A detection tracking method and device, electronic equipment and storage medium

Abstract

The application discloses a detection tracking method and device, electronic equipment and storage medium, which are used for realizing complete and accurate tracking of high-altitude objects. The method comprises the following steps: detecting a second image obtained by performing contrast enhancement processing on a first image to obtain a plurality of sub-images; determining an estimated position center point of a to-be-tracked target in the first image based on the position of the to-be-tracked target in a previous frame image of the first image, and determining a corresponding position evaluation value of each sub-image; determining estimated size information of the to-be-tracked target in the first image based on size information of the to-be-tracked target in the previous frame image, and determining a corresponding size evaluation value of each sub-image; determining a corresponding comprehensive evaluation value based on the obtained position evaluation values and one-to-one corresponding size evaluation values, screening a target sub-image containing the to-be-tracked target which meets a screening condition, and updating sub-images contained in a tracking sequence corresponding to the to-be-tracked target.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular to a detection tracking method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, with the rapid development of economic society and the acceleration of urbanization process, the population of large cities is growing, and the safety problem of public places also comes. For example, the safety problem caused by high-altitude throwing.

[0003] Specifically, for the fast-moving target such as high-altitude throwing, high-altitude flying birds, high-altitude flying aircraft, high-altitude unmanned aerial vehicles, the detection scheme provided in the prior art is to use a background modeling algorithm to obtain the specific position of the dynamic target in the background, and then to realize real-time tracking of the target through a moving image with a certain frame rate.

[0004] However, for scenes with low contrast, the scheme of tracking and detecting the target based on the background modeling algorithm may have the problem of dividing a target into multiple targets, that is, the position of the target cannot be accurately determined, so that it is difficult to correctly track the target, thereby affecting the overall tracking effect.

[0005] At the same time, due to the too fast movement speed of the target, that is, the distance between the position of the target in the previous frame image and the position of the target in the next frame image is too large, the algorithm based on the existing detection scheme cannot associate the two targets, resulting in the disappearance of the previous target sequence and the generation of a new target sequence, that is, the tracking sequence of the target cannot be formed very completely. That is, the detection scheme of the prior art has the problem of "missing the target", which leads to the inability to accurately and completely track the target. SUMMARY

[0006] The embodiments of the present application provide a detection tracking method, device, electronic equipment and storage medium, which are used to realize complete and accurate tracking of high-altitude objects.

[0007] In a first aspect, a detection tracking method is provided, and the method comprises:

[0008] performing contrast enhancement processing on a first image to obtain a second image, and performing detection processing on the second image to obtain a plurality of sub-images containing connected domains of dynamic regions;

[0009] determining an estimated position center point of a target to be tracked in the first image based on the position of the target to be tracked in a previous frame image of the first image, and obtaining a corresponding position evaluation value based on the distance between the estimated position center point and the position center point corresponding to each obtained sub-image;

[0010] determine estimated size information of the target to be tracked in the first image based on size information of the target to be tracked in the previous frame image, and obtain corresponding size evaluation values based on the size information of each sub-image and the estimated size information respectively;

[0011] determine corresponding comprehensive evaluation values based on the obtained position evaluation values and one-to-one corresponding size evaluation values, and screen target sub-images containing the target to be tracked that meet screening conditions based on the obtained comprehensive evaluation values, and update sub-images contained in a tracking sequence corresponding to the target to be tracked.

[0012] In a possible implementation, the first image is subjected to a contrast enhancement process to obtain a second image, including:

[0013] the first image is subjected to a digital image transformation process to obtain a hue saturation value (HSV) color model feature map;

[0014] feature extraction is performed on the HSV color model feature map to obtain feature pixel values of a preset region;

[0015] the first image is subjected to a weighting process based on the feature pixel values of the preset region to obtain a second image.

[0016] In a possible implementation, after the plurality of sub-images are obtained, the method further includes:

[0017] foreground recognition processes are respectively performed on the plurality of sub-images to obtain recognition results corresponding to the plurality of sub-images;

[0018] when it is determined that the recognition result of any sub-image is that the sub-image is a full background image, the any sub-image is subjected to a deletion process to obtain a first processing set.

[0019] In a possible implementation, after the first processing set is obtained, the method further includes:

[0020] super-resolution recognition processes are performed on each sub-image in the first processing set to obtain resolution recognition results corresponding to each sub-image in the first processing set respectively;

[0021] when it is determined that the resolution of any sub-image corresponding to a resolution recognition result is lower than a preset threshold, the any sub-image in the first processing set is subjected to a deletion process to obtain a second processing set.

[0022] In a possible implementation, corresponding position evaluation values are obtained based on distances between position center points of each sub-image and the estimated position center point respectively, including:

[0023] The following operations are performed on each sub-image respectively:

[0024] A first relative distance value between the position point of the target to be tracked in the previous frame image and the estimated position center point is determined, and a first difference value between the first relative distance value and a second relative distance value is determined; wherein the second relative distance value is the distance value between the position center point of the first sub-image and the position point of the target to be tracked in the previous frame image;

[0025] A region radius of the first region is determined based on the sub-image corresponding to the target to be tracked in the previous frame image and the first sub-image, and a second difference value between the first difference value and the region radius is determined;

[0026] The second difference value is processed based on an activation function to obtain a position evaluation value of the first sub-image; the activation function is used to map a real number to an interval between 0 and 1.

[0027] In a possible implementation, a corresponding size evaluation value is obtained based on the obtained size information corresponding to each sub-image and the estimated size information, including:

[0028] The following operations are performed on each sub-image respectively:

[0029] It is determined whether the size information of the second sub-image is within the range of the maximum size information and the minimum size information corresponding to the estimated size information;

[0030] When it is determined that the size information of the second sub-image is not within the range of the maximum size information and the minimum size information, it is determined that the size evaluation value of the second sub-image is empty;

[0031] When it is determined that the size information of the second sub-image is within the range of the maximum size information and the minimum size information, it is determined that the size evaluation value of the second sub-image is a preset value.

