Target tracking method and device

Abstract

The present application provides a target tracking method and device, wherein the target tracking method includes: receiving a target to be tracked and a video frame sequence; sequentially identifying the target to be tracked in each video frame of the video frame sequence, obtaining the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; obtaining a conversion rule between the video frame position coordinates and the map position point coordinates in a preset three-dimensional electronic map; converting each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; and drawing the movement trajectory of the target to be tracked in the three-dimensional electronic map according to each three-dimensional map position point coordinate. Through this method, the user can intuitively observe the repeated trajectory of the target to be tracked in different time periods.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more particularly to a target tracking method, a target tracking device, a computing device, and a computer-readable storage medium. Background Art

[0002] Object tracking is an important topic in the field of computer vision and has been widely used in various fields.

[0003] In current mobile target tracking systems, the commonly used target trajectory expression method is usually planar, such as x represents longitude and y represents latitude; another expression method is to use a map as the background, the time axis as the x-axis, and draw the trajectory at a certain point on the map corresponding to time t. However, both of these expressions have a problem: when the same road section appears in different time periods, this path will be drawn multiple times. If the drawing is overwritten, only the last path will be retained and the previous trajectories will not be visible. If the drawing is repeated, the road section will be chaotic and it will not be possible to intuitively reflect the same trajectory of the target to be tracked in different time periods, which is not conducive to the user's observation of the movement trajectory of the target to be tracked. Summary of the Invention

[0004] In view of this, embodiments of the present application provide a target tracking method. This application also relates to a target tracking device, a computing device, and a computer-readable storage medium to address the existing issues of complex display, inconvenient operation, and poor user experience when comparing the movement trajectories of a target to be tracked while passing through the same road section at different time periods.

[0005] According to a first aspect of an embodiment of the present application, a target tracking method is provided, comprising:

[0006] Receive the target to be tracked and the video frame sequence;

[0007] Identifying the target to be tracked in each video frame of the video frame sequence in sequence, and obtaining the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame;

[0008] Obtaining a conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis;

[0009] converting each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate;

[0010] The movement trajectory of the target to be tracked in the three-dimensional electronic map is drawn in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point.

[0011] According to a second aspect of an embodiment of the present application, a target tracking device is provided, comprising:

[0012] A receiving module, configured to receive a target to be tracked and a video frame sequence;

[0013] an identification module configured to sequentially identify the target to be tracked in each video frame of the video frame sequence, and obtain the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame;

[0014] an acquisition module configured to acquire a conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis;

[0015] a conversion module configured to convert each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate;

[0016] The drawing module is configured to draw a movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point.

[0017] According to a third aspect of an embodiment of the present application, a computing device is provided, comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, wherein the processor implements the steps of the target tracking method when executing the computer instructions.

[0018] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer instructions, and when the computer instructions are executed by a processor, the steps of the target tracking method are implemented.

[0019] The target tracking method provided by the present application receives a target to be tracked and a video frame sequence; identifies the target to be tracked in each video frame of the video frame sequence, obtains the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; obtains a conversion rule between the video frame position coordinates and the map position point coordinates in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis; converts each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; and draws the movement trajectory of the target to be tracked in the three-dimensional electronic map according to each three-dimensional map position point coordinate. The target tracking method provided by the embodiment of the present application uses 3D technology to display the overlapping trajectories of different time periods in 3D space, and uses real-world three-dimensional visual effects to represent the repeated trajectories of multiple times, so that the user can intuitively observe the repeated trajectories of the target to be tracked in different time periods. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of a target tracking method provided by one embodiment of the present application;

[0021] Figure 2a This is a schematic diagram of the movement trajectory of a target to be tracked in an electronic map provided by an embodiment of the present application;

[0022] Figure 2b This is a three-dimensional schematic diagram of the motion trajectory of a target to be tracked in an electronic map provided by an embodiment of the present application;

[0023] Figure 3 This is a processing flow chart of a target tracking method for tracking the whereabouts of Zhang San in surveillance, provided by an embodiment of the present application;

[0024] Figure 4 This is a schematic structural diagram of a target tracking device provided by one embodiment of the present application;

[0025] Figure 5 This is a structural block diagram of a computing device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of the present application. Therefore, the present application is not limited to the specific implementations disclosed below.

[0027] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0028] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0029] First, the terms involved in one or more embodiments of the present application are explained.

[0030] SURF algorithm: used for image feature point extraction. The extracted feature points are rotationally invariant and scale invariant, and have higher performance advantages than the SIFT algorithm. It is mainly used in image recognition, dynamic tracking and other fields.

[0031] In this application, a target tracking method is provided. This application also relates to a target tracking device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0032] Figure 1 A flow chart of a target tracking method according to an embodiment of the present application is shown, which specifically includes the following steps:

[0033] Step 102: Receive a target to be tracked and a video frame sequence.

[0034] The target tracking method provided in this application is based on object recognition tracking. Object recognition tracking requires a given tracking picture. After the system obtains the target input, it performs target matching in each video frame of the video, where the target to be tracked is the given target to be tracked, and the video frame sequence is the video frame sequence obtained after decoding the video that needs to be matched with the target.

[0035] The target to be tracked can be a picture, photo, screenshot, etc., or it can be a part selected in a certain video frame in a video frame sequence by receiving a selection instruction from the user. For example, if you need to track a person in a certain video, you can select a screenshot corresponding to the person to be tracked in a certain video frame of the video through the user's selection instruction, and then the screenshot will be the target to be tracked.

