association relationship.

[0020] In a possible implementation manner of the first aspect, judging the spatial association of the body action or the face orientation change of the tracking object and the body action or the face orientation change of the reference object comprises:

[0021] drawing a body action track according to the body action of the object, the object comprising the tracking object and the reference object;

[0022] drawing a face orientation change track according to the face orientation change of the object, the object comprising the tracking object and the reference object;

[0023] when the body action track and / or the face orientation change track of any two objects coincide, counting the association times;

[0024] wherein the coincidence of the body action track and / or the face orientation change track of any two objects exists in the time dimension and the length of the coincident region is greater than the required length or greater than the required proportion.

[0025] In a possible implementation manner of the first aspect, determining the search range according to the position of the second terminal comprises:

[0026] establishing a search area using the position of the second terminal;

[0027] segmenting the search area using the movement track of the reference object to obtain a plurality of search sub-areas;

[0028] according to the determined relative position of the tracking object and the reference object;

[0029] The relative positions of the tracking object and the reference object are used to select a search sub-region, and the selected search sub-region is used as a search range.

[0030] In a possible implementation of the first aspect, the step of excluding part of the suspected tracking objects using the movement trajectory comprises:

[0031] Assigning coordinate points to the tracking objects and the suspected tracking objects within a spatial range;

[0032] Connecting the tracking objects and the suspected tracking objects according to the time sequence to obtain a movement trajectory, the movement trajectory comprising a plurality of sequentially connected sub-movement trajectories;

[0033] Calculating the movement speed of the sub-movement trajectory, and excluding part of the suspected tracking objects using the movement speed;

[0034] The continuity of the plurality of suspected tracking objects is determined according to the surrounding environment, and the continuity is assigned to the movement trajectory.

[0035] In a possible implementation of the first aspect, the step of assigning the continuity to the movement trajectory comprises:

[0036] Determining the surrounding environment features of one suspected tracking object;

[0037] Using the suspected tracking object and the surrounding environment features to form a feature matrix and recording the movement trajectory of the feature matrix;

[0038] Using the movement trajectory of the feature matrix to replace the movement trajectory of the suspected tracking object.

[0039] In a possible implementation of the first aspect, the step of matching the tracking objects and the suspected tracking objects belonging to the same movement trajectory comprises:

[0040] Transferring the tracking objects into a gray domain and picking up a first gray feature group, the first gray feature group comprising a pattern and a size;

[0041] Transferring the suspected tracking objects into the gray domain and picking up a second gray feature group, the second gray feature group comprising a pattern and a size;

[0042] Putting the similar patterns in the first gray feature group and the second gray feature group into a pattern group;

[0043] Determining a change vector of the pattern group by means of the size and counting the dispersion of the change vector;

[0044] Recording the suspected tracking objects with the dispersion less than or equal to an allowable value as the tracking objects;

[0045] The step of matching is performed on any two objects on the movement trajectory, the objects comprising the tracking objects and the suspected tracking objects.

[0046] In a second aspect, the present application provides a cross-terminal target continuous tracking device, comprising:

[0047] A first data acquisition unit configured to determine a tracking object from image data sent back by the first terminal according to the acquired instruction;

[0048] A second data acquisition unit configured to establish a feature area centered on the tracking and identify other objects in the feature area to obtain a reference object;

[0049] A first judgment unit configured to judge the association between the reference object and the tracking object;

[0050] A search range processing unit configured to search for the reference object in image data sent back by the second terminal, and determine a search range according to the position of the second terminal when the reference object exists in the image data sent back by the second terminal;

[0051] A third data acquisition unit configured to find a suspected tracking object in the search range;

[0052] A movement track unit configured to generate a movement track of the tracking object using the tracking object and the suspected tracking object and exclude part of the suspected tracking object using the movement track;

[0053] A matching unit configured to match the tracking object and the suspected tracking object belonging to the same movement track;

[0054] A first marking unit configured to mark the suspected tracking object that is successfully matched as the tracking object.