[0032] In a possible implementation, based on the obtained comprehensive evaluation values, a target sub-image meeting a screening condition is screened, including:

[0033] The obtained comprehensive evaluation values are sorted in descending order to obtain sorted comprehensive evaluation values;

[0034] The sub-image corresponding to each sorted comprehensive evaluation value is compared with the previous frame image of the first image in terms of features to obtain a feature comparison value, and the sub-image corresponding to the maximum feature comparison value in the feature comparison values is taken as a target sub-image.

[0035] In a second aspect, a detection and tracking device is provided, and the device includes:

[0036] The first processing unit is configured to perform contrast enhancement processing on the first image to obtain a second image, and perform detection processing on the second image to obtain a plurality of sub-images containing dynamic regions;

[0037] The first obtaining unit is configured to determine a center point of an estimated position of the target to be tracked in the first image based on a position of the target to be tracked in a previous frame of the first image, and obtain a corresponding position evaluation value based on a distance between the center point of the estimated position and a corresponding center point of each of the obtained sub-images.

[0038] The second obtaining unit is configured to determine estimated size information of the target to be tracked in the first image based on size information of the target to be tracked in the previous frame of the first image, and obtain a corresponding size evaluation value based on the estimated size information and corresponding size information of each of the sub-images.

[0039] The tracking unit is configured to determine a corresponding comprehensive evaluation value based on each of the position evaluation values and one-to-one corresponding size evaluation values, and filter a target sub-image containing the target to be tracked based on each of the comprehensive evaluation values, and update a sub-image contained in a tracking sequence corresponding to the target to be tracked.

[0040] In a possible implementation, the first processing unit is specifically configured to:

[0041] perform digital image transformation processing on the first image to obtain an HSV color model feature map;

[0042] perform feature extraction on the HSV color model feature map to obtain feature pixel values of a preset region;

[0043] perform weighted processing on the first image based on the feature pixel values of the preset region to obtain a second image.

[0044] In a possible implementation, the apparatus further includes a second processing unit configured to:

[0045] perform foreground recognition processing on each of the plurality of sub-images to obtain a corresponding recognition result of each of the plurality of sub-images;

[0046] when it is determined that the recognition result of any sub-image is that the sub-image is a full background image, perform deletion processing on the any sub-image to obtain a first processing set.

[0047] In a possible implementation, the second processing unit is further configured to:

[0048] perform super-resolution identification processing on each of the sub-images in the first processing set to obtain a resolution identification result corresponding to each of the sub-images in the first processing set;

[0049] when it is determined that the resolution corresponding to any of the sub-images in the resolution identification result is lower than a preset threshold, performing deletion processing on the any of the sub-images in the first processing set to obtain a second processing set.

[0050] In a possible implementation, the first obtaining unit is specifically configured to:

[0051] perform the following operations on each of the sub-images respectively:

[0052] determine a first relative distance value between a position point of the target to be tracked in the previous frame image and a center point of the estimated position, and determine a first difference value between the first relative distance value and a second relative distance value; the second relative distance value is a distance value between the center point of the position of the first sub-image and the position point of the target to be tracked in the previous frame image;

[0053] determine a region radius of the first region based on the sub-image corresponding to the target to be tracked in the previous frame image and the first sub-image, and determine a second difference value between the first difference value and the region radius;

[0054] perform processing on the second difference value based on an activation function to obtain a position evaluation value of the first sub-image; the activation function is used to map a real number to an interval between 0 and 1.

[0055] In a possible implementation, the second obtaining unit is specifically configured to:

[0056] perform the following operations on each of the sub-images respectively:

[0057] determine whether the size information of the second sub-image is within a range of the maximum size information and the minimum size information corresponding to the estimated size information;

[0058] when it is determined that the size information of the second sub-image is not within the range of the maximum size information and the minimum size information, determine that the size evaluation value of the second sub-image is empty;

[0059] when it is determined that the size information of the second sub-image is within the range of the maximum size information and the minimum size information, determine that the size evaluation value of the second sub-image is a preset value.

[0060] In a possible implementation, the tracking unit is specifically configured to:

[0061] sort the obtained comprehensive evaluation values in descending order to obtain sorted comprehensive evaluation values.

[0062] The feature comparison is performed between the sub-image corresponding to the maximum feature comparison value and a previous frame of the first image to obtain a feature comparison value, and the sub-image corresponding to the maximum feature comparison value is taken as a target sub-image.

[0063] In a third aspect, an electronic device is provided, and the electronic device comprises:

[0064] a memory configured to store program instructions;

[0065] a processor configured to invoke the program instructions stored in the memory and perform the steps included in any of the methods of the first aspect according to the obtained program instructions.

[0066] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps included in any of the methods of the first aspect.

[0067] In a fifth aspect, a computer program product is provided, and when the computer program product is executed on an electronic device, the electronic device is enabled to perform the steps included in any of the methods of the first aspect.

[0068] The embodiments of the present application provide at least the following beneficial effects:

[0069] In the method, first, the electronic device can perform contrast enhancement processing on the obtained first image to obtain a second image. In this way, the obtained second image is an image with strong contrast, which overcomes the problem of inaccurate subsequent detection caused by low contrast. Then, the electronic device can perform detection processing on the second image to obtain a plurality of sub-images containing connected domains of dynamic regions.