[0036] A video frame sequence refers to the video frames obtained after the video is decoded. It is a sequence generated according to the playback time sequence of the video. In actual applications, the number of videos can be one, two or more segments. In this application, there is no limit on the number of videos. The video frames in the video frame sequence are arranged in chronological order. If the frame rate of the video is 30 frames, one second of video can be decoded into 30 video frames, and 10 seconds of video can be decoded into 300 video frames.

[0037] The purpose of receiving the target to be tracked and the video frame sequence is to identify the target to be tracked in the video frame sequence, and to perform target matching and identification between the target to be tracked and each video frame.

[0038] In a specific embodiment provided in the present application, an example is given in which the target to be tracked is Zhang San and the video frame sequence L has 300 video frames, and the target to be tracked (a photo of Zhang San) and the video frame sequence L are obtained.

[0039] Step 104: sequentially identifying the target to be tracked in each video frame of the video frame sequence, and obtaining the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame.

[0040] The recognition method provided by this application is based on object recognition and tracking. That is, in each video, it is determined whether the target to be tracked is included. If the target to be tracked is identified in the video frame, the video frame position information of the target to be tracked in the video frame is obtained. The video frame position information specifically includes the video frame position coordinates and video frame position time point of the target to be tracked in the video frame. If the target to be tracked is not identified, it is ignored.

[0041] Specifically, the target to be tracked is identified in each video frame of the video frame sequence in sequence, and the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame are obtained, including S1042-S1048:

[0042] S1042: Determine target video frames in sequence in the video frame sequence.

[0043] In the process of identifying the target to be tracked in the video frame sequence, target matching is performed between the target to be tracked and each video frame, and the video frame on which target matching is being performed is the target video frame.

[0044] S1044 , extracting a target feature point set of the target to be tracked, and extracting a target video frame feature point set of the target video frame.

[0045] The target feature point set is a set of feature points of the target to be tracked extracted according to a feature point extraction algorithm, and the target video frame feature point set is a set of feature points of the target video frame extracted according to the feature point extraction algorithm.

[0046] Specifically, feature points can be extracted using the SURF algorithm. Feature points corresponding to the target to be tracked are then combined into a target feature point set, and feature points corresponding to the target video frame are combined into a target video frame feature point set. The SURF algorithm, used for extracting feature points from images, is rotationally and scale-invariant, offering superior performance compared to the SIFT algorithm. It is primarily used in image recognition, dynamic tracking, and other fields.

[0047] S1046: Determine a set matching degree between the target feature point set and the target video frame feature point set.

[0048] The set matching degree is used to express the probability of overlapping feature points between two feature point sets. If the set matching degree of the two sets is higher, it means that more feature points in the target feature point set appear in the target video frame feature point set, which further indicates that the probability of the target to be tracked appearing in the target video frame is greater.

[0049] Specifically, in the process of determining the set matching degree based on the target feature point set and the target video frame feature point set, a first feature point is selected from the target feature point set, and a second feature point is selected from the target video frame feature point set, and the first feature point and the second feature point are matched. In actual applications, each feature point is a vector of fixed dimension. Matching two feature points is specifically reflected in calculating the vector similarity of the two vectors. The specific calculation method can be cosine similarity, Euclidean distance, etc. In this application, the specific method of calculating the vector similarity is not limited. The similarity of the two vectors is used as the matching value of the two feature points. If the matching value is greater than the threshold, it is determined that the first feature point and the second feature point match, and the matching feature point pair is composed of the first feature point and the second feature point. Otherwise, it is considered not to match.

[0050] After matching each feature point in the target feature point set, the successfully matched feature points are grouped into a set of matching feature point pairs. Each matching feature point pair in the matching feature point pair set includes a target feature point and a target video frame feature point. The set matching degree of the target feature point set and the target video frame feature point set is then determined based on the number of matching feature point pairs in the matching feature point pair set and the number of target feature point sets in the target feature point set. For example, if there are 80 matching feature point pairs in the matching feature point pair set and 100 target feature points in the target feature point pair set, the set matching degree is determined to be 0.8; if there are 10 matching feature point pairs in the matching feature point pair set and 130 target feature points in the target feature point pair set, the set matching degree is determined to be 0.07.

[0051] S1048. When the set matching degree is greater than or equal to a preset threshold, obtain the video frame position coordinates of the target to be tracked in the target video frame, and determine the time point corresponding to the target video frame as the video frame position time point.

[0052] When the set matching degree is greater than or equal to a preset threshold, it can be determined that the target to be tracked is identified in the target video frame, the video frame position coordinates of the target to be tracked in the target video frame can be obtained, and the time point of the target video frame is determined as the video position time point.

[0053] Specifically, obtaining the video frame position coordinates of the target to be tracked in the target video frame includes:

[0054] Determine a matching feature point set according to the target feature point set and the target video frame feature point set;

[0055] The coordinates of the center point of the set of matching feature points are determined as the video frame position coordinates of the target to be tracked in the target video frame.

[0056] The video frame position information of the target to be tracked in the target video frame includes the video frame position coordinates and the video frame time point of the target to be tracked in the target video frame. In the above S1046, a matching feature point pair set can be determined based on the target feature point set and the target video frame feature point set. Each matching feature point pair in the matching feature point pair set includes a target feature point and a target video frame feature point corresponding to the target feature point. The set center point is determined based on each target video frame feature point in the matching feature point pair set. The set center point refers to the point with the smallest distance to other points in the set. Usually, the set center point represents the position of the target to be tracked in the target video frame. The set center point information is the set center point coordinates. The coordinates of the set center point are the video frame position coordinates of the target to be tracked in the target video frame. Combined with the time point corresponding to the target video frame, the video frame position information of the target to be tracked in the target video frame can be determined.

