Object tracking method, apparatus, and system

Abstract

The present application relates to an object tracking method, apparatus, and system. The method comprises: receiving target video frame data sent by an image acquisition device, the target video frame data comprising spatial coordinate information of at least one object; outputting, by means of a display device, target video frames corresponding to the target video frame data, and determining, from each of the video frames on the basis of the spatial coordinate information, a target object to be tracked; determining position information of the target object in the display device; on the basis of the position information, determining an offset of the target object relative to a target position in a canvas of the display device and a scaling ratio for the canvas; and adjusting the target object according to the offset and the scaling ratio, so that the target object is displayed at the target position of the display device. Thus, automatic tracking of an object to be tracked can be realized, thereby improving the tracking efficiency for the object to be tracked, ensuring the smoothness of the image, and improving user experience.

Description

Object tracking method, device and system

[0001] The present application claims priority to the Chinese patent application No. 202410947168.7, filed on July 15, 2024, and entitled "Object tracking method, device and system", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of image processing, in particular to an object tracking method, device and system. BACKGROUND

[0003] In today's intelligent era, various traditional products have entered the digital stage. With the increasing number of tracking scenarios (such as tracking the activities of infants), tracking products are becoming more and more popular.

[0004] In related technologies, in order to facilitate the user to timely understand the situation of the tracked object, the tracking product often includes a camera end and a display device end. The camera end is used to capture the behavior of the tracked object in real time, and the display device end is used to remotely display the situation of the tracked object in real time, so that the user can timely understand the situation of the tracked object.

[0005] However, in actual application, when the user needs to view the detailed situation of the tracked object (such as an infant), it is generally necessary to manually move the canvas of the display device end so that the tracked object is located in the middle of the canvas for observation. However, this manual tracking and viewing method of the tracked object not only has low efficiency, is prone to cause picture lag, but also increases the user's action cost and affects the user experience. SUMMARY

[0006] The present application provides an object tracking method, device and system to improve the tracking efficiency of the tracked object, ensure the smoothness of the picture, and improve the user experience.

[0007] In a first aspect, the present application provides an object tracking method, which comprises:

[0008] receiving target video frame data sent by an image acquisition device, wherein the target video frame data comprises spatial coordinate information of at least one object;

[0009] outputting a target video frame corresponding to the target video frame data through a display device, and determining a target object to be tracked from the target video frame based on the spatial coordinate information;

[0010] determining position information of the target object in the display device;

[0011] determine, based on the position information, an offset of the target object relative to a target position in a canvas of the display device and a zoom scale of the canvas;

[0012] adjust the target object according to the offset and the zoom scale, so that the target object is displayed at the target position of the display device.

[0013] With reference to the first aspect, in a first possible implementation manner of the first aspect, the image acquisition device determines the target video frame data by:

[0014] obtaining a captured image of a preset region;

[0015] determining whether the captured image meets a preset object tracking condition;

[0016] in a case where it is determined that the captured image meets the object tracking condition, determining the captured image as a target video frame, identifying an object included in the target video frame, and determining original spatial coordinate information of each object included in the target video frame;

[0017] multiplying the original spatial coordinate information by a preset scale to obtain spatial coordinate information;

[0018] writing the spatial coordinate information of each object as supplementary enhancement information into image information of the target video frame;

[0019] encoding the target video frame and the image information of the target video frame to obtain target video frame data corresponding to the target video frame.

[0020] With reference to the first aspect, in a second possible implementation manner of the first aspect, the determining whether the captured image meets a preset object tracking condition comprises:

[0021] generating a function signal in response to a received triggering operation of a preset object tracking function button;

[0022] sending the function signal to the image acquisition device, so that the image acquisition device determines that the captured image meets a preset object tracking condition in a case where the function signal is received.

[0023] With reference to the first aspect, in a third possible implementation manner of the first aspect, the target video frame data is encoded data;

[0024] the outputting, by the display device, a target video frame corresponding to the target video frame data and determining a target object to be tracked from the target video frame based on the spatial coordinate information comprises:

[0025] decode the target video frame data to obtain the target video frame;

[0026] acquire spatial coordinate information of each object from the target video frame;

[0027] output the target video frame through the display device, and determine a target object to be tracked from the target video frame based on the spatial coordinate information.

[0028] With reference to the first aspect, in a fourth possible implementation manner of the first aspect, the determining, based on the spatial coordinate information, of the target object to be tracked from the target video frame comprises:

[0029] annotating, based on the spatial coordinate information, a plurality of objects included in the target video frame displayed by the display device in the target video frame;

[0030] in a case where a selection operation for any object displayed by the display device is received, determining the object corresponding to the selection operation as the target object to be tracked;

[0031] in a case where no selection operation for any object displayed by the display device is received, determining an object feature of an object corresponding to each spatial coordinate information, determining whether each object feature is a preset target object feature, and in a case where it is determined that the object feature is the target object feature, determining the object corresponding to the object feature as the target object.

[0032] With reference to the first aspect, in a fifth possible implementation manner of the first aspect, the annotating, based on the spatial coordinate information, of the plurality of objects included in the target video frame displayed by the display device in the target video frame comprises:

[0033] writing the spatial coordinate information into a preset object array, wherein each array element of the object array corresponds to one of the spatial coordinate information;

[0034] in response to a received display operation for an object in the target video frame, traversing the object array;

[0035] for each array element of the traversed object array, converting spatial coordinate information corresponding to the array element into display coordinate; the display coordinate is a coordinate on the display device;

[0036] displaying the display coordinate in a corresponding region of the display device through a preset first display mode.

[0037] With reference to the first aspect, in a sixth possible implementation form of the first aspect, the object array comprises each array element corresponding to an index, and the determining, in a case that a selection operation is received for any object displayed by the display device, the object corresponding to the selection operation as a target object to be tracked comprises:

[0038] In response to a conversion operation for the displayed object in the display device, determining a target index currently recorded; wherein, when traversing the object array, the index corresponding to the traversed array element is recorded;

[0039] Determining a target display coordinate of the array element corresponding to the target index;

[0040] Displaying the target display coordinate in a corresponding target region of the display device by a preset second display mode;

[0041] If a selection operation is received for the target region corresponding to the target display coordinate, determining the object corresponding to the target region as the target object to be tracked.

[0042] With reference to the first aspect, in a seventh possible implementation form of the first aspect, the display screen of the display device is a touch screen;

[0043] The determining, in a case that a selection operation is received for any object displayed by the display device, the object corresponding to the selection operation as a target object to be tracked comprises:

[0044] The determining, in a case that a trigger operation is received for any object of the display screen, the object corresponding to the trigger operation as a target object to be tracked.

[0045] With reference to the first aspect, in an eighth possible implementation form of the first aspect, the determining the position information of the target object in the display device comprises:

[0046] Obtaining a mapping relationship between a space coordinate in a preset region and a coordinate in a captured image from the image acquisition device; wherein, the image acquisition device determines the mapping relationship when capturing the captured image in the preset region;

[0047] According to the space coordinate information of the target object, determining image position information of the target object in the target video frame from the mapping relationship;

[0048] Obtaining a display mapping relationship between the coordinate information of the target video frame and a display screen of the display device;

[0049] Based on the display mapping relationship, determining position information based on the display device corresponding to the image position information.