[0070] Further, the electronic device can determine an estimated position center point of the target to be tracked in the first image based on the position of the target to be tracked in a previous frame of the first image, and obtain a corresponding position evaluation value based on the distance between the position center point corresponding to each obtained sub-image and the estimated position center point, and determine the estimated size information of the target to be tracked in the first image based on the size information of the target to be tracked in the previous frame of the first image, and obtain a corresponding size evaluation value based on the size information corresponding to each sub-image and the estimated size information. In this way, the corresponding comprehensive evaluation value can be determined based on the obtained each position evaluation value and one-to-one corresponding each size evaluation value.

[0071] Finally, the electronic device can screen the target sub-image containing the target to be tracked that meets the screening condition based on the obtained comprehensive evaluation values, and update the sub-image contained in the tracking sequence corresponding to the target to be tracked, so as to realize complete and accurate tracking of the target to be tracked.

[0072] Additional features and advantages of the application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0073] The accompanying drawings incorporated in and forming a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application. They are intended for use only for illustrative purposes and, not to limit the scope of the application.

[0074] Figure 1 An application scenario in an embodiment of the present application is shown in the following schematic diagram.

[0075] Figure 2 A flowchart of a detection and tracking method in an embodiment of the present application is shown in the following schematic diagram.

[0076] Figure 3 A schematic diagram of determining a position evaluation value in an embodiment of the present application is shown in the following schematic diagram.

[0077] Figure 4 A schematic diagram of determining a speed and an acceleration corresponding to a target to be tracked in a previous frame of image in an embodiment of the present application is shown in the following schematic diagram.

[0078] Figure 5 A schematic diagram of determining a size evaluation value in an embodiment of the present application is shown in the following schematic diagram.

[0079] Figure 6 A schematic diagram of a detection and tracking method in an embodiment of the present application is shown in the following schematic diagram.

[0080] Figure 7 A structural block diagram of a detection and tracking device in an embodiment of the present application is shown in the following schematic diagram.

[0081] Figure 8 A structural schematic diagram of an electronic device in an embodiment of the present application is shown in the following schematic diagram. DETAILED DESCRIPTION

[0082] In order to make the objects, technical solutions and advantages 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 a part of the embodiments of the present application, rather than all the embodiments. 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 protection scope of the present application. In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other at will. Moreover, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in an order different from that herein.

[0083] The terms "first" and "second" in the description and claims of the present application and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0084] As described above, in the prior art, when detecting and tracking a high-altitude fast-moving target, in a low-contrast scene, the target is easily segmented into multiple targets, resulting in inaccurate positioning of the target, i.e., the position of the target is not accurately positioned, which may lead to loss of tracking of the target, i.e., the tracking of the target cannot be completed and accurately.

[0085] Therefore, the embodiments of the present application provide a detection and tracking method. In the method, first, the electronic device can perform contrast enhancement processing on the obtained first image to obtain a second image. In this way, the obtained second image is an image with strong contrast, overcoming the problem of low contrast leading to inaccurate subsequent detection. Then, the electronic device can perform detection processing on the second image to obtain a plurality of sub-images containing connected domains of dynamic regions.

[0086] Further, the electronic device can determine an estimated position center point of the target to be tracked in the first image based on the position of the target to be tracked in the previous frame image of the first image, and obtain a corresponding position evaluation value based on the distance between the position center point corresponding to each obtained sub-image and the estimated position center point, respectively; and determine the estimated size information of the target to be tracked in the first image based on the size information of the target to be tracked in the previous frame image, and obtain a corresponding size evaluation value based on the size information corresponding to each sub-image and the estimated size information, respectively. In this way, based on the obtained each position evaluation value and the one-to-one corresponding each size evaluation value, a corresponding comprehensive evaluation value can be determined.

[0087] Finally, the electronic device can filter the target sub-image containing the target to be tracked that meets the filtering condition based on the obtained comprehensive evaluation values, and update the sub-image contained in the tracking sequence corresponding to the target to be tracked, thereby realizing complete and accurate tracking of the target to be tracked.

[0088] After introducing the design idea of the embodiment of the application, the application scenarios to which the technical solutions in the embodiment of the application are applicable will be briefly introduced. It should be noted that the application scenarios described in the embodiment of the application are used to more clearly illustrate the technical solutions of the embodiment of the application, and do not constitute a limitation on the technical solutions provided by the embodiment of the application. It can be known by those skilled in the art that, as new application scenarios appear, the technical solutions provided by the embodiment of the application are also applicable to similar technical problems.

[0089] Please refer to Figure 1 Fig. 1 is a schematic diagram of a scene to which the embodiment of the application can be applied. The scene includes an information collection device 101, an electronic device 102, and other electronic devices 103. The detection and tracking method of the embodiment of the application can be realized by the information collection device 101 and the electronic device 102 in cooperation, and can realize tracking and processing of high-altitude objects in combination with other electronic devices. Figure 1

[0090] In the specific implementation process, the information collection device 101 described above can obtain video stream information, and the video stream information includes at least one high-altitude object. After the information collection device 101 collects data corresponding to the at least one high-altitude object, the data can be sent to the electronic device 102 through the network 104. For example, the information collection device 101 can be arranged at an intersection, a shopping mall, a commercial building, a residential building, or the like.

[0091] The electronic device 102 can include one or more processors 1021, a memory 1022, an I / O interface 1023 for interacting with the information collection device 101, and an I / O interface 1024 for interacting with other electronic devices 103, and the like. In the specific implementation process, multiple electronic devices 102 can interact with multiple information collection devices 101, one electronic device 102 can interact with multiple information collection devices 101, or one electronic device 102 can interact with one information collection device 101, which is not limited in the embodiment of the application. Specifically, the electronic device 102 can also be connected to other electronic devices 103, feed back tracking data of the high-altitude object to the other electronic devices, Figure 1 Fig. 1 shows an example in which one electronic device 102 interacts with one information collection device 101 and one other electronic device 103.