[0055] In a third aspect, the present application provides a cross-terminal target continuous tracking system, comprising:

[0056] One or more memories configured to store instructions; and

[0057] One or more processors configured to call and run the instructions from the memories to perform the method as described in the first aspect and any possible implementation manner of the first aspect.

[0058] In a fourth aspect, the present application provides a computer readable storage medium, comprising:

[0059] A program, when the program is run by a processor, the method as described in the first aspect and any possible implementation manner of the first aspect is performed.

[0060] In a fifth aspect, the present application provides a computer program product, comprising program instructions, when the program instructions are run by a computing device, the method as described in the first aspect and any possible implementation manner of the first aspect is performed.

[0061] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, such as generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0062] The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0063] In a possible design, the chip system further includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and arranged on different devices, and connected through wired or wireless means, or the processor and the memory can be coupled on the same device. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 is a schematic block diagram of a step flow of a target continuous tracking method provided by the present application.

[0065] Figure 2 is a schematic diagram of obtaining a reference object provided by the present application.

[0066] Figure 3 is a schematic diagram of a moving track provided by the present application.

[0067] Figure 4 is a schematic diagram of judging whether two tracks coincide provided by the present application.

[0068] Figure 5 is a schematic diagram of obtaining a search sub-region provided by the present application.

[0069] Figure 6 is a schematic diagram of obtaining a moving track provided by the present application.

[0070] Figure 7 is a schematic diagram of screening a moving track provided by the present application.

[0071] Figure 8 is a schematic diagram of projecting a figure on a reference plane provided by the present application. DETAILED DESCRIPTION

[0072] The technical solutions in the present application will be described in further detail below with reference to the drawings.

[0073] The present application discloses a cross-terminal target continuous tracking method, please refer to Figure 1 In some examples, the cross-terminal target continuous tracking method provided by the present application includes the following steps:

[0074] S101, determining the tracking object in the image data sent back by the first terminal according to the obtained instruction;

[0075] S102, establishing a feature area centered on the tracking and identifying other objects in the feature area to obtain a reference object;

[0076] S103, judging the association relationship between the reference object and the tracking object;

[0077] S104, searching for the reference object in the image data sent back by the second terminal, and determining the search range according to the position of the second terminal when the reference object exists in the image data sent back by the second terminal;

[0078] S105, finding the suspected tracking object in the search range;

[0079] S106, generating the moving track of the tracking object using the tracking object and the suspected tracking object and excluding part of the suspected tracking object using the moving track;

[0080] S107, matching the tracking object and the suspected tracking object belonging to the same moving track;

[0081] S108, recording the suspected tracking object matched successfully as the tracking object.

[0082] First of all, it needs to be pointed out that the present application is applied to an analysis server, which collects images through cameras deployed in a coverage range (such as a construction site), and then uses the images to continuously track the tracking object. At present, one difficulty of continuous tracking lies in the discontinuity of the tracking object caused by cross-terminal (camera) and the instability of the information exhibited by the tracking object in the image, which leads to the phenomenon of losing the tracking object in the process of continuous tracking.

[0083] In the present application, specifically, in step S101, first, the tracking object is determined in the image data sent back by the first terminal according to the obtained instruction, and then a feature area is established centered on the tracking and other objects in the feature area are identified to obtain a reference object, that is, the content in step S102, as shown in Figure 2 .

[0084] For the feature area, generally speaking, it is a circular area established with the tracking object as the reference, and the radius value of the circular area is a set value, generally 0.5-1 meters.

[0085] The reference object here refers to other objects in a moving state, including personnel and equipment.

[0086] Then in step S103, the association relationship between the reference object and the tracking object is judged. The purpose of using the reference object is to expand the feature library of the tracking object.

[0087] It should be understood that, in order to identify the tracking object, the features belonging to the tracking object are relied on for identification, and when the features belonging to the tracking object are less, the feature library of the tracking object needs to be expanded, and in the present application, the reference object is used to expand the feature library of the tracking object.