[0050] With reference to the first aspect, in a ninth possible implementation form of the first aspect, the determining, based on the position information, of the offset of the target object in the canvas of the display device relative to the target position and the zoom scale of the canvas comprises:

[0051] obtaining a canvas size of the display device and a target size of the target position;

[0052] determining, according to the position information and the canvas size, the offset of the target object in the canvas of the display device relative to the target position;

[0053] determining, according to the position information and the target size, the zoom scale of the canvas.

[0054] With reference to the first aspect, in a tenth possible implementation form of the first aspect, the determining, according to the position information and the canvas size, of the offset of the target object in the canvas of the display device relative to the target position comprises:

[0055] establishing a coordinate system of the canvas;

[0056] determining, according to the position information, a first coordinate of a center position of the target object in the canvas in the coordinate system;

[0057] determining, according to the canvas size, a second coordinate of a center point of the target position in the canvas in the coordinate system;

[0058] determining, according to the first coordinate and the second coordinate, a horizontal offset and a vertical offset of the target object in the canvas relative to the target position;

[0059] determining the horizontal offset and the vertical offset as the offset of the target object in the canvas relative to the target position.

[0060] With reference to the first aspect, in an eleventh possible implementation form of the first aspect, the position information is position information of a preset region containing the target object, and the determining, according to the position information and the target size, of the zoom scale of the canvas comprises:

[0061] determining, according to the position information, a first width value and a first height value corresponding to the preset region containing the target object;

[0062] determining, according to the target size, a second width value and a second height value of the target position;

[0063] determine a first ratio of the second width value and the first width value, and a second ratio of the second height value and the first height value;

[0064] determine a minimum ratio value from the first ratio and the second ratio;

[0065] determine the minimum ratio value as a zoom ratio of the canvas in a case where the minimum ratio value is less than a preset ratio threshold.

[0066] With reference to the first aspect, in a twelfth possible implementation manner of the first aspect, the adjusting the target object according to the offset and the zoom ratio comprises:

[0067] moving the target object according to the offset;

[0068] scaling the canvas of the display device according to the zoom ratio.

[0069] With reference to the first aspect, in a thirteenth possible implementation manner of the first aspect, when the target video frame data sent by the image acquisition device is first received, a timer is started, and after the target video frame corresponding to the target video frame data is output by the display device, the method further comprises:

[0070] determining whether a count value currently recorded by the timer is greater than a preset count threshold;

[0071] in a case where it is determined that the count value is greater than the count threshold, performing the step of determining the target object to be tracked from the target video frame based on the spatial coordinate information, and when the target object is adjusted, adjusting the target object through a preset animation, and after the target object is adjusted, updating the timer to a preset value;

[0072] in a case where it is determined that the count value is less than or equal to the count threshold, discarding the spatial coordinate information of the plurality of objects included in the target video frame data.

[0073] A second aspect, the present application provides an object tracking device, the device comprises:

[0074] a receiving module configured to receive target video frame data sent by an image acquisition device, the target video frame data including spatial coordinate information of at least one object;

[0075] a display module configured to output a target video frame corresponding to the target video frame data through a display device, and determine a target object to be tracked from the target video frame based on the spatial coordinate information;

[0076] A first determining module is configured to determine position information of the target object in the display device.

[0077] A second determining module is configured to determine, based on the position information, an offset of the target object relative to a target position in a canvas of the display device and a zoom scale of the canvas.

[0078] An adjusting module is configured to adjust the target object according to the offset and the zoom scale, so that the target object is displayed at the target position of the display device.

[0079] In a third aspect, the present application provides an object tracking system, which comprises an image acquisition device, a client, and a display device.

[0080] The image acquisition device is configured to acquire a target video frame of a preset area, identify spatial coordinate information of each object included in the target video frame, encode the spatial coordinate information into target video frame data, and send the target video frame data to the client.

[0081] The display device is configured to display the target video frame sent by the image acquisition device.

[0082] The client comprises a processor and a memory, and the processor is configured to execute an object tracking program stored in the memory to implement the object tracking method of any one of the first aspect.

[0083] The technical scheme provided in the embodiments of the present application comprises the following steps: receiving target video frame data sent by an image acquisition device, wherein the target video frame data comprises spatial coordinate information of at least one object; outputting a target video frame corresponding to the video frame data by a display device; determining a target object to be tracked from the target video frame based on the spatial coordinate information; determining position information of the target object in the display device; determining an offset of the target object relative to a target position in a canvas of the display device and a zooming scale of the canvas based on the position information; and adjusting the target object according to the offset and the zooming scale, so that the target object is displayed at the target position of the display device. This technical scheme can collect spatial coordinate information of each object in a shooting area by an image acquisition device, and send the spatial coordinate information to a client. The client can determine a target object to be tracked in a target video frame sent by the image acquisition device according to spatial coordinate information of objects included in the target video frame, and determine position information of the target object in a display device, so as to adjust and enlarge the target object to display the target object at a target position of the display device. This can display a target object to be tracked in real time at a target position according to a preset scale of a display interface when the image acquisition device shoots multiple objects, so that the target object can be displayed completely and clearly, automatic tracking of the target object is realized, tracking efficiency of the target object is improved, the smoothness of a picture is ensured, and user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0084] In order to more clearly illustrate the technical scheme of the present application, the drawings required in the embodiments will be briefly introduced. Obviously, other drawings can also be obtained by those skilled in the art without any creative effort.

[0085] FIG. 1 is a structural schematic diagram of an object tracking system according to an embodiment of the present application;

[0086] FIG. 2 is an embodiment flowchart of an object tracking method according to an embodiment of the present application;

[0087] FIG. 3 is an embodiment flowchart of another object tracking method according to an embodiment of the present application;

[0088] FIG. 4 is an embodiment flowchart of another object tracking method according to an embodiment of the present application;

[0089] FIG. 5 is a schematic diagram of an object labeling method according to an embodiment of the present application;

[0090] FIG. 6 is a schematic diagram of another object labeling method according to an embodiment of the present application;

[0091] FIG. 7 is an embodiment block diagram of an object tracking device according to an embodiment of the present application;

[0092] FIG. 8 is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0093] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0094] The following disclosure provides many different embodiments, or examples, for implementing different structures of the present application. For the purpose of simplicity, the components and arrangements of the examples that are described herein are shown in the following description. These are, of course, merely examples and are not intended to limit the application in any way. Furthermore, the application can be used in any number of environments and applications without departing from the spirit of the present application. Additionally, the present application can be implemented in different embodiments and / or examples and that the disclosure is not limited to the specific examples described herein. The following description is, therefore, not to be taken in a limited sense, as the present application is broadly contemplated to be implemented in other embodiments.