[0092] ​In the embodiment of the present application, the electronic device 102 can receive the data sent by the information collection device 101 through the I / O interface 1023, then process the data by using the processor 1021, and store the processed information in the memory 1022. Of course, the electronic device 102 can send the processed information to other electronic device 103 through the interface 1024.

[0093] The information collection device 101 and the electronic device 102 can be connected through one or more networks 104. The other electronic device 103 and the electronic device 102 can also be connected through one or more networks 104. The network 104 can be a wired network or a wireless network. For example, the wireless network can be a mobile cellular network or a wireless fidelity (WIFI) network. Of course, the network 104 can also be other possible networks, and the embodiment of the present application does not make any limitation in this regard.

[0094] In the specific implementation process, after the electronic device 102 receives the data of the video stream containing at least one high-altitude object, the data can be processed to determine the falling trajectory of the high-altitude object, obtain the tracking sequence of the high-altitude object, and feed back the tracking sequence to the other electronic device 103, and then the other electronic device 103 realizes the confirmation and subsequent processing of the falling trajectory of the high-altitude object.

[0095] To further illustrate the scheme of the detection and tracking method provided by the embodiment of the present application, the following will be described in detail in combination with the drawings and the specific implementation. Although the embodiment of the present application provides the method operation steps as described in the following embodiments or shown in the drawings, more or less operation steps can be included in the method based on conventional or non-creative labor. The execution order of these steps is not limited to the execution order provided by the embodiment of the present application in the steps that do not have necessary causal relationship in logic. The method can be executed in sequence or in parallel (for example, in the application environment of parallel processor or multi-thread processing) in the actual processing process or when the device executes, according to the method order shown in the embodiments or drawings.

[0096] The following will be described in combination with the method flowchart shown in Figure 2 to illustrate the detection and tracking method in the embodiment of the present application, Figure 2 The steps shown in Figure 1 can be executed by the electronic device as shown in

[0097] Step 201: performing contrast enhancement processing on the first image to obtain a second image; and performing detection processing on the second image to obtain a plurality of sub-images containing dynamic regions. Step 202: performing tracking processing on the plurality of sub-images to obtain a tracking sequence of the high-altitude object.

[0098] In the embodiment of the present application, the electronic device can obtain the video stream to be processed from the information collection device, and then perform frame splitting processing on the video stream to be processed to obtain each image. Then, the electronic device can determine the first image, and perform contrast enhancement processing on the first image to obtain the second image. It should be noted that the first image can be the third frame image or the fifth frame image in the video stream to be processed, and the embodiment of the present application does not limit this.

[0099] In an optional implementation, the electronic device can perform contrast enhancement processing on the first image to obtain the second image by using but not limited to the following steps.

[0100] Step A: performing digital image transformation processing on the first image to obtain a hue saturation value HSV color model feature map.

[0101] In the embodiment of the present application, the electronic device can perform digital image transformation processing on the first image. Specifically, the electronic device can convert the RGB color mode corresponding to the first image into hue saturation value (HSV) based on a conversion equation to obtain a hue saturation value HSV color model feature map, where the conversion equation is as follows.

[0102] g(i,j)=αf(i,j)+β

[0103] Where g is the HSV color domain pixel value after conversion, f is the RGB color domain pixel value before conversion, and a and β are constants.

[0104] Step B: performing feature extraction on the HSV color model feature map to obtain feature pixel values of a preset region.

[0105] In the embodiment of the present application, the electronic device can perform feature extraction on the HSV color model feature map. The feature extraction method can be one or more of linear feature extraction, mean value feature extraction, and region feature extraction, and the embodiment of the present application does not limit this. For example, the region feature extraction method is used to perform feature extraction on the HSV color model feature map.

[0106] Step C: performing weighted processing on the first image based on the feature pixel values of the preset region to obtain the second image.

[0107] In the embodiment of the present application, the electronic device can weight the original image based on the HSV image of the dynamic region, i.e., the feature pixel values of the preset region, to obtain the enhanced image, i.e., the second image. The above process can be represented by the following formula:

[0108]

[0109] Wherein, Fb is used to represent the second image, Fs is used to represent the first image, and g(i, j) is used to represent the feature pixel value of the preset region.

[0110] In the embodiment of the present application, after obtaining the second image, the electronic device can perform detection processing on the second image, that is, by executing a dynamic detection algorithm on the second image, the information of the dynamic target detection frame is obtained to obtain the corresponding sub-image.

[0111] In the specific implementation process, the electronic device can process the second image based on a background modeling algorithm to obtain the connected domain of the dynamic region in the second image, and further obtain the sub-image corresponding to each connected domain. The background modeling algorithm includes but is not limited to static difference algorithm, Gaussian Mixture Model (GMM), and visual background extractor (ViBE).

[0112] In the specific implementation process, the electronic device can perform filtering processing on each obtained connected domain to obtain the continuous region edge corresponding to each connected domain. The filtering algorithm used to perform filtering processing includes but is not limited to mean filtering algorithm, median filtering algorithm, and Gaussian filtering algorithm. Further, the single device can also process each obtained connected domain based on a connected domain search algorithm to determine the circumscribed region of the foreground of each dynamic region, so that each connected domain containing the edge continuous circumscribed region can be obtained, that is, a relatively complete sub-image can be obtained. The connected domain search algorithm can include but is not limited to Depth-First-Search (DFS) and Breadth First Search (BFS).

[0113] In the embodiment of the present application, after the electronic device obtains the complete connected domain containing the dynamic region of each sub-image, the sub-image can be super-resolution corrected to obtain a relatively clear sub-image.

[0114] Optionally, the electronic device can perform foreground recognition processing on each of the plurality of sub-images to obtain a recognition result corresponding to each of the plurality of sub-images; when it is determined that the recognition result of any sub-image is that the sub-image is a full background image, the any sub-image is deleted to obtain a first processing set.