[0057] In a specific embodiment provided in the present application, following the above example, Zhang San is identified in turn in each video frame (L1, L2...L300) in the video frame sequence L, and the video frame position coordinates and video position time point of Zhang San in each video frame are obtained as (P1-t1, P2-t2...P300-t300), where P1 is the video frame position coordinates of the first video frame, and t1 is the video position time point of the first video frame.

[0058] Step 106: Obtaining a conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis.

[0059] The preset three-dimensional electronic map is an electronic map obtained using a third-party map generation API. The electronic map is used to display the actual location of the target to be tracked. The three-dimensional electronic map includes longitude, latitude and time axis. Preferably, the vertical axis of the three-dimensional electronic map is set to the time axis, the horizontal axis is set to the longitude, and the vertical axis is set to the latitude.

[0060] Specifically, the conversion rule includes a first conversion rule;

[0061] Obtaining the conversion rules between the video frame position coordinates and the map position point coordinates in the preset three-dimensional electronic map, including:

[0062] Determining whether a first conversion rule between the video frame position coordinates and the two-dimensional map position coordinates in a preset three-dimensional electronic map is stored;

[0063] If yes, obtaining the first conversion rule;

[0064] If not, the first conversion rule is generated according to the video frame sequence and the three-dimensional electronic map.

[0065] In practical applications, the conversion rules include a first conversion rule, wherein the first conversion rule corresponds to the video frame. Different cameras have different shooting angles and placement positions, and the positional relationships in the video frames they capture are also different. For example, there are camera 1 and camera 2. The video frame captured by camera 1 corresponds to the first conversion rule 1, and the chroma video frame captured by camera 2 corresponds to the first conversion rule 2. Obtaining the first conversion rule is to obtain the first conversion rule corresponding to each video frame.

[0066] Specifically, generating the first conversion rule according to the video frame sequence and the three-dimensional electronic map includes:

[0067] determining a first video frame in the sequence of video frames;

[0068] The first conversion rule is generated according to the first video frame and the three-dimensional electronic map.

[0069] The first video frame is a video frame in a video frame sequence including at least two landmark buildings, and a first conversion rule can be generated according to the first video frame and the three-dimensional electronic map.

[0070] Furthermore, generating the first conversion rule according to the first video frame and the three-dimensional electronic map includes:

[0071] Determining at least two video frame markers and position information between each of the video frame markers in the first video frame;

[0072] Determining a corresponding target map marker in the three-dimensional electronic map according to the at least two video frame markers;

[0073] Determine the position information between each of the target map markers according to the latitude and longitude coordinates corresponding to each of the target map markers;

[0074] The conversion rule is determined based on the position information between each of the video frame markers and the position information between each of the target map markers.

[0075] In practical applications, a 3D electronic map is pre-configured with multiple map markers and the corresponding latitude and longitude coordinates for each map marker. Specifically, map markers can be understood as landmark buildings and road signs within the map area that provide positioning capabilities. A set of map marker feature points corresponding to each map marker and the actual latitude and longitude coordinates of each map marker are also stored.

[0076] At least two video frame markers are determined in the first video frame based on the map marker feature point set. The video frame markers are landmark buildings, road signs, and the like with positioning capabilities in the video frame. For example, Building A is a map marker in a three-dimensional electronic map and a video frame marker in the video frame. After determining the at least two video frame markers, the position information between each video frame marker in the video frame can be determined. The position information between each video frame marker in the video frame can be the distance information between the video frame markers.

[0077] After determining the video frame marker, the target map marker corresponding to the video frame marker can be determined in the electronic map, and then the location information between each target map marker can be determined based on the latitude and longitude coordinates corresponding to at least two target map markers. The location information between each target map marker can be the distance information between each target map marker.

[0078] Based on the distance information between the markers in the video frame and the distance information between the markers on the target map, the zoom ratio between the video and the map can be determined. Based on the zoom ratio, a first conversion rule between the position information in the video frame and the map position point information in the preset electronic map can be determined. The specific conversion rule formula is shown in the following formula 1:

[0079] X1=a*X0+b, Y1=c*Y0+d Formula 1

[0080] Where (X0, Y0) is the video frame position coordinate, (X1, Y1) is the map point coordinate, and a, b, c, and d are preset parameters.

[0081] It should be noted that, when the system does not save the conversion rule and cannot determine the conversion rule, the user needs to be prompted to manually input the coordinate mapping relationship, and the corresponding first conversion rule is determined according to the coordinate mapping relationship.

[0082] Step 108: converting each video frame position coordinate into a 3D map position point coordinate in the 3D electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate.

[0083] After obtaining the conversion rules, the video frame position coordinates and the corresponding video frame position time point in each video frame can be converted into three-dimensional map position point coordinates in the three-dimensional electronic map according to the conversion rules. Specifically, taking the three-dimensional map position point coordinates as P(x, y, z) as an example, x is the longitude of the video frame position coordinates, y is the latitude of the video frame position coordinates, and z is the video frame position time point.

[0084] Specifically, the conversion rule includes a first conversion rule and a second conversion rule;

[0085] Converting each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate, and the video frame position time point corresponding to each video frame position coordinate, including:

[0086] Converting each of the video frame position coordinates into corresponding two-dimensional map position coordinates according to the first conversion rule;

[0087] Determine the number of trajectory layers according to each of the video frame position time points;

[0088] Determine the time axis coordinate value corresponding to each video frame position coordinate according to the second conversion rule, the number of trajectory layers, and each video frame position time point;

[0089] The three-dimensional map position point coordinates corresponding to each video frame position coordinate are generated according to the two-dimensional map position coordinates and the time axis coordinate value corresponding to each video frame position coordinate.