[0095] In order to solve the technical problem that the prior art tracking and viewing method for a tracked object is not only inefficient, but also causes picture lag and increases user action cost and affects user experience, the present application provides an object tracking method, device and system, which can collect spatial coordinate information of each object in a shooting area by an image collection device, and send the spatial coordinate information to a client. The client can determine a target object to be tracked in a target video frame sent by the image collection device according to the spatial coordinate information of the object included in the target video frame, and determine position information of the target object on a display device, so as to display the target object at a target position of the display device after being adjusted and enlarged. Thus, when the image collection device shoots multiple objects, the display device can display the target object to be tracked in real time at the target position according to a preset proportion of the display interface, so that the target object can be displayed completely and clearly, automatic tracking of the tracked object is realized, tracking efficiency of the tracked object is improved, picture smoothness is ensured, and user experience is improved.

[0096] In order to facilitate understanding of the object tracking method provided by the present application, the object tracking system provided by the present application will be described first as follows:

[0097] Referring to FIG. 1, FIG. 1 is a structural schematic diagram of an object tracking system provided in an embodiment of the present application. As shown in FIG. 1, the object tracking system 10 can include an image collection device 11, a client 12, and a display device 13.

[0098] The image acquisition device 11 is configured to acquire images of a preset area. The image acquisition device 11 can be a camera or a video camera, and the embodiments of the present application do not limit the image acquisition device 11.

[0099] The client 12 can be a hardware device or software that supports network connection and provides various network services. When the client 12 is hardware, the client 12 can be various electronic devices with a display screen, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like. In FIG. 1, a desktop computer is taken as an example. When the client 12 is software, the software can be installed in the above-mentioned electronic devices.

[0100] The display device 13 is configured to display images acquired by the image acquisition device 11. The display device 13 can be connected to the client 12, and when the client 12 receives images acquired by the image acquisition device 11, the client 12 can send the images to the display device 13 for display. Therefore, the display device 13 can be a separate display device, such as a projector, or a display module installed in the client 12, such as a display screen of the client 12. In FIG. 1, the display device is taken as the display screen of the client 12.

[0101] In actual applications, the image acquisition device 11 can be installed in a preset area (for example, a living room) and acquire images of the preset area in real time, and send the acquired images to the client 12. After receiving the images sent by the image acquisition device 11, the client 12 can display the images through the connected display device 13. Based on the application of the object tracking system 10, a user can monitor the preset area in real time, for example, the user can view images of the preset area sent by the image acquisition device 11 through a client 12 located in another area.

[0102] Therefore, a user can use the object tracking system to take care of an object (for example, a baby) in a preset area and observe activities of the object in real time.

[0103] For example, in the object tracking system 10 shown in FIG. 1, the preset area can include an object 14. After the image acquisition device 11 acquires images of the object 14, the corresponding video frames can be displayed on the display device 13. A user can view the object 14 on the display screen of the display device, and the object 15 displayed on the display device 13 is a photographed image of the object 14.

[0104] In this scenario, there is a user demand: in the process of monitoring the object in the preset area, when the object in the preset area moves, it may move to the boundary of the shooting range of the image acquisition device 11 or a region far from the center, which makes the object in the image acquisition device 11 display position more remote or blurred, so that the user cannot clearly observe and understand the object when viewing the image through the display device 13.

[0105] At present, the user generally manually moves the screen of the display device 13 to make the object located at the center of the screen, so as to facilitate tracking and viewing the object, however, this way of tracking and viewing the tracked object not only has low efficiency and is easy to cause picture lag, but also increases the user action cost and affects the user experience.

[0106] To this end, the client 12 can track the object in the video frame displayed by the display device 13 according to the preset proportion of the display interface at the target position of the display device 13 by executing the object tracking method provided in the present application, so as to realize automatic tracking of the tracked object, improve the tracking efficiency of the tracked object, ensure the smoothness of the picture, and improve the user experience.

[0107] The object tracking method provided in the present application will be further explained and described in detail in combination with the drawings and specific embodiments, and the embodiments do not constitute a limitation on the embodiments of the present application.

[0108] Referring to FIG. 2, it is an embodiment flowchart of an object tracking method provided in the present application. As shown in FIG. 2, the flowchart can include the following steps:

[0109] Step 201, receiving target video frame data sent by an image acquisition device, wherein the target video frame data includes spatial coordinate information of at least one object.

[0110] The image acquisition device is a device for acquiring images in a preset area, for example, the image acquisition device 11 shown in FIG. 1. The image acquisition device can be a camera or other acquisition device, and the present application does not limit this.

[0111] The target video frame data refers to image data acquired by the image acquisition device, which can be data corresponding to a target video frame, such as image size, pixel format, color space, etc. of the target video frame, wherein the target video frame data further includes spatial coordinate information of at least one object in the target video frame. The spatial coordinate information can be 2D or 3D coordinate information, and the present application does not limit this.

[0112] The target video frame is a frame of video image collected by the image collection device, and it is further determined that the video frame image collected by the image collection device satisfies the preset object tracking condition, that is, if the video frame image collected by the image collection device satisfies the object tracking condition, the frame of video image is determined as the target video frame, and the spatial coordinate information of each object in the target video frame is obtained.

[0113] The spatial coordinate information refers to the actual spatial coordinate of the object included in the target video frame in the actual space. The actual spatial coordinate can be 2D or 3D coordinate information, which is not limited in the embodiments of the present application. The actual space is a preset region photographed by the image collection device. Further, in order to facilitate subsequent application of the spatial coordinate information of the object, the spatial coordinate information can also be a thousandth of the original spatial coordinate information. The original spatial coordinate information is the actual spatial coordinate information in the actual space.

[0114] In the embodiments of the present application, the execution subject of the embodiments of the present application can be a client, for example, the client 12 in the object tracking system 10 shown in FIG. 1. Based on this, when the image collection device determines that the object in the current photographed region needs to be tracked, the photographed image of the current collected preset region can be obtained. The photographed image can be a frame of video image currently collected by the image collection device, and the preset region refers to the current photographed region corresponding to the image collection device.

[0115] Then, it can be determined whether the photographed image satisfies the preset object tracking condition. The object tracking condition can represent that when the target object in the photographed image is tracked, if the position and scaling ratio of the target object are adjusted, the frequency of adjustment will not be too fast to cause unclear picture shaking. For example, the object tracking condition is that the number of video frames between adjacent two target video frames is at least N, and N is a preset positive integer, for example, 5 frames or 10 frames, which is not limited in the embodiments of the present application. For another example, the object tracking condition can be that the time length between adjacent two target video frames is a preset value, and the preset value is 50 ms, which can also be 80 ms, which is not limited in the embodiments of the present application.

[0116] Optionally, in the case where it is determined that the photographed image satisfies the object tracking condition, it is indicated that the object in the target video frame can be tracked, and therefore the photographed image can be determined as the target video frame. Then, the object included in the target video frame can be identified to determine the original spatial coordinate information of each object included in the target video frame. In the embodiments of the present application, the execution subject can identify the position of each object included in the target video frame through a preset artificial intelligence algorithm, so as to obtain the original spatial coordinate information of each object.