[0115] Specifically, the electronic device can perform foreground recognition processing on all sub-images based on a target classification algorithm to obtain a recognition result corresponding to each sub-object, and then delete the sub-image whose recognition result is that the sub-image is a full background image.

[0116] The target classification algorithm can include, but is not limited to, K-nearst neighbor (KNN), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Scale Invariant Feature Transform (SIFT).

[0117] Further, after the electronic device obtains the first processing set, the electronic device can further perform super-resolution recognition processing on each sub-image in the first processing set to obtain a resolution recognition result corresponding to each sub-image in the first processing set; when it is determined that the resolution of any sub-image in the resolution recognition result is lower than a preset threshold, any sub-image in the first processing set is deleted to obtain a second processing set.

[0118] It can be seen that, in the embodiment of the application, each sub-image in the first processing set can be processed based on a super-resolution reconstruction algorithm, so that a clearer sub-image can be obtained. That is, the sub-image with blur and ghosting in the first processing set can be removed, so that the sub-image without the full background image and the sub-image without blur and ghosting in the obtained second processing set can be obtained, thereby providing a good implementation basis for subsequent determination of the to-be-tracked target, and avoiding the problem of incorrect tracking of the to-be-tracked target due to unclear sub-images.

[0119] The super-resolution reconstruction algorithm includes, but is not limited to, a Generative Adversarial Network (GAN) algorithm, a nearest neighbor interpolation algorithm, a linear interpolation algorithm, a bicubic interpolation algorithm, and a spline interpolation algorithm.

[0120] In the embodiment of the application, after obtaining each sub-image in the second processing set, the to-be-tracked target in the target sub-image can be marked by comparing the to-be-tracked target in the current frame with the to-be-tracked target in the previous frame, performing motion calculation and size linear judgment based on the trajectory of the to-be-tracked target in the existing tracking sequence, comparing the to-be-tracked target in the current frame with the to-be-tracked target in each sub-image, and determining the final target sub-image, using the identification of the tracking sequence of the previous frame to mark the to-be-tracked target in the target sub-image, and obtaining a specific identification of the to-be-tracked target in the tracking sequence corresponding to the target sub-image, so as to complete the tracking of the to-be-tracked target in the first image, and complete the tracking of the to-be-tracked target in each image based on the foregoing method, and realize complete and accurate tracking of the to-be-tracked target.

[0121] It should be noted that, in the embodiment of the application, the existing tracking sequence is determined based on the previous N frames of images, and N is a positive integer, which will not be described herein.

[0122] Specifically, the process of determining the target sub-image is introduced below.

[0123] Step 202: Based on the position of the target to be tracked in the previous frame of the first image, the estimated position center point of the target to be tracked in the first image is determined, and the position evaluation value of each sub-image is obtained based on the distance between the position center point of each sub-image and the estimated position center point.

[0124] In an embodiment of the present application, the electronic device can perform the following operations on each sub-image respectively:

[0125] Step a: Determine the first relative distance value between the position point of the target to be tracked in the previous frame and the estimated position center point, and determine the first difference value between the first relative distance value and the second relative distance value; wherein the second relative distance value is the distance value between the position center point of the first sub-image and the position point of the target to be tracked in the previous frame;

[0126] Step b: Determine the region radius of the first region based on the sub-image corresponding to the target to be tracked in the previous frame and the first sub-image, and determine the second difference value between the first difference value and the region radius;

[0127] Step c: Process the second difference value based on an activation function to obtain the position evaluation value of the first sub-image; the activation function is used to map a real number to an interval between 0 and 1.

[0128] In the specific implementation process, please refer to Figure 3 , Figure 3 The schematic diagram for determining the position evaluation value. Among them, "T frame" can be understood as the previous frame image, "T+1 frame" can be understood as the first image, the "triangle" corresponding to "T frame" can be understood as the sub-image containing the target to be tracked in the previous frame image, the "triangle" corresponding to "T+1 frame prediction" can be understood as the predicted sub-image, and the "triangle" corresponding to "T+1 frame real" can be understood as the sub-image in the first image. And, Figure 3 The "C" in the above formula can be understood as the first relative distance value between the position point of the target to be tracked in the previous frame and the estimated position center point; Figure 3 The "Cr" in the above formula can be understood as the second relative distance value between the position center point of the first sub-image and the position point of the target to be tracked in the previous frame; Figure 3 The "r" in the above formula can be understood as the region radius of the target containing the preset threshold.

[0129] Specifically, the first relative distance value can be determined based on the following formula one.

[0130] c = ∫(v + ∫adt)dt; formula one

[0131] wherein v is used to represent the speed of the target to be tracked in the previous frame of image, and a is used to represent the acceleration of the target to be tracked in the previous frame of image.

[0132] And, please see Figure 4 , Figure 4 a schematic diagram for determining the speed and acceleration corresponding to the target to be tracked in the previous frame of image. Wherein, "T frame" can be understood as the previous frame of image, that is, the speed and acceleration corresponding to the target to be tracked can be determined based on the information corresponding to the frame of image before the previous frame of image.

[0133] Specifically, the radius of the region can be determined based on the following formula two:

[0134]

[0135] wherein v is used to represent the speed of the target to be tracked in the previous frame of image, a is used to represent the acceleration of the target to be tracked in the previous frame of image, and c is used to represent the first relative distance value.

[0136] Further, the position evaluation value can be determined based on the following formula three:

[0137]

[0138] wherein v is used to represent the speed of the target to be tracked in the previous frame of image, a is used to represent the acceleration of the target to be tracked in the previous frame of image, dt is used to represent the frame interval, is used to represent the first relative distance value, r is used to represent the radius of the region containing 95% of the target to be tracked, is used to represent the second relative position, Sd is used to represent the position evaluation value, and sigmoid(x) is used to represent the activation function,

[0139] In the embodiment of the present application, after determining the corresponding position evaluation value of each sub-image, the corresponding size evaluation value thereof can also be determined.