[0090] In practical applications, the conversion rules specifically include a first conversion rule and a second conversion rule. The first conversion rule is used to convert the video frame position coordinates into the horizontal and vertical coordinates of the 3D map position point. The second conversion rule is used to determine the time axis coordinates of the 3D map position point based on the video frame position point.

[0091] The position coordinates of each video frame are converted into the horizontal and vertical coordinates of a position point on the three-dimensional map according to a first conversion rule.

[0092] The step of determining the number of trajectory layers according to the position and time point of each video frame includes:

[0093] Determine two consecutive adjacent first video frame position time points and second video frame position time points;

[0094] determining, when a time interval between the second video frame position time point and the first video frame position time point is greater than or equal to a preset time period threshold, that the first video frame position coordinates and the second video frame position coordinates are located in different tracks;

[0095] When the calculation of each video frame position point is completed, the number of trajectory layers is counted.

[0096] In practical applications, the target to be tracked usually passes through the same road section in different time periods. In this application, each time a road section is passed is marked as a trajectory. For example, if the same road section is passed in three time periods, the number of trajectory layers is three. Specifically, a maximum time period threshold TM is first set in the system. If the time interval between the video frame position time points corresponding to two consecutive video frames is greater than or equal to the maximum time period threshold TM, then the two video frames are considered to belong to two time periods. Correspondingly, the video frame position coordinates of the target to be tracked in the two video frames should also be on different trajectories in the three-dimensional map position points in the three-dimensional map.

[0097] The second conversion rule is used to determine the time axis coordinates of the three-dimensional map position point according to the video frame position point, and the second conversion rule specifically includes:

[0098] Determine the target layer trajectory and obtain the starting time point of the target layer trajectory;

[0099] Obtain the previous layer trajectory and the end time point of the previous layer trajectory;

[0100] Determine the time difference between the target layer trajectory and the previous layer trajectory according to the start time point of the target layer trajectory and the end time point of the previous layer trajectory;

[0101] The difference between the target layer track and the previous layer track on the time axis is determined according to the position information of the target track layer in the track layer, the time difference and each video frame position time point.

[0102] After determining the number of trajectory layers, the time axis coordinate value corresponding to the position coordinate of each video frame can be calculated according to the following formula 2:

[0103] z=(X*i / n+A*d)+B*t Formula 2

[0104] Where z represents the time difference between two adjacent layers of tracks, X, A, and B are preset parameters, n represents the number of track layers, i represents the i-th layer track (i.e., the target layer track), d represents the time difference between the end time of the previous track (the previous layer track) and the start time of the i-th layer track (i.e., the target layer track), t represents the video frame position time point corresponding to the video frame position coordinate, X*i / n represents the base height of the i-th layer track, A*d represents the influence of the time difference between the two layers of tracks on the height, and B*t represents the influence of the video frame position time point within the same layer of track on the height. It should be noted that z in the formula is the time difference between two adjacent layers of tracks, and the time axis coordinate value corresponding to each video frame position coordinate is related to the time axis value of the previous track. For example, if the time axis value of the first layer track is 3 and the current video frame position coordinate corresponds to the second layer track, the z corresponding to the current video frame position coordinate is calculated by the above formula 2 as 7, then the time axis coordinate value corresponding to the current video frame position coordinate is 7+3=10.

[0105] The time axis value is related to the time axis value of the previous layer of tracks. By calculating the time axis difference between two adjacent layers of tracks, it is beneficial to compress the distance between two adjacent layers of tracks proportionally when the number of track layers exceeds a threshold during subsequent data processing, thus saving space on the 3D electronic map.

[0106] Step 110: Draw a movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map location point.

[0107] After the coordinates of the three-dimensional map position points are determined, the movement trajectory of the target to be tracked in the three-dimensional electronic map can be drawn according to the coordinates of each three-dimensional map position point.

[0108] Specifically, drawing the movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point includes:

[0109] Marking a corresponding drawing point in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point;

[0110] Each of the drawing points is connected in sequence to generate a movement trajectory of the target to be tracked in the three-dimensional electronic map.

[0111] In actual applications, corresponding drawing points are marked in the three-dimensional electronic map according to the coordinates of each three-dimensional map location point, and then each drawing point is connected in sequence to generate the movement trajectory of the target to be tracked in the three-dimensional electronic map. It should be noted that when connecting the drawing points, only the drawing points on the same layer of the trajectory need to be connected.

[0112] Optionally, the method further includes:

[0113] The moving trajectory is divided into a plurality of trajectory segments according to a preset trajectory segment division rule, wherein the trajectory segments include trajectory segment directions corresponding to the trajectory segments.

[0114] In practical applications, in order to better display the actual motion trajectory of the target to be tracked in the moving trajectory, the moving trajectory may be divided into multiple trajectory segments according to a preset trajectory segment division rule, and each trajectory segment includes a trajectory segment direction corresponding to the trajectory segment.

[0115] A trajectory segment specifically refers to a portion of a moving trajectory, and each trajectory segment is represented by a rectangular diagram with a direction, that is, each trajectory segment includes its corresponding trajectory segment direction.