[0117] As an example embodiment, a preset application can be installed in the client, and the client interacts with the image capture device through the application. Therefore, when a user wants to track an object in the area photographed by the image capture device, the client can display an interface of the application on the display device, and the interface can have a preset object tracking function button.

[0118] Based on this, the user can click the button, and the client can generate a corresponding function signal after detecting the triggering operation on the button, and send the function signal to the image capture device, so that the image capture device determines to track the object in the current photographed area, that is, determines the target video frame and the original spatial coordinate information of each object included in the target video frame.

[0119] After the image capture device identifies the original spatial coordinate information of each object included in the photographed image, the image capture device can multiply the original spatial coordinate information by a preset proportion to obtain the spatial coordinate information of each object. The preset proportion can be a thousandth or a percentage, and the embodiments of the present application do not limit this.

[0120] Then, the spatial coordinate information of each object can be written into the image information of the target video frame as SEI (Supplemental Enhancement Information) information.

[0121] In the H.264 and H.265 video coding standards, SEI is a mechanism for providing additional video information, which is usually unrelated to the video content itself, but is very useful for video decoding and processing. SEI information can include many contents, such as scene changes of video, timestamps, color parameters, camera parameters, etc. Generally, SEI information is embedded in a special way in the video stream, which can provide additional context information in the decoding process, and help to improve the quality of the video, the performance of the decoder and the experience of the application.

[0122] Based on this, the image capture device can encode the spatial coordinate information of the object included in each frame of image as SEI information, and encode the SEI information into the header information of the video frame.

[0123] Finally, the target video frame and the image information of the target video frame can be encoded to obtain target video frame data.

[0124] According to the above process, the image capture device can send the target video frame data to the client after obtaining the target video frame data.

[0125] Based on this, the client can receive the target video frame data sent by the image capture device.

[0126] As an optional implementation, the client can display the received target video frame through an installed application, and the client has a preset parsing module for parsing the spatial coordinate information in the parsed video frame data. Based on this, after receiving the target video frame data, the client can parse the target video frame data through the parsing module and obtain the spatial coordinate information included in the target video frame data. Then, the above-mentioned parsing module can send the parsed spatial coordinate information to the application in a notification manner, so that the application determines the target object to be tracked in the target video frame.

[0127] Step 202, output the target video frame corresponding to the target video frame data through the display device, and determine the target object to be tracked in the target video frame based on the spatial coordinate information.

[0128] The display device is a device with a display screen connected to the client, which can be a display screen installed on the client, or a separate display device connected to the client, such as a projector.

[0129] In the embodiment of the application, after the client receives the target video frame data sent by the image acquisition device, since the target video frame data is encoded data, the client can decode the target video frame data to obtain the target video frame, and obtain the spatial coordinate information of each object included in the target video frame, and output the target video frame corresponding to the target video frame data through the display device.

[0130] Further, when the client outputs the target video frame through the display device, the client can determine the target object to be tracked in the target video frame based on the obtained spatial coordinate information of each object.

[0131] As to how to determine the target object to be tracked in the target video frame based on the spatial coordinate information of each object, it will be described below through the flowchart shown in FIG. 3, which will not be described in detail here.

[0132] Step 203, determine the position information of the target object in the display device.

[0133] Step 204, based on the position information, determine the offset of the target object relative to the target position in the canvas of the display device and the scaling ratio of the above-mentioned canvas.

[0134] Step 205, adjust the target object according to the above-mentioned offset and the above-mentioned scaling ratio, so that the target object is displayed at the target position of the display device.

[0135] The steps 203 to 205 are described as follows:

[0136] The position information refers to position information corresponding to a basic coordinate system of a display screen or a canvas of the display device, in other words, position information of the target object relative to the display device.

[0137] The target position refers to a position of the display screen on the display device, which can be a preset region of the display screen, for example, a region centered on the center of the display screen, or a point on the display screen, for example, the center point of the display screen. It can be understood that when the target position is the center point, the target object can be displayed at the target position, and the target region can be dynamically determined with the target position as the center, so that the target object is displayed in the target region.

[0138] In an embodiment of the present application, the client can determine the position information of the target object in the display device based on the target video frame received from the image acquisition device, and determine the offset of the target object relative to the target position in the canvas of the display device and the scaling ratio of the canvas based on the position information, so that the position of the target object can be adjusted according to the offset and the scaling ratio, so that the target object is displayed at the target position of the display device. The target position can be the center region of the display screen of the display device. According to the above method, the target object to be tracked in each video frame can be adjusted to the center region of the display screen and displayed according to the preset ratio of the display interface, so as to realize automatic tracking of the target object.

[0139] In an embodiment, the position information of the target object in the display device can be determined based on the spatial coordinate information of the target object.

[0140] As an optional implementation, the image acquisition device can determine the mapping relationship between the spatial coordinates in the preset region and the coordinates in the captured image when capturing the captured image in the preset region. Based on this, the client can obtain the mapping relationship, and after determining the spatial coordinate information of the target object, the image position information of the target object in the frame target video frame can be determined from the mapping relationship based on the spatial coordinate information.

[0141] Further, the client also has a display mapping relationship between the coordinate information of the received target video frame and the display screen in the display device when displaying the target video frame in the display device. Based on the display mapping relationship, the client can determine the position information corresponding to the image position information based on the display device.

[0142] In an embodiment, the adjustment of the target object by the client based on the position information can include movement and scaling adjustment.

[0143] In one scenario, the position information of the target object on the display device can indicate that the target object is located at the edge of the canvas of the display device, which can be covered by the display screen when displayed. Based on this, the client can move the position of the target object to the center of the display screen, so that the display device can display the target object completely.

[0144] In another scenario, the position information of the target object on the display device can indicate that the target object is located in a small area in the center of the canvas of the display device, for example, occupying one tenth of the entire display screen. Based on this, the client can enlarge the position of the target object to a preset percentage of the display screen, for example, enlarging the area occupied by the target object to three fourths of the entire display screen.

[0145] In yet another scenario, the position information of the target object on the display device can indicate that the target object is located in an edge area in the canvas of the display device, and the area occupied by the target object occupies one tenth of the display screen. Based on this, in order to prevent the display screen from covering the target object when the target object is enlarged, the client can move the target object to the center of the display screen before enlarging the target object.

[0146] As to how the client determines the offset of the target object relative to the target position and the scaling ratio of the canvas based on the position information of the target object in the above scenarios, and how to move and / or scale the target object according to the offset and the scaling ratio, etc., so that the target object is displayed at the target position of the display device, which can be described below by the flow shown in FIG. 4, which will not be described in detail here.

[0147] In addition, in order to prevent the adjustment of the target object for each video frame, resulting in a high frequency of adjusting the target object, causing stuttering and wasting resources, the client can set a timer or a counter to adjust the target object every interval of a preset time period or a preset number of video frames.

[0148] As an optional implementation, the client can start the timer when it first receives the target video frame data sent by the image capture device, and after outputting the target video frame through the display device, it can determine whether the count value recorded by the timer at present is greater than a preset count threshold.

