Target Tracking Marking Method, System, Electronic Device and Readable Storage Medium

Abstract

The present invention discloses a target tracking and marking method, system, electronic device and readable storage medium. The target tracking and marking method includes: acquiring shooting data; reading the captured images according to a preset rule and putting them into a queue to be recognized; sequentially selecting single-frame captured images and recognizing the target to be measured and the image position information of the target to be measured; marking a tracking mark for the target to be measured according to the image position information; releasing the recognized single-frame captured image from the queue to be recognized, and selecting the next frame of captured image to recognize the target to be measured; comparing the recognition speed of the captured image with the reading speed of the captured image; adjusting the preset rule according to the comparison result, and reading the captured image according to the adjusted preset rule and putting it into the queue to be recognized. The present invention can effectively recognize and then mark and track the target in the environment to be measured with high precision and continuously by adjusting the rule of the data reading unit in real time according to the recognition speed of the captured image and the reading speed of the data reading unit.

Description

Technical Field

[0001] The present invention belongs to the field of machine vision detection, and particularly relates to a target tracking marking method, system, electronic device and readable storage medium. Background Art

[0002] With the gradual maturity of computer vision in recent years and the more powerful computing performance of computing devices, the computer can process visual images more quickly. Taking OpenCV (an open-source cross-platform computer vision library) as an example, it has many supported algorithm interfaces for computer vision and image processing. At the same time, it opens an interface for directly reading the captured frame data for the operation of some shooting devices (such as cameras). Each time a frame of data is read from the camera, and then the accessed vision detection algorithm or vision tracking algorithm performs image processing to achieve the recognition of the image. However, there is such a problem in the prior art. On the premise that the camera frame rate is determined, if the calculation time of the vision detection or vision tracking algorithm exceeds the frame interval of the camera, that is, the processing speed is slower than the frame data collection speed. If we want to achieve continuous time marking of the captured frame data, there will inevitably be a frame loss phenomenon, and in severe cases, the recognition target will be lost. Summary of the Invention

[0003] The technical problem to be solved by the embodiments of the present invention is to overcome the defect that the target is lost when the image processing speed is slower than the frame data collection speed of the shooting device in the image recognition process in the prior art, and to provide a target tracking marking method, system, electronic device and readable storage medium.

[0004] The embodiments of the present invention solve the above technical problems through the following technical solutions:

[0005] A target tracking marking method, the target tracking marking method comprising:

[0006] Obtaining the shooting data of the shooting device for the environment to be measured, the shooting data including multiple frames of shooting images;

[0007] Reading the shooting images according to a preset rule and putting them into the queue to be recognized;

[0008] Sequentially selecting single-frame shooting images from the queue to be recognized, and recognizing the single-frame shooting images to obtain the target to be measured and the image position information of the target to be measured in the single-frame shooting image;

[0009] Marking a tracking mark for the target to be measured according to the image position information;

[0010] Releasing the recognized single-frame shooting image from the queue to be recognized, and selecting the next frame of shooting image from the queue to be recognized to recognize the target to be measured;

[0011] Compare the recognition speed of the captured image with the reading speed of the captured image;

[0012] Adjust the preset rule according to the comparison result, and read the captured image into the to-be-recognized queue according to the adjusted preset rule.

[0013] Preferably, the step of comparing the recognition speed of the captured image with the reading speed of the captured image specifically includes:

[0014] Detect whether the data length of the to-be-recognized queue is greater than a first threshold and less than a second threshold;

[0015] The step of adjusting the preset rule according to the comparison result specifically includes:

[0016] If the comparison result is greater than the first threshold and less than the second threshold, the adjusted preset rule is to read the captured image once every n frames and put it into the to-be-recognized queue.

[0017] Preferably, the step of comparing the recognition speed of the captured image with the reading speed of the captured image further includes:

[0018] Set multiple threshold intervals between the first threshold and the second threshold;

[0019] Detect the target threshold interval into which the data length of the to-be-recognized queue falls;

[0020] The step of adjusting the preset rule according to the comparison result further includes:

[0021] Adjust the value of n according to the target threshold interval, and the value of n is positively correlated with the upper limit value of the target threshold interval.

[0022] Preferably, the step of adjusting the preset rule according to the comparison result further includes:

[0023] If the comparison result is not less than the second threshold, release all the captured images in the to-be-recognized queue, and read new captured images to form a new to-be-recognized queue.