[0088] In step S104, the reference object is searched in the image data sent back by the second terminal, and when the reference object exists in the image data sent back by the second terminal, the search range is determined according to the position of the second terminal, that is, the range in which the reference object appears, and the tracking object is also likely to appear in this range.

[0089] Then step S105 is executed, in which the tracking object is searched in the search range, and a suspected tracking object is found, and the suspected tracking object is still found by using the feature library mentioned above, for example, an object is found to have one or two (or a reference set rule) features in the feature library, and the object is recorded as a suspected tracking object.

[0090] In step S106, the movement trajectory of the tracking object is generated using the tracking object and the suspected tracking object, and part of the suspected tracking object is excluded using the movement trajectory, and at this time, the movement trajectory obtained is as shown in FIG. 5, there are two possibilities of reasonable and unreasonable, and the unreasonable movement trajectory is excluded, so that part of the suspected tracking object can be excluded. Figure 3

[0091] Then in step S107, the tracking object and the suspected tracking object belonging to the same movement trajectory are matched, and the result is matched and not matched, at this time, the suspected tracking object not matched is excluded. The suspected tracking object matched successfully is recorded as a tracking object, that is, the content in step S108.

[0092] One application scenario of the above-mentioned method is that a tracking object is specified in the obtained video, and then the analysis server can give the movement trajectory of the tracking object, and after the movement trajectory of the tracking object is obtained, analysis can be performed according to the movement trajectory of the tracking object and the required result can be obtained.

[0093] The application scenario of the present application is mainly a multi-person scene, and the multi-person scene has interference factors such as position change and mutual shielding, and the technical solution in the present application just uses the information provided by the multi-person to realize the persistent tracking of the tracking object.

[0094] In some examples, the specific way of judging the association relationship between the reference object and the tracking object is as follows:

[0095] S201, obtaining the changes of the limb action and the face orientation of the tracking object and the changes of the limb action and the face orientation of the reference object; ​

[0096] S202, judge the spatial correlation between the body movement or face orientation change of the tracking object and the body movement or face orientation change of the reference object and count the number of correlations;

[0097] S203, when the number is greater than or equal to the allowed number, determine that the reference object and the tracking object have a correlation.

[0098] The contents in steps S201 to S203 are to judge the correlation between the reference object and the tracking object through body movement and face orientation change, and the specific judging method is based on the spatial correlation.

[0099] When two movements (body movement and body movement, face orientation change and face orientation change, body movement and face orientation change) are considered to have a spatial correlation, the number of correlations between the reference object and the tracking object is accumulated, and when the number is greater than or equal to the allowed number, it is determined that the reference object and the tracking object have a correlation.

[0100] The way to judge the spatial correlation between the body movement or face orientation change of the tracking object and the body movement or face orientation change of the reference object is:

[0101] Draw a body movement trajectory according to the body movement of the object, which includes the tracking object and the reference object;

[0102] Draw a face orientation change trajectory according to the face orientation change of the object, which includes the tracking object and the reference object;

[0103] When the body movement trajectory and / or face orientation change trajectory of any two objects coincide, count the number of correlations;

[0104] Wherein, the coincidence of the body movement trajectory and / or face orientation change trajectory of any two objects exists in the time dimension and the length of the overlapping area is greater than the required length or greater than the required proportion.

[0105] The above method is to judge through the movement trajectory, the body movement trajectory is drawn according to the body movement, and the face orientation change trajectory is drawn according to the face orientation change, which is an arc line drawn from a feature of the face (such as eyes, nose, mouth, etc.), and each feature is set with a fixed parameter, for example, the eye is assigned a rotation radius, which is obtained by measuring the average value of many people.

[0106] The body movement trajectory is a line segment, a combination of multiple line segments connected end to end, or an arc line.

[0107] Please refer to Figure 4When the body action trajectory and / or the face orientation change trajectory of any two objects coincide, the coincidence in the time dimension and the length of the coincident region greater than the required length or greater than the required proportion are required, where the length and proportion are set values.