[0149] Optionally, in the case where the count value is greater than the above-mentioned count threshold, the above-mentioned step of determining the target object to be tracked from the target video frame based on the spatial coordinate information can be continued, and when adjusting the above-mentioned target object, the target object is adjusted through a preset animation. The above-mentioned animation is a pre-set animation effect, for example, moving the target object from the current position directly to the target position, or slowly moving the target position to the target position.

[0150] After the target object is adjusted, the timer can be updated to a preset value, for example, the timer is reset to zero to restart the timing.

[0151] On the contrary, if it is determined that the count value is less than or equal to the count threshold, the spatial coordinate information of the plurality of objects included in the target video frame data can be directly discarded, that is, the object tracking method provided in the embodiments of the present application is not performed on the target video frame.

[0152] Further, it can be determined in real time whether the count value is greater than the count threshold, and when the count value is greater than the count threshold and the target video frame is not received, a prompt information can be output to prompt that the target object cannot be tracked in time.

[0153] As another optional implementation, the client can start a counter when the target video frame data sent by the image acquisition device is first received. The counter can be used to count the number of target video frames. Based on this, after the target video frame is output through the display device, it can be determined whether the count value currently recorded by the counter is greater than a preset count threshold.

[0154] Optionally, if it is determined that the count value is greater than the count threshold, the step of determining the target object to be tracked from each video frame based on the spatial coordinate information can be continued, and when the target object is adjusted, the target object is adjusted through a preset animation. The animation is a pre-set animation effect, for example, the target object is directly jumped from the current position to the target position, or the target position is slowly moved to the target position.

[0155] After the target object is adjusted, the counter can be updated to a preset value, for example, the counter is reset to zero to restart the counting.

[0156] On the contrary, if it is determined that the count value is less than or equal to the count threshold, the spatial coordinate information of the plurality of objects included in the target video frame data can be directly discarded, that is, the object tracking method provided in the embodiments of the present application is not performed on the target video frame.

[0157] Further, it can be determined in real time whether the count value is greater than the count threshold, and when the count value is greater than the count threshold and the target video frame is not received, a prompt information can be output to prompt that the target object cannot be tracked in time.

[0158] The technical scheme provided in the embodiments of the present application comprises the following steps: receiving target video frame data sent by an image acquisition device, wherein the target video frame data comprises spatial coordinate information of at least one object; outputting a target video frame corresponding to the video frame data by a display device; determining a target object to be tracked from the target video frame based on the spatial coordinate information; determining position information of the target object in the display device; determining an offset of the target object relative to a target position in a canvas of the display device and a zooming scale of the canvas based on the position information; and adjusting the target object according to the offset and the zooming scale, so that the target object is displayed at the target position of the display device. This technical scheme can collect spatial coordinate information of each object in a shooting area by the image acquisition device, and send the spatial coordinate information to a client. The client can determine a target object to be tracked in a target video frame sent by the image acquisition device according to the spatial coordinate information of the object included in the target video frame, and determine position information of the target object in the display device, so as to adjust and enlarge the target object to be displayed at the target position of the display device. Therefore, when the image acquisition device shoots multiple objects, the display device can display the target object to be tracked in real time at the target position according to a preset scale of a display interface, so that the target object can be displayed completely and clearly, the automatic tracking of the target object is realized, the tracking efficiency of the target object is improved, the smoothness of the picture is ensured, and the user experience is improved.

[0159] Referring to FIG. 3, an embodiment flowchart of another object tracking method provided in the embodiments of the present application is shown. The flowchart shown in FIG. 3 describes how to determine a target object to be tracked from a target video frame according to spatial coordinate information of each object in the target video frame, based on the flowchart shown in FIG. 2. As shown in FIG. 3, the flowchart can comprise the following steps:

[0160] In step 301, based on the spatial coordinate information, multiple objects included in a target video frame displayed by a display device are labeled in the target video frame.

[0161] The spatial coordinate information refers to spatial coordinates of each object in a preset area shot by an image acquisition device in the target video frame data. Further, the spatial coordinate information can be actual spatial coordinates or percentage spatial coordinates of the actual spatial coordinates, and the embodiments of the present application do not limit this.

[0162] In the embodiments of the present application, after receiving the target video frame data sent by the image acquisition device, the client can obtain the spatial coordinate information of each object included in the target video frame from the target video frame data.

[0163] Afterwards, the position of each object in the display canvas of the display device when the display device displays the target video frame can be determined according to the spatial coordinate information of each object, and each object corresponding to each position can be marked.

[0164] As an exemplary embodiment, the marking of each object can be to enclose each object by a preset display frame, for example, as shown in FIG. 5. Referring to FIG. 5, it is a schematic diagram of an object marking method provided by an embodiment of the present application. As shown in FIG. 5, each object can be enclosed by a rectangular frame.

[0165] As another exemplary embodiment, the marking of each object can be to highlight each object and to blur the background, for example, as shown in FIG. 6. Referring to FIG. 6, it is another schematic diagram of an object marking method provided by an embodiment of the present application. As shown in FIG. 6, the background where the object is located can be blurred, and each object can be highlighted.

[0166] As an optional implementation, when marking the plurality of objects included in the target video frame based on the spatial coordinate information, the spatial coordinate information of each object included in the target video frame can be written into a preset object array. Each array element of the object array corresponds to a spatial coordinate information.

[0167] Based on this, the display interface of the display device can include a preset display button, which is used to control the display of each object included in the current target video frame. The user can control the display device to mark each object included in the currently displayed target video frame by clicking the display button.

[0168] Based on the above display interface, after detecting the triggering operation of the user on the display button, the control end can traverse the object array in response to the received display operation on the object in the target video frame.

[0169] After traversing the object array, the spatial coordinate information corresponding to each array element of the traversed object array can be converted into display coordinates. The display coordinates are coordinates in the display canvas of the display device.

[0170] Based on this, when the client determines the display coordinates of each object, the position of the object in the display device can be determined, and therefore the display coordinates in the corresponding region of the display device can be displayed by a preset first display mode. The corresponding region is the region where the object is displayed, which can be a rectangular frame containing the object, or a rectangular frame containing part of the region of the object, for example, a rectangular frame containing the face of the object.

[0171] Step 302, in the case that a selection operation is received for any object displayed by the display device, the object corresponding to the selection operation is determined as the target object to be tracked.

[0172] Step 303, in the case that no selection operation is received for any object displayed by the display device, the object feature of the object corresponding to each spatial coordinate information is determined.

[0173] Step 304, it is determined whether each object feature is a preset target object feature.

[0174] Step 305, in the case that the object feature is determined as the target object feature, the object corresponding to the object feature is determined as the target object.

[0175] The following describes steps 302 to 305:

[0176] The above selection operation refers to a selection operation performed by the user on the object in the video frame currently displayed through the display interface of the display device.

[0177] In an embodiment, when the client labels each object in the video frame, the target object is defaulted as any object in the video frame (for example, the object located at the front, or the target object determined in the historical video frame), and the target object is displayed through a preset second display mode. The second display mode can be updating the rectangular frame containing the target object to a preset color (for example, red), or highlighting or enlarging the display of the target object, and the embodiment of the present application does not limit this.