[0024] Preferably, after the step of marking the to-be-detected target according to the image position information, the target tracking and marking method further includes:

[0025] Obtain the geographical location data of the imaging device;

[0026] Obtain the actual geographical location information of the to-be-detected target according to the geographical location data of the imaging device and the image position data of the to-be-detected target at the same moment;

[0027] Annotate the actual geographical location information for the target to be measured.

[0028] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned target tracking and marking method is implemented.

[0029] A computer-readable storage medium stores a computer program thereon. When the program is executed by a processor, the steps of the above-mentioned target tracking and marking method are implemented.

[0030] A target tracking and marking system includes a shooting data acquisition module, a queue to be recognized generation module, an identification module, a marking module, and a release module. The queue to be recognized generation module includes a comparison unit, a rule adjustment unit, and a reading unit;

[0031] The shooting data acquisition module is used to acquire shooting data of the shooting device for the environment to be measured, and the shooting data includes multiple frames of shooting images;

[0032] The queue to be recognized generation module is used to read the shooting images according to a preset rule and put them into the queue to be recognized;

[0033] The identification module is used to sequentially select a single-frame shooting image from the queue to be recognized, and identify the target to be measured and the image position information of the target to be measured in the single-frame shooting image;

[0034] The marking module is used to annotate a tracking mark for the target to be measured according to the image position information;

[0035] The release module is used to release the recognized single-frame shooting image from the queue to be recognized;

[0036] The identification module is further used to select the next frame of shooting image from the queue to be recognized to identify the target to be measured;

[0037] The comparison unit is used to compare the recognition speed of the recognized shooting image with the reading speed of the read shooting image;

[0038] The rule adjustment unit is used to adjust the preset rule according to the comparison result;

[0039] The reading unit is used to read the shooting images according to the adjusted preset rule and put them into the queue to be recognized.

[0040] Preferably, the queue to be recognized generation module further includes a length detection unit;

[0041] The length detection unit is used to detect whether the data length of the to-be-recognized queue is greater than the first threshold and less than the second threshold. If the comparison result is greater than the first threshold and less than the second threshold, the rule adjustment unit is called to adjust the preset rule, and the adjusted preset rule is to capture an image every n frames and read the captured image once and put it into the to-be-recognized queue.

[0042] Preferably, the to-be-recognized queue generation module further includes an interval setting unit;

[0043] The interval setting unit is used to set a plurality of threshold intervals between the first threshold and the second threshold;

[0044] The length detection unit is further used to detect the target threshold interval into which the data length of the to-be-recognized queue falls;

[0045] The rule adjustment unit is further used to adjust the value of n according to the target threshold interval, and the value of n is positively correlated with the upper limit value of the target threshold interval.

[0046] Preferably, when the comparison result is not less than the second threshold, the length detection unit is further used to call the release module to release all the captured images in the to-be-recognized queue, and call the reading unit to read new captured images to form a new to-be-recognized queue.

[0047] Preferably, the target tracking and marking system further includes a geographical location data acquisition module and a data processing module;

[0048] The geographical location data acquisition module is used to acquire the geographical location data of the imaging device;

[0049] The data processing module is used to obtain the actual geographical location information of the to-be-detected target according to the geographical location data of the imaging device and the image position data of the to-be-detected target at the same moment;

[0050] The marking module is used to mark the actual geographical location information on the to-be-detected target.

[0051] The positive and progressive effects of the embodiments of the present invention are as follows: According to the recognition speed of the recognized captured images and the reading speed of the reading data unit, the embodiments of the present invention adjust the rules of the reading data unit in real time, and can effectively recognize the targets in the to-be-detected environment with high precision and continuously, and then perform marking and tracking. Description of the Drawings

[0052] Figure 1 It is a flowchart of the target tracking and marking method according to Embodiment 1 of the present invention.

[0053] Figure 2It is a flowchart of step 16 in the target tracking and marking method according to Embodiment 2 of the present invention.

[0054] Figure 3 It is a flowchart of the target tracking and marking method according to Embodiment 3 of the present invention.

[0055] Figure 4 It is a schematic structural diagram of an electronic device according to Embodiment 4 of the present invention.

[0056] Figure 5 It is a schematic diagram of modules of a target tracking and marking system according to Embodiment 6 of the present invention.