[0116] To determine whether consecutively entered map points (i.e., plotted points on a trajectory segment) belong to the same trajectory segment, two conditions must be met simultaneously: first, the distance between the first and last points in the consecutive input plots must be less than a preset threshold, D; and second, the angle between all consecutively entered points and the direction of the previous trajectory segment must be less than a preset threshold, M. For example, if five consecutively entered map points, a, b, c, d, and e, are entered, to determine whether these five map points belong to the same trajectory segment, we first determine whether the distance between a and e is less than a threshold, 10. Furthermore, we must determine whether the angle between the line connecting each map point, a, b, c, d, and e, and the last map point, m, in the previous trajectory segment is less than 15°. Specifically, the angle between the line connecting am, bm, cm, dm, and em must be less than 15°. When the distance between a and e is less than a threshold of 10, and the angle between each map location point and the previous trajectory segment is less than 15°, it can be determined that the five consecutive map location points a, b, c, d, and e are the same trajectory segment.

[0117] At the same time, the trajectory segment also specifies the trajectory segment direction. Specifically, for each trajectory segment, the direction vector is determined according to the first and last drawing points in the trajectory segment, and the trajectory segment position of the current trajectory segment is determined according to the first and last drawing points.

[0118] See also Figure 2a and Figure 2b , Figure 2a A schematic diagram of the movement trajectory of a target to be tracked in an electronic map provided by an embodiment of the present application is shown. Figure 2b A three-dimensional schematic diagram of the movement trajectory of a target to be tracked in an electronic map provided by an embodiment of the present application is shown. Figure 2aAs shown in , the target to be tracked starts from point X, moves to point Y via the first track, and then moves to point X via the second track. If only the second track can be displayed in the two-dimensional map, by adjusting the viewing angle of the three-dimensional track map, as shown in Figure 2b As shown, Figure 2b It is a three-dimensional image of an electronic map. Figure 2b In the time axis direction of the electronic map, two actual motion trajectories between point X and point Y in different time periods are displayed. The two motion trajectories are located in different planes along the time axis direction, allowing users to intuitively observe the repeated trajectories of the target to be tracked in different time periods.

[0119] Optionally, the movement trajectory includes at least two layers of sub-movement trajectories;

[0120] The method further comprises:

[0121] The transparency of the current sub-movement track is determined and set according to the time axis coordinates corresponding to each layer of the sub-movement track.

[0122] In practical applications, the target tracking method provided by this application is suitable for scenarios where the same target to be tracked passes through the same road section at different time periods. When the target to be tracked passes through the same road section multiple times, many layers of sub-movement trajectories will be generated. The sub-movement trajectories in the upper layer will block the movement trajectories in the lower layer. At this time, the movement of the sub-movement trajectories in the lower layer cannot be seen intuitively. Based on this, different transparency can be set for each layer of sub-movement trajectories. Specifically, a target point V(X v , Y v , Z v ), the calculation rule of the transparency of the target layer sub-movement trajectory is as follows:

[0123] O=g*Z v *255 Formula 3

[0124] Among them, O represents the transparency of the target layer sub-movement trajectory, g is the preset parameter, and Z v is the time axis coordinate of the target point V.

[0125] The target tracking method provided by the present application receives a target to be tracked and a video frame sequence; identifies the target to be tracked in each video frame of the video frame sequence, obtains the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; obtains a conversion rule between the video frame position coordinates and the map position point coordinates in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis; converts each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; and draws the movement trajectory of the target to be tracked in the three-dimensional electronic map according to each three-dimensional map position point coordinate. The target tracking method provided by the embodiment of the present application uses 3D technology to display the overlapping trajectories of different time periods in 3D space, and uses real-world three-dimensional visual effects to represent the repeated trajectories of multiple times, so that the user can intuitively observe the repeated trajectories of the target to be tracked in different time periods.

[0126] Secondly, different transparency levels are set for each track segment, so that the upper track segments have higher transparency, thus preventing the upper track segments from obscuring the lower track segments and facilitating user observation.

[0127] The following combined Figure 3 , the target tracking method is further described. Figure 3 A processing flow chart of a target tracking method for tracking the whereabouts of Zhang San during surveillance provided by an embodiment of the present application is shown, which specifically includes the following steps:

[0128] Step 302: Receive a target to be tracked and a video frame sequence.

[0129] In a specific implementation provided in the present application, the target to be tracked is Zhang San, and the video frame sequence is 400 video frames obtained after decoding the surveillance video saved by a camera.

[0130] Step 304: sequentially identifying the target to be tracked in each video frame of the video frame sequence, and obtaining the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame.

[0131] In a specific embodiment provided in the present application, following the above example, Zhang San is identified in each video frame in turn, and the video position coordinates of Zhang San in each video frame and the corresponding video frame position time point (Q001-t001, Q002-t002...Q400-t400) are obtained, where Q001 represents the video position coordinates in the first video frame, and t001 represents the time point of the first video frame.

[0132] Step 306: Determine the number of trajectory layers according to each video frame position and time point.

[0133] In a specific embodiment provided by this application, following the above example, the preset maximum time period threshold is set to 5 minutes. After calculation, it is found that the time interval between t190 and t191 is greater than 5 minutes, and the time interval between t277 and t278 is greater than 5 minutes. Therefore, it can be determined that there are three trajectory layers, namely, t001-t190 is the set of time points corresponding to the first trajectory layer, t191-t277 is the set of time points corresponding to the second trajectory layer, and t278-t400 is the set of time points corresponding to the third trajectory layer.

[0134] Step 308: Obtain a first conversion rule and a second conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map.