[0140] Step 203: based on the size information of the target to be tracked in the previous frame of image, determine the estimated size information of the target to be tracked in the first image, and based on the size information and the estimated size information corresponding to each sub-image respectively, obtain the corresponding size evaluation value.

[0141] In the embodiment of the present application, the electronic device can perform the following operations on each sub-image respectively to determine the size evaluation value corresponding to each sub-image.

[0142] Step 1: determine whether the size information of the second sub-image is within the range of the maximum size information and the minimum size information corresponding to the estimated size information;

[0143] Step 2: If it is determined that the size information of the second sub-image is not within the range of the maximum and minimum size information, then the size evaluation value of the second sub-image is determined to be empty;

[0144] Step 3: When it is determined that the size information of the second sub-image is within the range of the maximum and minimum size information, the size evaluation value of the second sub-image is determined to be the preset value.

[0145] Please see Figure 5 The diagram shown illustrates the determination of the size assessment value in an embodiment of the present invention. In specific implementation, the electronic device can determine the estimated size information of the target in the first image based on the size information of the target in the previous frame image. For example, Figure 5 The "triangle corresponding to frame T" can be understood as the region corresponding to the sub-image of the target to be tracked in the previous frame, and the size information of this region is used as the size information of the target to be tracked. Then, optical flow method can be used to determine the estimated size information of the target to be tracked in the first image based on the size information of the target to be tracked in the previous frame.

[0146] Specifically, the estimated size information can include the maximum size information, i.e. Figure 5 The "maximum bounding box" and minimum size information in the text. Figure 5 The "minimum bounding box" is used in this way. This allows for the determination of the size assessment value based on the comparison between the actual and estimated size information of the sub-image.

[0147] In this embodiment of the invention, when it is determined that the size information of a sub-image is not within the range of the maximum and minimum size information, the size evaluation value of the sub-image is determined to be empty; that is, the sub-image is not within the estimated size range, and therefore it is determined to have no size evaluation value. Conversely, when it is determined that the size information of a sub-image is within the range of the maximum and minimum size information, the size evaluation value of the sub-image is a preset value. The preset value is, for example, 0.1, 0.3, etc., and can be determined based on actual implementation; this embodiment of the invention does not impose any limitations on the preset value.

[0148] Step 204: Based on the obtained position evaluation values ​​and corresponding size evaluation values, determine the corresponding comprehensive evaluation value, and based on the obtained comprehensive evaluation values, filter the target sub-images that meet the filtering conditions and contain the target to be tracked, and update the sub-images contained in the tracking sequence corresponding to the target to be tracked.

[0149] In the embodiment of the present application, the electronic device can sort the obtained comprehensive evaluation values in descending order, and obtain the sorted comprehensive evaluation values; then, the electronic device can perform feature comparison between the sub-images corresponding to the sorted comprehensive evaluation values and the previous frame image of the first image, obtain feature comparison values, and take the sub-image corresponding to the maximum feature comparison value as the target sub-image.

[0150] Please refer to Figure 6 In the embodiment of the present application, the electronic device can perform contrast enhancement processing on the obtained first image to obtain a second image. In this way, the obtained second image is an image with relatively strong contrast, which overcomes the problem of inaccurate subsequent detection caused by low contrast. Then, the moving target in the second image is extracted through a background modeling algorithm to generate a motion foreground image, and the background modeling result, i.e., a plurality of sub-images, is obtained by performing target extraction on the motion foreground image.

[0151] Further, since the high-speed moving target often appears to be trailing, in order to improve the clarity of the target, the sub-image is filtered, i.e., foreground recognition processing and super-resolution recognition processing are performed, to obtain a relatively clear sub-image. Then, the target sub-image is determined based on the estimated information determined by the position and size of the to-be-tracked target in the previous frame image, to generate a real-time tracking sequence of the to-be-tracked target, i.e., to update the existing tracking sequence, so as to realize complete and accurate tracking of the to-be-tracked target.

[0152] Based on the same inventive concept, the embodiment of the present application provides a detection and tracking device capable of realizing the functions corresponding to the detection and tracking method described above. The detection and tracking device can be a hardware structure, a software module, or a hardware structure plus a software module. The detection and tracking device can be realized by a chip system, which can be composed of a chip or can include a chip and other discrete devices. Please refer to Figure 7 As shown in the figure, the detection and tracking device includes a first processing unit 701, a first obtaining unit 702, a second obtaining unit 703, and a tracking unit 704, wherein:

[0153] The first processing unit 701 is configured to perform contrast enhancement processing on the first image to obtain a second image, and perform detection processing on the second image to obtain a plurality of sub-images containing connected domains of dynamic regions;

[0154] The first obtaining unit 702 is configured to determine the estimated position center point of the to-be-tracked target in the first image based on the position of the to-be-tracked target in the previous frame image of the first image, and obtain the corresponding position evaluation value based on the distance between the position center point corresponding to each obtained sub-image and the estimated position center point.

[0155] The second obtaining unit 703 is configured to determine estimated size information of the target to be tracked in the first image based on size information of the target to be tracked in the previous frame image, and obtain a corresponding size evaluation value based on the size information corresponding to each sub-image and the estimated size information.

[0156] The tracking unit 704 is configured to determine a corresponding comprehensive evaluation value based on the obtained position evaluation value and the one-to-one corresponding size evaluation value, and update a sub-image included in a tracking sequence corresponding to the target to be tracked based on the obtained comprehensive evaluation value.

[0157] In a possible implementation, the first processing unit 701 is specifically configured to:

[0158] perform digital image transformation processing on the first image to obtain an HSV (Hue Saturation Value) color model feature map;

[0159] perform feature extraction on the HSV color model feature map to obtain feature pixel values of a preset region;

[0160] perform weighted processing on the first image based on the feature pixel values of the preset region to obtain a second image.