[0057] Figure 6 It is a schematic diagram of a module of a to-be-identified queue generation module in the target tracking and marking system according to Embodiment 6 of the present invention.

[0058] Figure 7 It is a schematic diagram of a module of a to-be-identified queue generation module in the target tracking and marking system according to Embodiment 7 of the present invention.

[0059] Figure 8 It is a schematic diagram of modules of a target tracking and marking system according to Embodiment 8 of the present invention. Detailed implementation manners

[0060] The present invention will be further described below by way of embodiments, but the present invention is not limited to the scope of the described embodiments.

[0061] Embodiment 1

[0062] A target tracking and marking method, as Figure 1 shown, the target tracking and marking method includes:

[0063] Step 11: Obtain the shooting data of the shooting device for the environment to be measured, and the shooting data includes multiple frames of shooting images;

[0064] Step 12: Read the shooting images according to a preset rule and put them into the to-be-identified queue;

[0065] Step 13: Select a single-frame shooting image from the to-be-identified queue;

[0066] Step 14: Identify the target to be measured and the image position information of the target to be measured in the single-frame shooting image, and then execute step 15 and step 18 simultaneously;

[0067] Step 15: Release the identified single-frame shooting image from the to-be-identified queue, return to step 13, select the next frame of shooting image from the to-be-identified queue to identify the target to be measured, and execute step 16 simultaneously;

[0068] Step 16: Compare the recognition speed of the recognized shooting image with the reading speed of the read shooting image;

[0069] Step 17. Adjust the preset rule according to the comparison result, and return to Step 12. Read the captured image according to the adjusted preset rule and put it into the queue to be recognized.

[0070] Step 18. Mark the tracking mark on the target to be measured according to the image position information.

[0071] In this embodiment, by adjusting the rule of the data reading unit in real time according to the recognition speed of the captured image and the reading speed of the data reading unit, the target in the environment to be measured can be effectively recognized with high precision and continuously, and then marked and tracked. In addition, it should be noted that the target to be measured in this embodiment can be a target of a certain category, such as a car, a person, etc. As long as the object detected in the captured image can be marked. Even if the shooting angle of the imaging device changes, new targets will be updated in real time and marked and tracked.

[0072] Embodiment 2

[0073] The target tracking and marking method of this embodiment is a further improvement on the basis of Embodiment 1. As Figure 2 shown, Step 16 specifically includes:

[0074] Step 161. Detect whether the data length of the queue to be recognized is greater than the first threshold and less than the second threshold. If the comparison result is greater than the first threshold and less than the second threshold, execute Step 162. If the comparison result is not less than the second threshold, execute Step 163. If the comparison result is not greater than the first threshold, read according to the conventional reading rule, that is, the frame-by-frame reading method in the prior art.

[0075] The step of adjusting the preset rule according to the comparison result specifically includes:

[0076] Step 162. Adjust the preset rule. The adjusted preset rule is to read 1 captured image every n frames and put it into the queue to be recognized.

[0077] Step 163. Release all the captured images in the queue to be recognized, and return to Step 12 to read new captured images to form a new queue to be recognized.

[0078] In this embodiment, in order to more flexibly implement the reading of the data unit, before Step 161, Step 16 further includes:

[0079] Step 160. Set multiple threshold intervals between the first threshold and the second threshold.

[0080] After Step 162, Step 16 further includes:

[0081] Step 164: Detect the target threshold interval into which the data length of the queue to be recognized falls;

[0082] Step 165: Adjust the value of n according to the target threshold interval, and the value of n is positively correlated with the upper limit value of the target threshold interval.

[0083] Taking the interval segmentation into two segments as an example, obtain the list to be recognized: Read the shooting data according to time, enqueue the shooting image as a variable of the list to be recognized, set the first threshold (min) and the second threshold (max), and set the segmentation value (mid) of the interval segmentation. At this time, (min, mid) is the first threshold interval and the n value is set to 1, (mid, max) is the second threshold interval and the n value is set to 2. If the data length in the list to be recognized is less than min, enqueue frame by frame normally; if the data length of the list to be recognized is (min, mid), read the shooting image every other frame, that is, read one for every two shooting images; if the length of the list to be recognized is (mid, max), read the shooting image every two frames, that is, read one for every three shooting images; if the length of the list to be recognized is greater than max, clear the queue, read the data again and enqueue it, and restart the target positioning.