[0135] In a specific embodiment provided in the present application, following the above example, a preset first conversion rule for converting the video frame position coordinates into the horizontal and vertical coordinates of the map position point in the three-dimensional electronic map, and a second conversion rule for calculating the time axis coordinate value in the coordinates of each map position point are obtained.

[0136] Step 310: Convert each of the video frame position coordinates into corresponding two-dimensional map position coordinates according to the first conversion rule.

[0137] In a specific embodiment provided in the present application, following the above example, the video frame position coordinates (Q001, Q002...Q400) are respectively converted into two-dimensional map point position coordinates (J001, J002...J400) according to the first conversion rule, where J1 is (X001, Y001), J2 is (X002, Y002)...J400 is (X400, Y400).

[0138] Step 312: Determine the time axis coordinate value corresponding to each video frame position coordinate according to the second conversion rule, the number of trajectory layers, and each video frame position time point.

[0139] In a specific embodiment provided in the present application, following the above example, according to the second conversion rule and the number of track layers 3, the time axis coordinate value (Z1, Z2, ..., Z400) of each video frame position coordinate mapped to the three-dimensional electronic map is calculated.

[0140] Step 314: Generate the three-dimensional map position point coordinates corresponding to each video frame position coordinate according to the two-dimensional map position coordinates and the time axis coordinate value corresponding to each video frame position coordinate.

[0141] In a specific embodiment provided in the present application, following the above example, the three-dimensional map position point coordinates (M1, M2...M400) corresponding to each video frame position coordinate are generated according to the two-dimensional map coordinates and time axis coordinate values ​​corresponding to each video frame position coordinate, where M1 is (X1, Y1, Z1), M2 is (X2, Y2, Z2)...M400 is (X400, Y400, Z400).

[0142] Step 316: Mark the corresponding drawing point in the three-dimensional electronic map according to the coordinates of each three-dimensional map location point.

[0143] In a specific embodiment provided in the present application, following the above example, a corresponding drawing point is marked and generated in the three-dimensional electronic map according to the coordinates of each three-dimensional map location point.

[0144] Step 318: sequentially connect the drawing points corresponding to each layer of movement trajectory to generate each layer of movement trajectory of the target to be tracked in the three-dimensional electronic map.

[0145] In a specific embodiment provided in the present application, following the above example, the drawing points corresponding to each layer of movement trajectory are sequentially connected to generate three layers of movement trajectory of the target to be tracked in the three-dimensional electronic map.

[0146] Step 320: Determine and set the transparency of the current layer's movement trajectory according to the time axis coordinates of the first drawing point in each layer's movement trajectory.

[0147] In a specific embodiment provided in the present application, following the above example, corresponding transparency is set for each layer of movement trajectory, so that the user can intuitively observe that Zhang San has passed through the road section multiple times within a period of time.

[0148] The target tracking method provided by the present application receives a target to be tracked and a video frame sequence; identifies the target to be tracked in each video frame of the video frame sequence, obtains the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; obtains a conversion rule between the video frame position coordinates and the map position point coordinates in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis; converts each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; and draws the movement trajectory of the target to be tracked in the three-dimensional electronic map according to each three-dimensional map position point coordinate. The target tracking method provided by the embodiment of the present application uses 3D technology to display the overlapping trajectories of different time periods in 3D space, and uses real-world three-dimensional visual effects to represent the repeated trajectories of multiple times, so that the user can intuitively observe the repeated trajectories of the target to be tracked in different time periods.

[0149] Secondly, different transparency levels are set for each track segment, so that the upper track segments have higher transparency, thus preventing the upper track segments from obscuring the lower track segments and facilitating user observation.

[0150] Corresponding to the above target tracking method embodiment, the present application also provides a target tracking device embodiment, Figure 4 FIG. 1 shows a schematic diagram of the structure of a target tracking device provided by an embodiment of the present application. Figure 4 As shown, the device includes:

[0151] The receiving module 402 is configured to receive a target to be tracked and a video frame sequence;

[0152] an identification module 404 configured to sequentially identify the target to be tracked in each video frame of the video frame sequence, and obtain the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame;

[0153] an acquisition module 406 configured to acquire a conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis;

[0154] The conversion module 408 is configured to convert each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate;

[0155] The drawing module 410 is configured to draw a movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map location point.

[0156] Optionally, the conversion rule includes a first conversion rule and a second conversion rule;

[0157] The conversion module 408 is further configured to:

[0158] Converting each of the video frame position coordinates into corresponding two-dimensional map position coordinates according to the first conversion rule;

[0159] Determine the number of trajectory layers according to each of the video frame position time points;

[0160] Determine the time axis coordinate value corresponding to each video frame position coordinate according to the second conversion rule, the number of trajectory layers, and each video frame position time point;

[0161] The three-dimensional map position point coordinates corresponding to each video frame position coordinate are generated according to the two-dimensional map position coordinates and the time axis coordinate value corresponding to each video frame position coordinate.

[0162] The optional conversion module 408 is further configured to:

[0163] Determine two consecutive adjacent first video frame position time points and second video frame position time points;

[0164] determining, when a time interval between the second video frame position time point and the first video frame position time point is greater than or equal to a preset time period threshold, that the first video frame position coordinates and the second video frame position coordinates are located in different tracks;

[0165] When the calculation of each video frame position point is completed, the number of trajectory layers is counted.