[0178] Based on this, the client can detect whether a selection operation is received for any object displayed by the display device within a preset time period.

[0179] Optionally, in the case that a selection operation is received for any object displayed by the display device, the object corresponding to the selection operation is determined as the target object to be tracked.

[0180] As an optional implementation, each array element in the object array can correspond to an index, and the client can display the target object in the display device according to the index of each array element. Based on this, when the client labels each object in the video frame, a preset index (for example, index 1) is recorded as the target index, and the object corresponding to the target index is determined as the target object.

[0181] As an example embodiment, there can be transition buttons in the display interface, such as a "previous" button and a "next" button, for the objects in the video frame, and the user selects a target object in the display interface by clicking the transition button. When the user clicks the "previous" button, the client can determine the object corresponding to the previous index of the target index as the target object and display it on the display device in the second display mode; when the user clicks the "next" button, the client can determine the object corresponding to the next index of the target index as the target object and display it on the display device in the second display mode.

[0182] Based on this, when the client detects the triggering operation of the user on the transition button in the display device, it can determine the target index of the current record in response to the transition operation on the object displayed on the display device. When traversing the object array, the index corresponding to the traversed array element is recorded.

[0183] Then, the target display coordinates of the data element corresponding to the target index can be determined. The target display coordinates refer to the coordinates of the object in the canvas of the display device.

[0184] After that, the target display coordinates can be displayed on the corresponding target region of the display device in the preset second display mode. The target region is the region where the object corresponding to the target display coordinates is located. This region is used to identify the object so that the user can determine the object through this region.

[0185] Finally, when the selected target object is displayed in the second display mode, if a selection operation on the target region corresponding to the target display coordinates is received, the object corresponding to the target region can be determined as the target object to be tracked. The selection operation can be the triggering operation of the user on the determination button in the display interface, and the determination button is used to indicate that the currently displayed target object is determined as the target object to be tracked.

[0186] As another optional implementation, when the client labels each object in the target video frame currently displayed on the display device, the user can directly trigger any labeled object, and the client can determine the object triggered by the user as the target object to be tracked.

[0187] As an example embodiment, the user can perform a triggering operation on the object displayed on the display device through a mouse.

[0188] As another example embodiment, the display screen of the display device can be a touch screen, and the user can directly click any displayed object to determine the target object to be tracked. Based on this, the client can determine the object corresponding to the triggering operation as the target object to be tracked when it receives the triggering operation on any object displayed on the display device.

[0189] On the contrary, in the case that no selection operation for any object displayed by the display device is received, the object feature of the object corresponding to each spatial coordinate information is determined, and whether each object feature is the preset target object feature is determined. If it is determined that an object feature is the target object feature, the object corresponding to the object feature is determined as the target object; if the determined object feature is not the target object feature, the object corresponding to the object feature is determined as a non-target object. The preset target object feature can be an object feature of an object set in advance, or an object feature of a target object determined from a previous target video frame.

[0190] In the case that the target object is tracked, the target object in a period of time is tracked, that is, the target objects in the plurality of target video frames are the same object. Therefore, in order to improve the efficiency of tracking the target object, the target object can be recorded after the user selects the target object, so that the user does not need to select the target object in subsequent target video frames.

[0191] As an exemplary embodiment, the client can record the object feature of the target object as the target object feature after determining the target object of the target video frame according to the user operation.

[0192] Based on this, when the client receives the target video frame sent by the image acquisition device again, if no selection operation of the user for any object in the target video frame is received, the object feature of each object in the currently received target video frame is determined.

[0193] Then, the object feature consistent with the recorded target object feature is determined from the plurality of object features, and the object corresponding to the spatial coordinate information of the object feature is determined as the target object.

[0194] The technical scheme provided by the embodiment of the application can determine the target object to be tracked in each video frame according to the selection operation of the user on any object displayed by the display device or the historical recorded object feature, and efficiently and accurately determine the target object of each video frame.

[0195] Referring to FIG. 4, an embodiment flowchart of another object tracking method provided by the present application is shown. The flowchart shown in FIG. 4 is based on the flowchart shown in FIG. 2, and describes how to determine the offset of the target object relative to the target position in the canvas of the display device and the scaling ratio of the canvas based on the position information of the target object, and how to adjust the target object according to the offset and the scaling ratio. As shown in FIG. 4, the flowchart can include the following steps:

[0196] Step 401: Obtain the canvas size of the display device and the target size of the target position.

[0197] The canvas size is the size of the display area of the display device for displaying the video frame, and the canvas size can include the canvas length and the canvas width.

[0198] The target size refers to the size of the target position of the display device for displaying the target object, and the target position can be a preset area for displaying the target object, or a dynamically determined area for displaying the target object, which is not limited in the embodiments of the present application.

[0199] In an embodiment, the client can directly obtain the device information, and parse the canvas size of the client from the device information.

[0200] In an embodiment, the user can preset the size of the target position, and based on this, the client can directly obtain the target size of the target position set by the user.

[0201] In another embodiment, the target size of the target position can be a default value, which is the minimum size value when the display device can completely and clearly display the object.

[0202] Step 402: Determine the offset of the target object relative to the target position in the canvas of the display device according to the position information and the canvas size.

[0203] The offset refers to the offset of the target object relative to the target position in the canvas of the display device, which can include the horizontal offset and the vertical offset, i.e., the horizontal distance and the vertical distance between the position of the target object and the target position in the canvas of the display device.

[0204] In the embodiments of the present application, the client can determine the offset of the target object relative to the target position in the canvas of the display device according to the position information of the target object in the display device and the determined canvas size.

[0205] As an optional implementation, the client can establish a coordinate system of the canvas of the display device. Then, according to the position information, the coordinate of the center position of the target object in the canvas (referred to as the first coordinate for ease of description) can be determined in the coordinate system.

[0206] Meanwhile, according to the canvas size, the coordinate of the center point of the target position in the canvas (referred to as the second coordinate for ease of description) can be determined in the coordinate system.

[0207] Finally, according to the first coordinate and the second coordinate, the horizontal offset and the vertical offset of the target object relative to the target position in the canvas can be determined, and the horizontal offset and the vertical offset are determined as the offset of the target object relative to the target position in the canvas.

[0208] Further, in order to prevent the target object from being moved to cause part of the image in the video frame to be blocked by the display screen of the display device, the client can limit the offset, for example, set an offset threshold for each offset, which can be three quarters of the corresponding size of the display screen (the horizontal offset corresponds to the width value of the display screen, and the vertical offset corresponds to the height value of the display screen).

[0209] For example, assuming that the coordinate system is established with the lower left corner of the canvas as the origin, and the center point of the target position is the center point of the canvas, and the canvas size is 50 cm in length and 70 cm in width, the second coordinate is (25, 35). It is assumed that the position information corresponds to the upper right corner of the canvas, and the first coordinate is (50, 70).