[0084] Embodiment 3

[0085] The target tracking and marking method of this embodiment is further improved on the basis of Embodiment 1. As Figure 3 shown, after step 18 of marking the target to be measured according to the image position information, the target tracking and marking method further includes:

[0086] Step 19: Obtain the geographical location data of the shooting device;

[0087] Step 110: Obtain the actual geographical location information of the target to be measured according to the geographical location data of the shooting device and the image position data of the target to be measured at the same moment;

[0088] Step 111: Mark the actual geographical location information for the target to be measured.

[0089] In this embodiment, on the basis of tracking and marking the target, the position data of the target can be obtained in real time. Further, accurate positioning of the target can be achieved.

[0090] Embodiment 4

[0091] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the target tracking and marking method described in any one of Embodiments 1-3.

[0092] Figure 4 The structural schematic diagram of an electronic device provided for this embodiment. Figure 4 The block diagram of an exemplary electronic device 90 suitable for implementing the embodiments of the present invention is shown. Figure 4 The shown electronic device 90 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0093] As Figure 4 shown, the electronic device 90 may be presented in the form of a general-purpose computing device. For example, it may be a server device. The components of the electronic device 90 may include but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0094] The bus 93 includes a data bus, an address bus, and a control bus.

[0095] The memory 92 may include volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922, and may further include a read-only memory (ROM) 923.

[0096] The memory 92 may also include a program tool 925 having a set (at least one) of program modules 924. Such program modules 924 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0097] The processor 91 executes various functional applications and data processing by running computer programs stored in the memory 92.

[0098] The electronic device 90 may also communicate with one or more external devices 94 (such as a keyboard, a pointing device, etc.). Such communication may be carried out through an input / output (I / O) interface 95. And, the electronic device 90 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 96. The network adapter 96 communicates with other modules of the electronic device 90 through the bus 93. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in combination with the electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0099] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / modules. Conversely, the features and functions of one unit / modules described above can be further divided and embodied by multiple units / modules.

[0100] Embodiment 5

[0101] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the target tracking and marking method described in any one of Embodiments 1-3 are implemented.

[0102] Among them, more specifically, the readable storage medium may include but is not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination of the above.

[0103] In a possible implementation manner, the embodiment of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps of the target tracking and marking method described in any one of Embodiments 1-3.

[0104] Among them, the program code for executing the embodiments of the present invention can be written in any combination of one or more programming languages. The program code can be completely executed on the user device, partially executed on the user device, executed as an independent software package, partially executed on the user device and partially executed on a remote device, or completely executed on a remote device.

[0105] Embodiment 6

[0106] A target tracking and marking system, as Figures 5 - 6 shown, the target tracking and marking system includes a shooting data acquisition module 1, a to-be-identified queue generation module 2, an identification module 3, a marking module 4, and a release module 5. The to-be-identified queue generation module 2 includes a comparison unit 21, a rule adjustment unit 22, and a reading unit 23;

[0107] The shooting data acquisition module 1 is used to acquire shooting data of the shooting device for the environment to be measured, and the shooting data includes multiple frames of shooting images;

[0108] The to-be-identified queue generation module 2 is used to read the shooting images according to a preset rule and put them into the to-be-identified queue;

[0109] The recognition module 3 is used to sequentially select a single-frame captured image from the to-be-recognized queue, and recognize the to-be-detected target and the image position information of the to-be-detected target in the single-frame captured image;

[0110] The marking module 4 is used to label a tracking mark for the to-be-detected target according to the image position information;

[0111] The releasing module 5 is used to release the recognized single-frame captured image from the to-be-recognized queue;

[0112] The recognition module 3 is further used to select the next frame of captured image from the to-be-recognized queue to recognize the to-be-detected target;

[0113] The comparison unit 21 is used to compare the recognition speed of the recognized captured image with the reading speed of the read captured image;

[0114] The rule adjustment unit 22 is used to adjust the preset rule according to the comparison result;

[0115] The reading unit 23 is used to read the captured image according to the adjusted preset rule and put it into the to-be-recognized queue.

[0116] In this embodiment, by adjusting the rule of the reading data unit in real time according to the recognition speed of the recognized captured image and the reading speed of the reading data unit, it is possible to effectively recognize the target in the to-be-detected environment with high precision and continuously, and then perform marking and tracking. In addition, it should be noted that the to-be-detected target in this embodiment can be a target of a certain category, such as a car, a person, etc. As long as the object detected in the captured image can be marked. Even if the shooting angle of the imaging device changes, new targets will be updated in real time and marked and tracked.