[0108] Here, the reaction time is mainly considered, for example, the reaction time of the reference object should be limited when the subject makes a movement. The limitation methods include complete coincidence in the time dimension, the length of the coincident region greater than the required length, and the length of the coincident region greater than the required proportion.

[0109] For coincidence, one end of the body action trajectory and / or the face orientation change trajectory of any two objects is placed at the same point, and then one of the trajectories (body action trajectory, face orientation change trajectory) is rotated and proportionally adjusted to make the two trajectories coincide as much as possible. Then the length of the coincident region is calculated, and when the length accounts for

[0110] For the required length and the required proportion, the identification accuracy is generally limited. The higher the identification accuracy, the greater the values of the required length and the required proportion, and vice versa.

[0111] In some examples, the search range is determined according to the position of the second terminal in the following way:

[0112] S301, establishing a search area using the position of the second terminal;

[0113] S302, segmenting the search area using the movement trajectory of the reference object to obtain a plurality of search sub-areas;

[0114] S303, determining the relative position of the tracking object and the reference object;

[0115] S304, using the relative position of the tracking object and the reference object to select a search sub-area, and using the selected search sub-area as the search range.

[0116] In the above method, please refer to Figure 5 , the search area is segmented using the movement trajectory of the reference object to obtain a plurality of search sub-areas. Generally, the number of search sub-areas is two. Here, the reference object is in the horizontal direction, and the number of search sub-areas is two.

[0117] Then, according to the relative position of the tracking object and the reference object, the search sub-area is selected, for example, the tracking object is located on the left side of the reference object, and then the left search sub-area is selected as the search range. The purpose of this method is to reduce the area of the search range, and at this time, the probability of the tracking object existing in the search range is large.

[0118] However, when the search range is finally determined to have no tracking object, the search range needs to be expanded.

[0119] In some examples, the step of using the moving trajectory to exclude part of the suspected tracking objects is as follows:

[0120] S401, coordinate points are given to the tracking objects and the suspected tracking objects in a space range;

[0121] S402, the tracking objects and the suspected tracking objects are connected according to the time sequence to obtain a moving trajectory, the moving trajectory including a plurality of sequentially connected sub-moving trajectories;

[0122] S403, the moving speed of the sub-moving trajectory is calculated, and part of the suspected tracking objects is excluded using the moving speed;

[0123] In the above manner, the continuity of the plurality of suspected tracking objects is determined by referring to the surrounding environment, and the continuity is given to the moving trajectory.

[0124] Please refer to Figure 6 In the above manner, the suspected tracking objects are sorted by time sequence, and then sequentially connected to obtain a moving trajectory, at this time, the position of the suspected tracking object can be regarded as a point. The moving trajectory includes a plurality of sequentially connected sub-moving trajectories, and each sub-moving trajectory includes only two points.

[0125] Then the moving speed of the sub-moving trajectory can be calculated, and part of the suspected tracking objects can be excluded using the moving speed. As for the moving speed, a reference value (given by a person) is used or the actual moving speed of the tracking object in the above manner is used, and when there is no actual moving speed, the reference value (given by a person) is used.

[0126] Through the above manner, part of the sub-moving trajectories can be excluded, and compared with Figure 6 and Figure 7 .

[0127] When excluded, only the suspected tracking object at the end of the sub-moving trajectory is deleted, because the above manner can only determine that the suspected tracking object at the end of the sub-moving trajectory is wrong.

[0128] Then the above process is repeated, and one or more moving trajectories can be obtained.

[0129] In addition, the continuity of the plurality of suspected tracking objects can be determined by referring to the surrounding environment, and the continuity is given to the moving trajectory, for example, a suspected tracking object appears at different time points, and there are other objects in the surrounding environment of the suspected tracking object, and these objects can determine the continuity of the suspected tracking object.

[0130] At this time, continuity is given to the movement trajectory, that is, this part of the movement trajectory is directly fixed, rather than being obtained using a method of connecting in the order of occurrence time.