[0210] Based on the first coordinate and the second coordinate, it can be determined that the horizontal offset of the position of the target object in the canvas relative to the target position is -25, and the vertical offset is -35.

[0211] In step 403, the scaling ratio of the canvas is determined according to the position information and the target size.

[0212] The scaling ratio can refer to the scaling ratio of the canvas, or the scaling ratio of the canvas.

[0213] In the embodiment of the application, the client can determine the scaling ratio of the canvas according to the position information and the target size, and by scaling and enlarging the canvas according to the scaling ratio, the display device can clearly and completely display the target object.

[0214] As an optional implementation, the position information of the preset region containing the target object can include position coordinates of a plurality of boundary points in the preset region, or can include coordinates of a point and size information of the preset region, and the embodiments of the present application do not limit this. The preset region containing the target object can be a region composed of edges of the target object, or can be a preset region containing a preset part of the target object, for example, a region containing a head of the target object. It can be understood that a proportion of the target object to the entire region in the preset region containing the target object is greater than a preset value.

[0215] Based on this, the first width value and the first height value corresponding to the preset region containing the target object are determined according to the position information of the target object. It can be understood that if the preset region is irregularly shaped, the first width value can be a maximum width value of the preset region, and the first height value can be a maximum height value of the preset region.

[0216] At the same time, the second width value and the second height value of the target position can be determined according to the target size. Optionally, the target size can include shape information and coordinate information of the target position, and the second height value and the second width value of the target position are determined according to the shape information and the coordinate information.

[0217] In addition, the second width value and the second height value of the target position can also be determined according to the canvas size of the display device, for example, the width value of the canvas is reduced by 10%, to obtain the second width value, and the height value of the canvas is reduced by 10%, to obtain the second height value.

[0218] Finally, after the second height value and the second width value of the target position, and the first height value and the first width value of the target object are determined, a first proportion of the second width value and the first width value, and a second proportion of the second height value and the first height value can be determined.

[0219] Further, a minimum proportion can be determined from the first proportion and the second proportion, and the minimum proportion is compared with a preset proportion threshold. The proportion threshold can be 4 times magnification. By setting the proportion threshold, it can be prevented that the magnification of the target object is too large, so that the target object is overexposed.

[0220] Optionally, in a case where the minimum proportion value is compared to be less than the proportion threshold, the minimum proportion value can be determined as the scaling proportion of the canvas.

[0221] On the contrary, in a case where the minimum proportion value is compared to be greater than or equal to the proportion threshold, the proportion threshold can be determined as the scaling proportion of the canvas.

[0222] In step 404, the target object is adjusted in movement and / or in scale according to the offset and the scale ratio.

[0223] In the embodiment, after the offset of the target object and the scale ratio of the canvas are determined, the target object is adjusted in movement and / or in scale according to the offset and the scale ratio.

[0224] As an optional implementation, the target object is first adjusted in movement according to the offset, and then the canvas of the display device is adjusted in scale according to the scale ratio.

[0225] As another optional implementation, the canvas of the display device is first adjusted in scale according to the scale ratio, and then the offset is divided by the scale ratio to determine a new offset of the target object in the canvas relative to the target position after the adjustment in scale.

[0226] Then, the target object is translated according to the new offset to move the target object to the target position.

[0227] The technical scheme provided in the embodiment includes the following steps: obtaining the canvas size of the display device and the target size of the target position, determining the offset of the target object in the canvas of the display device relative to the target position according to the position information and the canvas size, determining the scale ratio of the canvas according to the position information and the target size, and adjusting the target object in movement and / or in scale according to the offset and the scale ratio. The technical scheme can efficiently and quickly determine the offset and the scale ratio of the target object in the canvas relative to the target position according to the canvas size of the display device and the target size of the target position.

[0228] Referring to FIG. 7, an embodiment of an object tracking device provided in the application is shown. As shown in FIG. 7, the device can include:

[0229] The receiving module 71 is configured to receive target video frame data sent by an image acquisition device, wherein the target video frame data includes spatial coordinate information of at least one object.

[0230] The display module 72 is configured to output a target video frame corresponding to the target video frame data through a display device, and determine a target object to be tracked from the target video frame based on the spatial coordinate information.

[0231] The first determining module 73 is configured to determine position information of the target object in the display device.

[0232] The second determining module 74 is configured to determine, based on the position information, an offset of the target object relative to a target position in a canvas of the display device and a zoom scale of the canvas.

[0233] The adjusting module 75 is configured to adjust the target object based on the position information, so that the target object is displayed at the target position of the display device.

[0234] As shown in FIG. 8, an electronic device provided by an embodiment of the present application includes a processor 81, a communication interface 82, a memory 83 and a communication bus 84, wherein the processor 81, the communication interface 82 and the memory 83 communicate with each other through the communication bus 84.

[0235] The memory 83 is configured to store a computer program.

[0236] In an embodiment of the present application, the processor 81 is configured to execute the program stored in the memory 83, so as to implement the object tracking method provided by any one of the preceding method embodiments, including:

[0237] receiving target video frame data sent by an image acquisition device, wherein the target video frame data includes spatial coordinate information of at least one object;

[0238] outputting a target video frame corresponding to the target video frame data through a display device, and determining a target object to be tracked from the target video frame based on the spatial coordinate information;

[0239] determining position information of the target object in the display device;

[0240] determining, based on the position information, an offset of the target object relative to a target position in a canvas of the display device and a zoom scale of the canvas;

[0241] adjusting the target object according to the offset and the zoom scale, so that the target object is displayed at the target position of the display device.

[0242] An embodiment of the present application further provides a storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the object tracking method provided by any one of the preceding method embodiments.

[0243] In particular implementations, the present application further provides a computer storage medium, wherein the computer storage medium can store a program, and the program can include some or all steps in the foregoing embodiments when executed. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0244] Those skilled in the art can clearly understand that the technology in the embodiments of the present application can be realized by means of software plus necessary general hardware platforms. Based on such understanding, the technical solutions in the embodiments of the present application can be embodied in the form of a software product in essence or in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disc, an optical disc, etc., 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 the methods described in the various embodiments or some parts of the embodiments of the present application.

[0245] The same or similar parts among the various embodiments in the specification can be referred to each other. In particular, for the … embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description in the method embodiment.

[0246] The above-described embodiments of the present application do not constitute a limitation on the protection scope of the present application.

Claims

1. A method of object tracking, characterized by, The method comprises: receiving target video frame data sent by an image acquisition device, the target video frame data comprising spatial coordinate information of at least one object; outputting a target video frame corresponding to the target video frame data by a display device, and determining a target object to be tracked from the target video frame based on the spatial coordinate information; determining position information of the target object in the display device; based on the position information, determining an offset of the target object relative to a target position in a canvas of the display device and a zoom ratio of the canvas; adjusting the target object according to the offset and the zoom ratio, so that the target object is displayed at the target position of the display device.