[0117] Embodiment 7

[0118] The target tracking and marking system of this embodiment is further improved on the basis of Embodiment 6. As Figure 7 shown, the to-be-recognized queue generation module 2 further includes a length detection unit 24;

[0119] The length detection unit 24 is used to detect whether the data length of the to-be-recognized queue is greater than a first threshold and less than a second threshold. If the comparison result is greater than the first threshold and less than the second threshold, the rule adjustment unit 22 is called to adjust the preset rule, and the adjusted preset rule is to read 1 captured image every n frames of captured images and put it into the to-be-recognized queue.

[0120] The length detection unit 24 is further configured to, when the comparison result is not less than the second threshold, call the release module 5 to release all the captured images in the to-be-recognized queue, and call the reading unit 23 to read new captured images to form a new to-be-recognized queue.

[0121] In this embodiment, the to-be-recognized queue generation module 2 further includes an interval setting unit 25;

[0122] The interval setting unit 25 is configured to set a plurality of threshold intervals between the first threshold and the second threshold;

[0123] The length detection unit 24 is further configured to detect the target threshold interval into which the data length of the to-be-recognized queue falls;

[0124] The rule adjustment unit 22 is further configured to adjust the value of n according to the target threshold interval, and the value of n is positively correlated with the upper limit value of the target threshold interval.

[0125] Taking the interval segmentation into two segments as an example, obtain the to-be-recognized list: read the captured data according to time, enqueue the captured image as a variable of the to-be-recognized list, set the first threshold (min) and the second threshold (max), and set the segmentation value (mid) of the interval segmentation. At this time, (min, mid) is the first threshold interval, and the n value is set to 1, (mid, max) is the second threshold interval, and the n value is set to 2. If the data length in the to-be-recognized list is less than min, enqueue frame by frame normally; if the data length of the to-be-recognized list is (min, mid), read the captured image every other frame, that is, read one captured image every two frames; if the length of the to-be-recognized list is (mid, max), read the captured image every two frames, that is, read one captured image every three frames; if the length of the to-be-recognized list is greater than max, clear the queue, read the data into the queue again, and restart the target positioning.

[0126] Embodiment 8

[0127] The target tracking and marking method of this embodiment is further improved on the basis of Embodiment 6, as Figure 8 shown, the target tracking and marking system further includes a geographical location data acquisition module 6 and a data processing module 7;

[0128] The geographical location data acquisition module 6 is configured to acquire the geographical location data of the photographing device;

[0129] The data processing module 7 is configured to obtain the actual geographical location information of the to-be-detected target according to the geographical location data of the photographing device and the image position data of the to-be-detected target at the same moment;

[0130] The marking module 4 is used to label the actual geographical location information for the target to be measured.

[0131] In this embodiment, based on the tracking and marking of the target, the position data of the target can be obtained in real time. Further, the accurate positioning of the target can be realized.

[0132] Although the specific implementation manners of the present invention have been described above, those skilled in the art should understand that this is only an example. The protection scope of the present invention is defined by the appended claims. Without departing from the principle and essence of the present invention, those skilled in the art can make various changes or modifications to these implementation manners, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A target tracking and marking method, characterized in that, The target tracking and marking method includes: Obtaining the shooting data of the shooting device for the environment to be measured, where the shooting data includes multiple frames of shooting images; Reading the shooting images according to a preset rule and putting them into the queue to be recognized; Sequentially selecting a single-frame shooting image from the queue to be recognized, and recognizing the target to be measured and the image position information of the target to be measured in the single-frame shooting image; Marking a tracking mark for the target to be measured according to the image position information; Releasing the recognized single-frame shooting image from the queue to be recognized, and selecting the next frame of shooting image from the queue to be recognized to recognize the target to be measured; Comparing the recognition speed of the recognized shooting images with the reading speed of the read shooting images; Adjusting the preset rule according to the comparison result, and reading the shooting images according to the adjusted preset rule and putting them into the queue to be recognized.