[0161] In a possible implementation, the apparatus further includes a second processing unit, configured to:

[0162] perform foreground recognition processing on the plurality of sub-images respectively to obtain recognition results corresponding to the plurality of sub-images;

[0163] when it is determined that the recognition result of any sub-image is that the sub-image is a full background image, perform deletion processing on the any sub-image to obtain a first processing set.

[0164] In a possible implementation, the second processing unit is further configured to:

[0165] perform super-resolution recognition processing on each sub-image in the first processing set to obtain a resolution recognition result corresponding to each sub-image in the first processing set respectively;

[0166] when it is determined that the resolution of any sub-image in the resolution recognition result is lower than a preset threshold, perform deletion processing on the any sub-image in the first processing set to obtain a second processing set.

[0167] In a possible implementation, the first obtaining unit 702 is specifically configured to:

[0168] The following operations are performed on each sub-image respectively:

[0169] determining a first relative distance value between the position point of the target to be tracked in the previous frame image and the estimated position center point, and determining a first difference value between the first relative distance value and a second relative distance value; wherein the second relative distance value is a distance value between the position center point of the first sub-image and the position point of the target to be tracked in the previous frame image;

[0170] determining a region radius of the first region based on the sub-image corresponding to the target to be tracked in the previous frame image and the first sub-image, and determining a second difference value between the first difference value and the region radius;

[0171] processing the second difference value based on an activation function to obtain a position evaluation value of the first sub-image; the activation function is used to map a real number to an interval between 0 and 1.

[0172] In a possible implementation, the second obtaining unit 703 is specifically configured to:

[0173] The following operations are performed on each sub-image respectively:

[0174] determining whether the size information of the second sub-image is within a range of the maximum size information and the minimum size information corresponding to the estimated size information;

[0175] when it is determined that the size information of the second sub-image is not within the range of the maximum size information and the minimum size information, determining that the size evaluation value of the second sub-image is empty;

[0176] when it is determined that the size information of the second sub-image is within the range of the maximum size information and the minimum size information, determining that the size evaluation value of the second sub-image is a preset value.

[0177] In a possible implementation, the tracking unit 704 is specifically configured to:

[0178] sorting the obtained comprehensive evaluation values in descending order to obtain sorted comprehensive evaluation values;

[0179] performing feature comparison between the sub-image corresponding to each of the sorted comprehensive evaluation values and the previous frame image of the first image to obtain feature comparison values, and taking the sub-image corresponding to the maximum feature comparison value in the feature comparison values as a target sub-image.

[0180] All related contents of the steps involved in the foregoing embodiments of the detection and tracking method can be cited to the function description of the function modules corresponding to the detection and tracking device in the embodiments of the present application, and will not be repeated here.

[0181] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical functional division. In actual implementation, another division manner can be used. In addition, the functional modules in each of the embodiments of the present application can be integrated in a controller, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module.

[0182] Based on the same inventive concept, the embodiments of the present application provide an electronic device, please refer to Figure 8 The electronic device includes at least one processor 801 and a memory 802 connected with the at least one processor. In the embodiments of the present application, the specific connection medium between the processor 801 and the memory 802 is not limited, Figure 8 In the above-mentioned embodiment, the connection between the processor 801 and the memory 802 is taken by way of example through the bus 800, and the bus 800 is indicated by a thick line in Figure 8 The connection mode between other components is only schematically illustrated and is not limited. The bus 800 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 8 In the above-mentioned embodiment, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus. In addition, the detection and tracking device further includes a communication interface 803 for receiving or sending data.

[0183] In the embodiments of the present application, the memory 802 stores instructions executable by the at least one processor 801. The at least one processor 801 can execute the steps included in the above-mentioned detection and tracking method by executing the instructions stored in the memory 802.

[0184] The processor 801 is the control center of the electronic device, and can connect various parts of the electronic device through various interfaces and lines. By running or executing the instructions stored in the memory 802 and calling the data stored in the memory 802, the electronic device can perform various functions and process data, thereby monitoring the whole electronic device.

[0185] Optionally, the processor 801 can include one or more processing units. The processor 801 can integrate an application processor and a modem processor. The application processor mainly processes the operating system, user interface, and application programs, etc. The modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 801. In some embodiments, the processor 801 and the memory 802 can be implemented on the same chip. In some embodiments, they can also be implemented on separate chips respectively.

[0186] The processor 801 can be a general processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present application can be directly embodied as hardware processor execution or executed by a combination of hardware and software modules in the processor.

[0187] The memory 802 is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 802 can include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. The memory 802 is any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory 802 in the embodiments of the present application can also be a circuit or any other device capable of realizing a storage function, used to store program instructions and / or data.

[0188] By designing and programming the processor 801, the code corresponding to the detection and tracking method introduced in the foregoing embodiments can be fixed in the chip, so that the chip can execute the steps of the foregoing detection and tracking method at runtime. How to design and program the processor 801 is a technology known to those skilled in the art, and will not be described here.

[0189] Based on the same inventive concept, the embodiments of the present application also provide a computer readable storage medium, which stores a computer program, when the computer program is executed by a processor to realize the steps of the detection and tracking method as described above.

[0190] In some possible implementation manners, each aspect of the detection tracking method provided by the present application can also be implemented in the form of a program product, which includes program codes for causing a control electronic device to perform the steps of the detection tracking method according to various exemplary embodiments of the present application described above in the specification when the program product is run on the control electronic device.

[0191] Those skilled in the art should understand that embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage, etc.) containing computer-usable program codes.

[0192] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0193] These computer program instructions can also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0194] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the functions specified in the flowcharts and / or block diagrams.