[0131] The specific way of giving continuity to the movement trajectory is as follows:

[0132] A surrounding environment feature of a suspected tracking object is determined.

[0133] A feature matrix is formed using the suspected tracking object and the surrounding environment feature, and a movement trajectory of the feature matrix is recorded.

[0134] The movement trajectory of the feature matrix is used to replace the movement trajectory of the suspected tracking object.

[0135] When a plurality of movement trajectories are obtained, a method of matching tracking objects and suspected tracking objects belonging to the same movement trajectory is used for processing. Even if the movement trajectory has been processed using the speed screening method, there is still a possibility that the tracking objects and the suspected tracking objects belong to two objects or a plurality of objects.

[0136] In some examples, the step of matching tracking objects and suspected tracking objects belonging to the same movement trajectory is as follows:

[0137] S501, the tracking object is transferred to the gray domain and a first gray feature group is picked up, the first gray feature group including a pattern and a size;

[0138] S502, the suspected tracking object is transferred to the gray domain and a second gray feature group is picked up, the second gray feature group including a pattern and a size;

[0139] S503, similar patterns in the first gray feature group and the second gray feature group are put into a pattern group;

[0140] S504, a change vector of the pattern group is determined by means of the size, and a dispersion of the change vector is counted;

[0141] S505, the suspected tracking object with a dispersion less than or equal to an allowable value is recorded as a tracking object;

[0142] Wherein, any two objects on the movement trajectory need to be matched, and the objects include tracking objects and suspected tracking objects.

[0143] In steps S501 to S505, the tracking object is first transferred to the gray domain, that is, the tracking object is gray processed, and then the tracking object after gray processing is picked up to obtain a first gray feature group, the first gray feature group including a pattern and a size, the size being the size of the pattern. The same processing method is used for the suspected tracking object.

[0144] Then, similar patterns in the first and second gray feature groups are put into a pattern group, and then a change vector of the pattern group is determined by comparing the specific change direction when a pattern in the pattern group changes into another pattern. A specific way is to establish a reference plane, place the first pattern in the pattern group on the reference plane, and move the second pattern in space and project it on the reference plane, as shown in Figure 8 .

[0145] When the projected pattern coincides with the first pattern on the reference plane, a direction vector is generated according to the movement of the second pattern in space.

[0146] A quantitative expression of the change vector is to assign different directions to the six degrees of freedom (X-axis movement, Y-axis movement, Z-axis movement, X-axis rotation, Y-axis rotation, and Z-axis movement), and then take the movement amount (angle, distance) as the length in each direction, that is, to decompose the movement of the second pattern in space into six basic movements.

[0147] A plurality of change vectors are obtained, and then the dispersion of the change vectors is counted. The dispersion of the change vectors refers to the similarity of two change vectors. One evaluation method is to put the two change vectors into a coordinate system so that their starting points or ending points coincide, and then move one of the change vectors so that the two change vectors coincide as much as possible, and then count the proportion of the length of the coincident part to obtain a proportion value.

[0148] When counting the length of the coincident part, if the maximum straight line distance of a part of the two change vectors is within the allowed range (set value), it is also considered that the part coincides.

[0149] Each group (two) of change vectors is processed to obtain a proportion value, and then the dispersion of the proportion values (change vectors) is counted. The dispersion is counted by removing the maximum value in the proportion value and the minimum value in the proportion value, and then obtaining an interval, which has a length.

[0150] Finally, the suspected tracking object with a dispersion less than or equal to the allowed value is recorded as a tracking object. The allowed value here is a set value related to the recognition accuracy.

[0151] In the above process, any two objects on the movement track need to be matched, including tracking objects and suspected tracking objects.

[0152] The application also provides a cross-terminal target continuous tracking device, comprising:

[0153] A first data acquisition unit is configured to determine a tracking object in image data sent back by a first terminal according to an acquired instruction.