2. The target tracking and marking method according to claim 1, characterized in that, The step of comparing the recognition speed of the recognized shooting images with the reading speed of the read shooting images specifically includes: Detecting whether the data length of the queue to be recognized is greater than a first threshold and less than a second threshold; The step of adjusting the preset rule according to the comparison result specifically includes: If the comparison result is greater than the first threshold and less than the second threshold, the adjusted preset rule is to read 1 shooting image every n frames of shooting images and put it into the queue to be recognized.

3. The target tracking and marking method according to claim 2, characterized in that, The step of comparing the recognition speed of the recognized shooting images with the reading speed of the read shooting images further includes: Setting multiple threshold intervals between the first threshold and the second threshold; Detecting the target threshold interval into which the data length of the queue to be recognized falls; The step of adjusting the preset rule according to the comparison result further includes: Adjusting the value of n according to the target threshold interval, and the value of n is positively correlated with the upper limit value of the target threshold interval.

4. The target tracking and marking method according to claim 2, characterized in that, The step of adjusting the preset rule according to the comparison result further includes: If the comparison result is not less than the second threshold, releasing all the shooting images in the queue to be recognized, and reading new shooting images to form a new queue to be recognized.

5. The target tracking and marking method according to claim 1, characterized in that, After the step of marking the target to be measured according to the image position information, the target tracking and marking method further includes: Obtaining the geographical location data of the shooting device; Obtaining the actual geographical location information of the target to be measured according to the geographical location data of the shooting device and the image position data of the target to be measured at the same moment; Marking the actual geographical location information for the target to be measured.

6. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the target tracking and marking method according to any one of claims 1 to 5.

7. A computer-readable storage medium, on which a computer program is stored, characterized in that, When the program is executed by the processor, it implements the steps of the target tracking and marking method according to any one of claims 1 to 5.

8. A target tracking and marking system, characterized in that, The target tracking and marking system includes a shooting data acquisition module, a queue generation module to be recognized, a recognition module, a marking module and a release module. The queue generation module to be recognized includes a comparison unit, a rule adjustment unit and a reading unit; The shooting data acquisition module is used to obtain the shooting data of the shooting device for the environment to be measured, where the shooting data includes multiple frames of shooting images; The to-be-recognized queue generation module is used to read the captured images according to a preset rule and put them into the to-be-recognized queue; The recognition module is used to sequentially select a single-frame captured image from the to-be-recognized queue, and recognize the to-be-detected target and the image position information of the to-be-detected target in the single-frame captured image; The marking module is used to label a tracking mark for the to-be-detected target according to the image position information; The releasing module is used to release the recognized single-frame captured image from the to-be-recognized queue; The recognition module is further used to select the next frame of captured image from the to-be-recognized queue to recognize the to-be-detected target; The comparison unit is used to compare the recognition speed of the recognized captured image with the reading speed of the read captured image; The rule adjustment unit is used to adjust the preset rule according to the comparison result; The reading unit is used to read the captured image according to the adjusted preset rule and put it into the to-be-recognized queue.

9. The target tracking marker system according to claim 8, wherein, The to-be-recognized queue generation module further includes a length detection unit; The length detection unit is used to detect whether the data length of the to-be-recognized queue is greater than a first threshold and less than a second threshold. If the comparison result is greater than the first threshold and less than the second threshold, the rule adjustment unit is called to adjust the preset rule, and the adjusted preset rule is to read 1 captured image every n frames of captured images and put it into the to-be-recognized queue.

10. The target tracking marker system according to claim 9, wherein, The to-be-recognized queue generation module further includes an interval setting unit; The interval setting unit is used to set a plurality of threshold intervals between the first threshold and the second threshold; The length detection unit is further used to detect the target threshold interval into which the data length of the to-be-recognized queue falls; The rule adjustment unit is further used to adjust the value of n according to the target threshold interval, and the value of n is positively correlated with the upper limit value of the target threshold interval.

11. The target tracking marker system according to claim 9, wherein, The length detection unit is further used to call the releasing module to release all the captured images in the to-be-recognized queue and call the reading unit to read new captured images to form a new to-be-recognized queue when the comparison result is not less than the second threshold.

12. The target tracking marker system according to claim 8, wherein, The target tracking mark system further includes a geographical location data acquisition module and a data processing module; The geographical location data acquisition module is used to acquire the geographical location data of the capturing device; The data processing module is used to obtain the actual geographical location information of the to-be-detected target according to the geographical location data of the capturing device and the image position data of the to-be-detected target at the same moment; The marking module is used to label the actual geographical location information for the to-be-detected target.

Images