[0166] Optionally, the second conversion rule includes:

[0167] Determine the target layer trajectory and obtain the starting time point of the target layer trajectory;

[0168] Obtain the previous layer trajectory and the end time point of the previous layer trajectory;

[0169] Determine the time difference between the target layer trajectory and the previous layer trajectory according to the start time point of the target layer trajectory and the end time point of the previous layer trajectory;

[0170] The difference between the target layer track and the previous layer track on the time axis is determined according to the position information of the target track layer in the track layer, the time difference and each video frame position time point.

[0171] Optionally, the identification module 404 is further configured to:

[0172] sequentially determining target video frames in the video frame sequence;

[0173] Extracting a target feature point set of the target to be tracked, and extracting a target video frame feature point set of the target video frame;

[0174] Determining a set matching degree between the target feature point set and the target video frame feature point set;

[0175] When the set matching degree is greater than or equal to a preset threshold, the video frame position coordinates of the target to be tracked in the target video frame are obtained, and the time point corresponding to the target video frame is determined as the video frame position time point.

[0176] Optionally, the identification module 404 is further configured to:

[0177] Determine a matching feature point set according to the target feature point set and the target video frame feature point set;

[0178] The coordinates of the center point of the set of matching feature points are determined as the video frame position coordinates of the target to be tracked in the target video frame.

[0179] Optionally, the conversion rule includes a first conversion rule;

[0180] The acquisition module 406 is further configured to:

[0181] Determining whether a first conversion rule between the video frame position coordinates and the two-dimensional map position coordinates in a preset three-dimensional electronic map is stored;

[0182] If yes, obtaining the first conversion rule;

[0183] If not, the first conversion rule is generated according to the video frame sequence and the three-dimensional electronic map.

[0184] Optionally, the acquisition module 406 is further configured to:

[0185] determining a first video frame in the sequence of video frames;

[0186] The first conversion rule is generated according to the first video frame and the three-dimensional electronic map.

[0187] Optionally, the acquisition module 406 is further configured to:

[0188] Determining at least two video frame markers and position information between each of the video frame markers in the first video frame;

[0189] Determining a corresponding target map marker in the three-dimensional electronic map according to the at least two video frame markers;

[0190] Determine the position information between each of the target map markers according to the latitude and longitude coordinates corresponding to each of the target map markers;

[0191] The conversion rule is determined based on the position information between each of the video frame markers and the position information between each of the target map markers.

[0192] Optionally, the drawing module 410 is further configured to:

[0193] Marking a corresponding drawing point in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point;

[0194] Each of the drawing points is connected in sequence to generate a movement trajectory of the target to be tracked in the three-dimensional electronic map.

[0195] Optionally, the device further includes:

[0196] The division module is configured to divide the moving trajectory into a plurality of trajectory segments according to a preset trajectory segment division rule, wherein the trajectory segment includes a trajectory segment direction corresponding to the trajectory segment.

[0197] Optionally, the device further includes:

[0198] The setting module is configured to determine and set the transparency of the current sub-movement track according to the time axis coordinates corresponding to each layer of the sub-movement track.

[0199] The target tracking device provided by the present application receives a target to be tracked and a video frame sequence; identifies the target to be tracked in each video frame of the video frame sequence, obtains the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; obtains a conversion rule between the video frame position coordinates and the map position point coordinates in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis; converts each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; and draws the movement trajectory of the target to be tracked in the three-dimensional electronic map according to each three-dimensional map position point coordinate. The target tracking device provided by the embodiment of the present application uses 3D technology to display the overlapping trajectories of different time periods in 3D space, and uses the real-world three-dimensional visual effect to represent the repeated trajectories of multiple times, so that the user can intuitively observe the repeated trajectories of the target to be tracked in different time periods.

[0200] Secondly, different transparency levels are set for each track segment, so that the upper track segments have higher transparency, thus preventing the upper track segments from obscuring the lower track segments and facilitating user observation.

[0201] The above is a schematic scheme of a target tracking device of this embodiment. It should be noted that the technical solution of the target tracking device and the technical solution of the target tracking method described above are of the same concept. For details not described in detail in the technical solution of the target tracking device, please refer to the description of the technical solution of the target tracking method described above.

[0202] Figure 5 The block diagram shows a structure of a computing device 500 according to an embodiment of the present application. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0203] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)), whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0204] In one embodiment of the present application, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 5 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0205] Computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 500 can also be a mobile or stationary server.

[0206] When the processor 520 executes the computer instructions, the steps of the target tracking method are implemented.

[0207] The above is a schematic solution of a computing device of this embodiment. It should be noted that the technical solution of the computing device and the technical solution of the target tracking method described above are of the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the target tracking method described above.

[0208] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the target tracking method as described above.

[0209] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of the storage medium and the technical solution of the target tracking method described above are based on the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the target tracking method described above.

[0210] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0211] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0212] It should be noted that for the aforementioned method embodiments, for ease of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0213] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0214] The preferred embodiments of the present application disclosed above are intended only to help illustrate the present application. The optional embodiments do not describe all details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of this application. This application selects and describes these embodiments in detail in order to better explain the principles and practical applications of this application, so that those skilled in the art can better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A target tracking method, characterized in that: include: Receive the target to be tracked and the video frame sequence; Identifying the target to be tracked in each video frame of the video frame sequence in sequence, and obtaining the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; Obtaining a conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis; converting each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; Drawing a movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point; Wherein, the conversion rule includes a first conversion rule and a second conversion rule; Converting each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate, and the video frame position time point corresponding to each video frame position coordinate, including: Converting each of the video frame position coordinates into corresponding two-dimensional map position coordinates according to the first conversion rule; Determine the number of trajectory layers according to each of the video frame position time points; Determine the time axis coordinate value corresponding to each video frame position coordinate according to the second conversion rule, the number of trajectory layers, and each video frame position time point; The three-dimensional map position point coordinates corresponding to each video frame position coordinate are generated according to the two-dimensional map position coordinates and the time axis coordinate value corresponding to each video frame position coordinate.