[0154] a second data acquisition unit configured to establish a feature area centered on the tracking object and identify other objects in the feature area to obtain a reference object;

[0155] a first judgment unit configured to judge a correlation between the reference object and the tracking object;

[0156] a search range processing unit configured to search for the reference object in image data sent back by the second terminal, and determine a search range according to a position of the second terminal when the reference object exists in the image data sent back by the second terminal;

[0157] a third data acquisition unit configured to find a suspected tracking object in the search range;

[0158] a movement trajectory unit configured to generate a movement trajectory of the tracking object using the tracking object and the suspected tracking object, and exclude part of the suspected tracking object using the movement trajectory;

[0159] a matching unit configured to match the tracking object and the suspected tracking object belonging to the same movement trajectory;

[0160] a first marking unit configured to mark the suspected tracking object matched successfully as the tracking object.

[0161] Further, the method further comprises:

[0162] a fourth data acquisition unit configured to acquire a body movement and a face orientation change of the tracking object and a body movement and a face orientation change of the reference object;

[0163] a second judgment unit configured to judge a spatial correlation between the body movement or the face orientation change of the tracking object and the body movement or the face orientation change of the reference object and count a correlation number;

[0164] a first determination unit configured to determine that the reference object and the tracking object have a correlation when the number is greater than or equal to a permitted number.

[0165] Further, the method further comprises:

[0166] a first trajectory drawing unit configured to draw a body movement trajectory according to a body movement of an object, the object including the tracking object and the reference object;

[0167] a second trajectory drawing unit configured to draw a face orientation change trajectory according to a face orientation change of an object, the object including the tracking object and the reference object;

[0168] a counting unit configured to count the correlation number when the body movement trajectory and / or the face orientation change trajectory of any two objects coincide;

[0169] The coincidence of the limb movement track and / or the face orientation change track of any two objects in the time dimension has a length of the coincident area greater than a required length or greater than a required proportion.

[0170] Further, the method further comprises:

[0171] The area establishing unit is configured to establish the search area using the location of the second terminal.

[0172] The area dividing unit is configured to divide the search area using the movement track of the reference object to obtain a plurality of search sub-areas.

[0173] The position determining unit is configured to determine the relative position between the tracking object and the reference object.

[0174] The area selecting unit is configured to select the search sub-area using the relative position between the tracking object and the reference object, and use the selected search sub-area as the search range.

[0175] Further, the method further comprises:

[0176] The coordinate assigning unit is configured to assign a coordinate point to the tracking object and the suspected tracking object within a space range.

[0177] The first movement track processing unit is configured to connect the tracking object and the suspected tracking object according to the time sequence to obtain a movement track, the movement track comprising a plurality of sequentially connected sub-movement tracks.

[0178] The speed calculating unit is configured to calculate the movement speed of the sub-movement track, and exclude part of the suspected tracking objects using the movement speed.

[0179] The reference surrounding environment determines the continuity of the plurality of suspected tracking objects, and the continuity is assigned to the movement track.

[0180] Further, the method further comprises:

[0181] The second determining unit is configured to determine the surrounding environment feature of one suspected tracking object.

[0182] The feature matrix processing unit is configured to use the suspected tracking object and the surrounding environment feature to form a feature matrix, and record the movement track of the feature matrix.

[0183] The second movement track processing unit is configured to replace the movement track of the suspected tracking object with the movement track of the feature matrix.

[0184] Further, the method further comprises:

[0185] The first processing unit is configured to transfer the tracking object into a gray domain and pick up a first gray feature group, the first gray feature group comprising a pattern and a size.

[0186] a second processing unit configured to transfer the suspected tracking object into a gray scale domain and pick up a second gray scale feature set, the second gray scale feature set comprising patterns and sizes;

[0187] a grouping unit configured to group similar patterns in the first gray scale feature set and the second gray scale feature set into a pattern group;

[0188] a third processing unit configured to determine a variation vector of the pattern group by means of the sizes and calculate a dispersion of the variation vector;

[0189] a second marking unit configured to mark the suspected tracking object as a tracking object if the dispersion is less than or equal to an allowed value;

[0190] wherein any two objects on the moving track need to be matched, the objects including tracking objects and suspected tracking objects.