[0195] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method of detecting tracking, characterized by, The method comprises: performing contrast enhancement processing on the first image to obtain a second image; and performing detection processing on the second image to obtain a plurality of sub-images containing dynamic regions; determining an estimated position center point of the target to be tracked in the first image based on the position of the target to be tracked in a previous frame image of the first image, and obtaining a corresponding position evaluation value based on the distance between the position center point of each obtained sub-image and the estimated position center point; determining the estimated size information of the target to be tracked in the first image based on the size information of the target to be tracked in the previous frame image, and obtaining a corresponding size evaluation value based on the size information of each sub-image and the estimated size information; based on the one-to-one correspondence between each position evaluation value and each size evaluation value, determining a corresponding comprehensive evaluation value, and based on each obtained comprehensive evaluation value, screening a target sub-image containing the target to be tracked that meets the screening condition, and updating the sub-images contained in the tracking sequence corresponding to the target to be tracked; wherein, based on the distance between the position center point of each obtained sub-image and the estimated position center point, the corresponding position evaluation value is obtained, comprising: perform the following operations on each sub-image respectively: determine the first relative distance value between the position point of the target to be tracked in the previous frame image and the estimated position center point, and determine the first difference value between the first relative distance value and the second relative distance value; wherein the second relative distance value is the distance value between the position center point of the first sub-image and the position point of the target to be tracked in the previous frame image; determine the region radius of the first region based on the sub-image corresponding to the target to be tracked in the previous frame image and the first sub-image, and determine the second difference value between the first difference value and the region radius; obtain the position evaluation value of the first sub-image based on the second difference value.

2. The method of claim 1, wherein, Performing contrast enhancement processing on the first image to obtain a second image comprises: performing digital image transformation processing on the first image to obtain an HSV color model feature map; performing feature extraction on the HSV color model feature map to obtain feature pixel values of a preset region; based on the feature pixel values of the preset region, performing weighted processing on the first image to obtain a second image.

3. The method of claim 1 or 2, wherein, After obtaining a plurality of sub-images, the method further comprises: performing foreground recognition processing on each of the plurality of sub-images to obtain a recognition result corresponding to each sub-image; when it is determined that the recognition result of any sub-image is that the sub-image is a full background image, performing deletion processing on the any sub-image to obtain a first processing set.

4. The method of claim 3, wherein, After obtaining the first processing set, the method further comprises: performing super-resolution recognition processing on each sub-image in the first processing set to obtain a resolution recognition result corresponding to each sub-image in the first processing set; when it is determined that the resolution of any sub-image corresponding to the resolution recognition result is lower than a preset threshold, performing deletion processing on the any sub-image in the first processing set to obtain a second processing set.

5. The method of claim 1 or 2, wherein, The position evaluation value of each sub-image is obtained based on the distance between the position center point of each obtained sub-image and the estimated position center point. The position evaluation value of the first sub-image is obtained by processing the second difference value based on an activation function, and the activation function is used to map a real number to an interval between 0 and 1.

6. The method of claim 1 or 2, wherein, The size evaluation value of each sub-image is obtained based on the corresponding size information of each obtained sub-image and the estimated size information. The following operations are performed on each sub-image respectively: It is determined whether the size information of the second sub-image is within the range of the maximum size information and the minimum size information corresponding to the estimated size information. When it is determined that the size information of the second sub-image is not within the range of the maximum size information and the minimum size information, it is determined that the size evaluation value of the second sub-image is empty. When it is determined that the size information of the second sub-image is within the range of the maximum size information and the minimum size information, it is determined that the size evaluation value of the second sub-image is a preset value.

7. The method of claim 1 or 2, wherein, The target sub-image meeting the screening condition is screened based on the obtained comprehensive evaluation values, including: The obtained comprehensive evaluation values are sorted in descending order to obtain sorted comprehensive evaluation values. The sub-image corresponding to the maximum feature comparison value in the feature comparison values is taken as the target sub-image by performing feature comparison between the sub-image corresponding to the sorted comprehensive evaluation value and the previous frame image of the first image.

8. A detection tracking device, characterized by, The device includes: The first processing unit is configured to perform contrast enhancement processing on the first image to obtain a second image, and perform detection processing on the second image to obtain a plurality of sub-images containing connected domains of dynamic regions. The first obtaining unit is configured to determine an estimated position center point of the target to be tracked in the first image based on the position of the target to be tracked in the previous frame image of the first image, and obtain a position evaluation value corresponding to each sub-image based on the distance between the position center point of each obtained sub-image and the estimated position center point. The second obtaining unit is configured to determine an estimated size information of the target to be tracked in the first image based on the size information of the target to be tracked in the previous frame image, and obtain a size evaluation value corresponding to each sub-image based on the size information corresponding to each sub-image and the estimated size information. The tracking unit is configured to determine a corresponding comprehensive evaluation value based on the obtained position evaluation values and one-to-one corresponding size evaluation values, screen a target sub-image containing the target to be tracked meeting the screening condition based on the obtained comprehensive evaluation values, and update the sub-images contained in the tracking sequence corresponding to the target to be tracked. The first obtaining unit is specifically configured to: respectively performing the following operations on each sub-image: determining a first relative distance value between a position point of the to-be-tracked target in the previous frame image and a predicted position center point, and determining a first difference value between the first relative distance value and a second relative distance value; the second relative distance value is a distance value between the position center point of the first sub-image and the position point of the to-be-tracked target in the previous frame image; determining a region radius of a first region based on the sub-image corresponding to the to-be-tracked target in the previous frame image and the first sub-image, and determining a second difference value between the first difference value and the region radius; obtaining a position evaluation value of the first sub-image based on the second difference value.

9. An electronic device, comprising: The electronic device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program, when executed by the processor, implements the steps of the detection tracking method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the steps of the detection tracking method according to any one of claims 1 to 7.

Images