2. The target tracking method according to claim 1, wherein: Determining the number of trajectory layers according to each video frame position time point includes: Determine two consecutive adjacent first video frame position time points and second video frame position time points; determining that the first video frame position coordinate and the second video frame position coordinate are located in different tracks if the time interval between the second video frame position time point and the first video frame position time point is greater than or equal to a preset time period threshold; When the calculation of each video frame position point is completed, the number of trajectory layers is counted.

3. The target tracking method according to claim 1, wherein: The second conversion rule includes: Determine the target layer trajectory and obtain the starting time point of the target layer trajectory; Obtain the previous layer trajectory and the end time point of the previous layer trajectory; Determine the time difference between the target layer trajectory and the previous layer trajectory according to the start time point of the target layer trajectory and the end time point of the previous layer trajectory; The difference between the target layer track and the previous layer track on the time axis is determined according to the position information of the target layer track on the track layer, the time difference and each video frame position time point.

4. The target tracking method according to claim 1, wherein: Identifying the target to be tracked in each video frame of the video frame sequence in sequence, and obtaining the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame, including: Determining target video frames in the video frame sequence in sequence; extracting a target feature point set of the target to be tracked, and extracting a target video frame feature point set of the target video frame; Determining a set matching degree between the target feature point set and the target video frame feature point set; When the set matching degree is greater than or equal to a preset threshold, the video frame position coordinates of the target to be tracked in the target video frame are obtained, and the time point corresponding to the target video frame is determined as the video frame position time point.

5. The target tracking method according to claim 4, wherein: Obtaining the video frame position coordinates of the target to be tracked in the target video frame includes: Determine a matching feature point set according to the target feature point set and the target video frame feature point set; The coordinates of the center point of the set of matching feature points are determined as the video frame position coordinates of the target to be tracked in the target video frame.

6. The target tracking method according to claim 1, wherein: The conversion rules include a first conversion rule; Obtaining the conversion rules between the video frame position coordinates and the map position point coordinates in the preset three-dimensional electronic map, including: Determining whether a first conversion rule between the video frame position coordinates and the two-dimensional map position coordinates in a preset three-dimensional electronic map is stored; If yes, obtaining the first conversion rule; If not, the first conversion rule is generated according to the video frame sequence and the three-dimensional electronic map.

7. The target tracking method according to claim 6, wherein: Generating the first conversion rule according to the video frame sequence and the three-dimensional electronic map includes: determining a first video frame in the sequence of video frames; The first conversion rule is generated according to the first video frame and the three-dimensional electronic map.

8. The target tracking method according to claim 7, wherein: Generating the first conversion rule according to the first video frame and the three-dimensional electronic map includes: Determining at least two video frame markers and position information between each of the video frame markers in the first video frame; Determining a corresponding target map marker in the three-dimensional electronic map according to the at least two video frame markers; Determine the position information between each of the target map markers according to the latitude and longitude coordinates corresponding to each of the target map markers; The conversion rule is determined based on the position information between each of the video frame markers and the position information between each of the target map markers.

9. The target tracking method according to claim 1, wherein: Drawing a movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point in the three-dimensional electronic map includes: Marking a corresponding drawing point in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point; Each of the drawing points is connected in sequence to generate a movement trajectory of the target to be tracked in the three-dimensional electronic map.

10. The target tracking method according to claim 9, wherein: The method further comprises: The moving trajectory is divided into a plurality of trajectory segments according to a preset trajectory segment division rule, wherein the trajectory segments include trajectory segment directions corresponding to the trajectory segments.

11. The target tracking method according to any one of claims 1 to 9, wherein: The movement trajectory includes at least two layers of sub-movement trajectories; and the method further includes: Determine and set the transparency of the current sub-movement track according to the time axis coordinates corresponding to each layer of sub-movement track.

12. A target tracking device, characterized in that: include: A receiving module, configured to receive a target to be tracked and a video frame sequence; an identification module configured to sequentially identify the target to be tracked in each video frame of the video frame sequence, and obtain the video frame position coordinates and the video frame position time point of the target to be tracked in each video frame; an acquisition module configured to acquire a conversion rule between the video frame position coordinates and the coordinates of a map position point in a preset three-dimensional electronic map, wherein the three-dimensional electronic map includes a time axis; a conversion module configured to convert each video frame position coordinate into a three-dimensional map position point coordinate in the three-dimensional electronic map according to the conversion rule, each video frame position coordinate and the video frame position time point corresponding to each video frame position coordinate; a drawing module configured to draw a movement trajectory of the target to be tracked in the three-dimensional electronic map according to the coordinates of each three-dimensional map position point; Wherein, the conversion rule includes a first conversion rule and a second conversion rule; Wherein, the conversion module is further configured to: Converting each of the video frame position coordinates into corresponding two-dimensional map position coordinates according to the first conversion rule; Determine the number of trajectory layers according to each of the video frame position time points; Determine the time axis coordinate value corresponding to each video frame position coordinate according to the second conversion rule, the number of trajectory layers, and each video frame position time point; The three-dimensional map position point coordinates corresponding to each video frame position coordinate are generated according to the two-dimensional map position coordinates and the time axis coordinate value corresponding to each video frame position coordinate.

13. A computing device comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, wherein: When the processor executes the computer instructions, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

15. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images