[0191] In one example, the units in any of the above apparatuses can be one or more integrated circuits configured to implement the above methods, for example, one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0192] For another example, when the units in the apparatuses can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor that can invoke programs. For another example, these units can be integrated together in the form of a system-on-a-chip (SOC).

[0193] In the present application, various messages / information / devices / network elements / systems / apparatuses / actions / operations / processes / concepts, etc. of various objects that can appear in the present application are named, and it can be understood that these specific names do not constitute a limitation on the related objects, and the names can be changed according to the scene, context or usage habits, etc. The technical meaning of the technical terms in the present application should be mainly determined from the function and technical effect embodied / implemented in the technical scheme.

[0194] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, apparatus and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0195] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0196] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to the actual needs to achieve the purposes of the embodiments.

[0197] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present application can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0198] It should also be understood that in various embodiments of the present application, the first, second, etc. are only to represent that a plurality of objects are different. For example, the first time window and the second time window are only to represent different time windows. There should be no impact on the time window itself, and the above first, second, etc. should not cause any limitation to the embodiments of the present application.

[0199] It should also be understood that in various embodiments of the present application, the terms and / or descriptions of different embodiments have consistency and can be mutually referred to if there is no special description and logical conflict. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0200] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a computer readable storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned computer readable storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0201] The present application also provides a cross-terminal target continuous tracking system, which comprises:

[0202] One or more memories for storing instructions; and

[0203] One or more processors for invoking and running the instructions from the memories to perform the methods as described in the above.

[0204] The present application also provides a computer program product, which includes instructions that, when executed, cause the target continuous tracking system (terminal device and network device) to perform operations of the target continuous tracking system (terminal device and network device) corresponding to the above methods.

[0205] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above, such as generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0206] The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0207] The processor mentioned in any of the above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the programs of the above feedback information transmission method.

[0208] In a possible design, the chip system further includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and arranged on different devices, connected through wired or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device. ​​​​​​​​

[0209] Optionally, the computer instructions are stored in a memory.

[0210] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal, outside the chip, such as a ROM or other type of static storage device that can store static information and instructions, a RAM, etc.

[0211] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0212] The non-volatile memory can be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory.

[0213] The volatile memory can be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM).

[0214] The embodiments of the present specific implementation are the preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, any equivalent changes made in the structure, shape, and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for continuous target tracking across terminals, characterized in that, include: Based on the received instructions, the tracking object is determined from the image data sent back by the first terminal; A feature region is established centered on the tracked object, and other objects within the feature region are identified to obtain a reference object; Determine the relationship between the reference object and the tracked object by observing changes in body movements and facial orientation; Search for reference objects in the image data sent back by the second terminal. When a reference object exists in the image data sent back by the second terminal, determine the search range based on the location of the second terminal. Search for the target within the search scope and find the suspected target; Use the tracked object and suspected tracked object to generate the movement trajectory of the tracked object and use the movement trajectory to exclude some suspected tracked objects; Matching tracked objects and suspected tracked objects belonging to the same movement trajectory; Record the suspected tracked object that is successfully matched as the tracked object; Determining the relationship between the reference object and the tracked object includes: Acquire the limb movements and facial orientation changes of the tracked object and the limb movements and facial orientation changes of the reference object; Determine the spatial correlation between the limb movements or facial orientation changes of the tracked object and the limb movements or facial orientation changes of the reference object, and count the number of correlations; When the number of occurrences is greater than or equal to the allowed number of occurrences, it is determined that there is a relationship between the reference object and the tracked object.

2. The cross-terminal continuous target tracking method according to claim 1, characterized in that, Determining the spatial correlation between the limb movements or facial orientation changes of the tracked object and those of the reference object includes: Draw the limb movement trajectory based on the limb movements of the object, which includes the tracking object and the reference object; Draw the trajectory of facial orientation change based on the changes in the facial orientation of the object, which includes the tracking object and the reference object; When the limb movement trajectories and / or facial orientation change trajectories of any two objects match, the number of associations is counted. Among them, the limb movement trajectories and / or facial orientation change trajectories of any two objects coincide in the time dimension and the length of the overlapping area is greater than the required length or greater than the required proportion.