2. The method of claim 1, wherein, The image acquisition device determines the target video frame data by: acquiring a captured image of a preset region; determining whether the captured image meets a preset object tracking condition; in a case where it is determined that the captured image meets the object tracking condition, determining the captured image as a target video frame, and identifying objects included in the target video frame to determine original spatial coordinate information of each object included in the target video frame; multiplying the original spatial coordinate information by a preset ratio to obtain spatial coordinate information; writing the spatial coordinate information of each object as supplementary enhancement information into image information of the target video frame; encoding the target video frame and the image information of the target video frame to obtain target video frame data corresponding to the target video frame.

3. The method of claim 2, wherein, The determination of whether the captured image meets the preset object tracking condition comprises: generating a function signal in response to a received triggering operation on a preset object tracking function button; sending the function signal to the image acquisition device, so that the image acquisition device determines that the captured image meets the preset object tracking condition upon receiving the function signal.

4. The method of claim 1, wherein, The target video frame data is encoded data; The outputting of the target video frame corresponding to the target video frame data by the display device and the determination of the target object to be tracked from the target video frame based on the spatial coordinate information comprise: decoding the target video frame data to obtain the target video frame; acquiring spatial coordinate information of each object from the target video frame; outputting the target video frame by the display device and determining the target object to be tracked from the target video frame based on the spatial coordinate information.

5. The method of claim 1, wherein, The determination of the target object to be tracked from the target video frame based on the spatial coordinate information comprises: based on the spatial coordinate information, marking a plurality of objects included in the target video frame in the target video frame displayed by the display device; in a case where a selection operation on any object displayed by the display device is received, determining the object corresponding to the selection operation as the target object to be tracked; In a case where no selection operation is received for any object displayed by the display device, an object feature of an object corresponding to each spatial coordinate information is determined; it is determined whether each object feature is a preset target object feature; in a case where it is determined that the object feature is the target object feature, the object corresponding to the object feature is determined as a target object.

6. The method of claim 5, wherein, The object features include: The spatial coordinate information is written into a preset object array, where each array element of the object array corresponds to one spatial coordinate information; In response to a received display operation for an object in the target video frame, the object array is traversed; For each array element of the traversed object array, the spatial coordinate information corresponding to the array element is converted into a display coordinate; the display coordinate is a coordinate on the display device; The display coordinate is displayed on a corresponding region of the display device by a preset first display mode.

7. The method of claim 6, wherein, Each array element of the object array corresponds to an index, and in a case where a selection operation is received for any object displayed by the display device, the object corresponding to the selection operation is determined as a target object to be tracked, which includes: In response to a conversion operation for a displayed object in the display device, a target index currently recorded is determined; where, when the object array is traversed, an index corresponding to a traversed array element is recorded; A target display coordinate of the array element corresponding to the target index is determined; The target display coordinate is displayed on a corresponding target region of the display device by a preset second display mode; If a selection operation is received for the target region corresponding to the target display coordinate, the object corresponding to the target region is determined as a target object to be tracked.

8. The method of claim 5, wherein, The display screen of the display device is a touch screen; In a case where a selection operation is received for any object displayed by the display device, the object corresponding to the selection operation is determined as a target object to be tracked, which includes: In a case where a trigger operation is received for any object of the display screen, the object corresponding to the trigger operation is determined as a target object to be tracked.

9. The method of claim 1, wherein, The determination of the position information of the target object in the display device includes: A mapping relationship between spatial coordinates in a preset region and coordinates in a captured image is obtained from the image acquisition device; where, when the image acquisition device captures a captured image in the preset region, the mapping relationship is determined; According to the spatial coordinate information of the target object, image position information of the target object in the target video frame is determined from the mapping relationship; A display mapping relationship between coordinate information of the target video frame and a display screen of the display device is obtained; Based on the display mapping relationship, position information based on the display device corresponding to the image position information is determined.

10. The method of claim 1, wherein, The determining, based on the position information, of an offset of the target object relative to a target position in a canvas of the display device and a zoom scale of the canvas comprises: obtaining a canvas size of the display device and a target size of the target position; determining, according to the position information and the canvas size, the offset of the target object relative to the target position in the canvas of the display device; determining, according to the position information and the target size, the zoom scale of the canvas.

11. The method of claim 10, wherein, The determining, according to the position information and the canvas size, of the offset of the target object relative to the target position in the canvas of the display device comprises: establishing a coordinate system of the canvas; determining, according to the position information, a first coordinate of a center position of the target object in the canvas in the coordinate system; determining, according to the canvas size, a second coordinate of a center point of the target position in the canvas in the coordinate system; determining, according to the first coordinate and the second coordinate, a horizontal offset and a vertical offset of the target object relative to the target position in the canvas; determining the horizontal offset and the vertical offset as the offset of the target object relative to the target position in the canvas.

12. The method of claim 10, wherein, The position information is position information of a preset region containing the target object, and the determining, according to the position information and the target size, of the zoom scale of the canvas comprises: determining, according to the position information, a first width value and a first height value corresponding to the preset region containing the target object; determining, according to the target size, a second width value and a second height value of the target position; determining a first scale of the second width value and the first width value, and a second scale of the second height value and the first height value; determining a minimum scale value from the first scale and the second scale; in a case where the minimum scale value is less than a preset scale threshold, determining the minimum scale value as the zoom scale of the canvas.

13. The method of claim 1, wherein, The adjusting the target object according to the offset and the zoom scale comprises: moving the target object according to the offset; scaling the canvas of the display device according to the zoom scale.

14. The method of claim 1, wherein, When the target video frame data sent by the image acquisition device is first received, a timer is started, and after the target video frame corresponding to the target video frame data is output by the display device, the method further comprises: determining whether a count value currently recorded by the timer is greater than a preset count threshold; in a case where it is determined that the count value is greater than the count threshold, performing the step of determining the target object to be tracked from the target video frame based on the spatial coordinate information, and when the target object is adjusted, adjusting the target object through a preset animation, and updating the timer to a preset value after the target object is adjusted; in a case where it is determined that the count value is less than or equal to the count threshold, discarding the spatial coordinate information of the plurality of objects included in the target video frame data.

15. An object tracking apparatus, characterized by, The device comprises: The receiving module is configured to receive target video frame data transmitted by the image acquisition device, the target video frame data comprising spatial coordinate information of at least one object; The display module is configured to output a target video frame corresponding to the target video frame data through the display device, and determine a target object to be tracked from the target video frame based on the spatial coordinate information; The first determining module is configured to determine position information of the target object in the display device; The second determining module is configured to determine, based on the position information, an offset of the target object relative to a target position in a canvas of the display device and a zoom ratio of the canvas; The adjusting module is configured to adjust the target object according to the offset and the zoom ratio, so that the target object is displayed at the target position of the display device.

16. An object tracking system, characterized by The object tracking system comprises an image acquisition device, a client, and a display device; The image acquisition device is configured to acquire a target video frame of a preset area, identify spatial coordinate information of each object included in the target video frame, encode the spatial coordinate information into target video frame data, and transmit the target video frame data to the client; The display device is configured to display the target video frame transmitted by the image acquisition device; The client comprises a processor and a memory, and the processor is configured to execute an object tracking program stored in the memory to implement the object tracking method of any one of claims 1-14.

Images