3. The cross-terminal continuous target tracking method according to claim 1 or 2, characterized in that, Determining the search scope based on the location of the second terminal includes: Establish the search area using the location of the second terminal; The search area is divided into multiple search sub-regions by using the movement trajectory of the reference object; Determine the relative position of the tracking object and the reference object; The search sub-region is selected by using the relative position of the tracked object and the reference object, and the selected search sub-region is used as the search range.

4. The cross-terminal continuous target tracking method according to claim 1, characterized in that, Using movement tracking to exclude certain suspected individuals from the following categories: Assign coordinate points to the tracked object and suspected tracked object within the spatial range; By connecting the tracked object and the suspected tracked object in chronological order of their appearance, a movement trajectory is obtained. The movement trajectory includes multiple segments of movement trajectory connected in sequence. Calculate the movement speed of the sub-trajectory and use the movement speed to exclude some suspected tracking objects; In this process, the continuity of multiple suspected tracking objects is determined by referring to the surrounding environment, and the continuity is assigned to the movement trajectory.

5. The cross-terminal continuous target tracking method according to claim 4, characterized in that, Imparting continuity to a movement trajectory includes: Determine the environmental characteristics of a suspected target; A feature matrix is ​​composed of suspected tracked objects and surrounding environmental features, and the movement trajectory of the feature matrix is ​​recorded. The movement trajectory of the suspected tracked object is replaced with the movement trajectory of the feature matrix.

6. The cross-terminal continuous target tracking method according to claim 1, 4, or 5, characterized in that, Matching tracked objects and suspected tracked objects belonging to the same movement trajectory includes: The tracked object is transferred to the grayscale region and a first grayscale feature group is picked, which includes the shape and size; The suspected target is transferred to the grayscale region and a second grayscale feature group is picked, which includes the image and size. Similar images from the first grayscale feature group and the second grayscale feature group are grouped into one image group; The variation vector of the graphic group is determined by the size, and the dispersion of the variation vector is statistically analyzed. Suspected tracking objects with a dispersion less than or equal to the allowable value are recorded as tracking objects; In this process, any two objects on the movement trajectory need to be matched, including the tracked object and the suspected tracked object.

7. A cross-terminal continuous target tracking device, characterized in that, include: The first data acquisition unit is used to determine the tracking object from the image data sent back by the first terminal according to the acquired instructions; The second data acquisition unit is used to establish a feature region centered on the tracked object and identify other objects within the feature region to obtain a reference object; The first judgment unit is used to determine the relationship between the reference object and the tracked object; The retrieval range processing unit is used to retrieve reference objects from the image data sent back by the second terminal. When a reference object exists in the image data sent back by the second terminal, the retrieval range is determined based on the location of the second terminal. The third data acquisition unit is used to search for tracking objects within the retrieval scope and find suspected tracking objects; The movement trajectory unit is used to generate the movement trajectory of the tracked object using the tracked object and the suspected tracked object, and to exclude some suspected tracked objects using the movement trajectory. The matching unit is used to match tracked objects and suspected tracked objects belonging to the same movement trajectory; The first marking unit is used to record a successfully matched suspected tracking object as a tracking object; Determining the relationship between the reference object and the tracked object includes: Acquire the limb movements and facial orientation changes of the tracked object and the limb movements and facial orientation changes of the reference object; Determine the spatial correlation between the limb movements or facial orientation changes of the tracked object and the limb movements or facial orientation changes of the reference object, and count the number of correlations; When the number of occurrences is greater than or equal to the allowed number of occurrences, it is determined that there is a relationship between the reference object and the tracked object.

8. A cross-terminal continuous target tracking system, characterized in that, The system includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by the processor, executes the method as described in any one of claims 1 to 6.

Images