A method, apparatus and electronic device for determining a focus region

Abstract

The application relates to a method, device and electronic equipment for determining a focusing area. The method comprises the following steps: obtaining m sub-areas based on a panoramic image; detecting each moving target in the m sub-areas; determining a motion state value of each moving target, sorting each moving target according to the size of the motion state value of each moving target to obtain a regular target with a motion state value; and selecting a preset number of moving targets from all the regular targets as preferred targets, and observing and focusing on an area corresponding to the preferred targets as a target area. Based on the above method, the selection of the focusing area of a motion field can be optimized, real-time positioning can be realized, positioning delay can be reduced, and user experience can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer vision, and in particular to a method and device for determining a focus area and an electronic device. BACKGROUND

[0002] In various sports games such as football, basketball and volleyball, the physical data of players, such as the moving distance and speed of players and the moving distance and speed of balls in the court, play an important role in the data analysis of players. In order to obtain the moving distance and speed of players and the moving distance and speed of balls in the court, the positioning of players and balls at any moment in the court needs to be obtained, so the court focus positioning is very important.

[0003] For the existing court focus point algorithm, the commonly used methods include GPS (Global Positioning System) physical positioning and manual positioning, and ball visual positioning. These methods update the position of the tracked target in real time, obtain the real-time focus area of the court, and position the focus area. However, these methods have several disadvantages. First, since the ball target is small, it is difficult to track and detect it in real time. Second, GPS has a delay, which causes a tracking lag problem. Third, the manual positioning method is very troublesome and requires high quality of the personnel. SUMMARY

[0004] The present application provides a method and device for determining a focus area and an electronic device to optimize the selection of the focus area of the sports field, realize real-time positioning, reduce positioning delay, and improve user experience.

[0005] In a first aspect, the present application provides a method for determining a focus area, the method comprising:

[0006] obtaining m sub-areas based on a panoramic image, wherein m is an integer greater than 1, and the sub-areas contain sports targets;

[0007] detecting each sports target in the m sub-areas;

[0008] determining the motion state value of each sports target, sorting the each sports target according to the size of the motion state value of the each sports target to obtain a regular target with a motion state value;

[0009] selecting a preset number of sports targets from all regular targets as preferred targets, and observing and focusing on the area corresponding to the preferred targets as a target area.

[0010] In a possible design, the obtaining the m sub-regions based on the panoramic image includes: dividing the panoramic image into respective foreground regions containing moving targets by using a background modeling algorithm; performing fusion processing on two foreground regions when a distance between the two foreground regions is less than a preset distance; and obtaining the m sub-regions after the respective foreground regions are subjected to the fusion processing.

[0011] In a possible design, the detecting each moving target in the m sub-regions includes: performing moving target detection on the m sub-regions by using a detection algorithm; performing deduplication processing on repeated moving targets when the repeated moving targets are detected in the m sub-regions, to obtain the each moving target that is not repeated; and performing tracking and position calibration on the each moving target by using a tracking algorithm, and assigning an identifier to the each moving target.

[0012] In a possible design, the determining the motion state value of each moving target includes: calculating respective average displacements c a and average speeds v a of the each moving target in N frames, where N is an integer greater than 1; and calculating the motion state value of the each moving target based on the average displacement c a and the average speed v a .

[0013] In a possible design, the calculating the motion state value of the each moving target based on the average displacement c a and the average speed v a includes: subtracting a negative average speed v a raised to a power of a natural logarithm from an average displacement c a , to obtain the motion state value of the each moving target.

[0014] In a possible design, the focusing observation on the target region corresponding to the preferred target includes: obtaining a current frame region corresponding to the preferred target, a center point coordinate cn of the current frame region, a previous frame region corresponding to the preferred target, and a center point coordinate cb of the previous frame region; performing smoothing processing on the current frame region and the previous frame region, to calculate a center point displacement c and a width-height change rate r; and obtaining the target region by using the center point displacement c and the width-height change rate r, and focusing observation on the target region.

[0015] In a possible design, the smoothing processing of the current frame region and the previous frame region to calculate the center point displacement c and the width-height change rate r includes: obtaining a center point coordinate absolute value function of a center point coordinate cb of the previous frame region and a center point coordinate cn of the current frame region, and a width absolute value function of a width wb of the previous frame region and a width wn of the current frame region; performing minimum value solving on the center point coordinate absolute value function and one tenth of the width wb of the previous frame region to obtain the center point displacement c; and performing minimum value solving on the width absolute value function and one tenth of the width wb of the previous frame region to obtain the width-height change rate r.

[0016] In summary, the method divides the panoramic image region into a plurality of sub-regions to complete small target detection of a super large image; detects motion targets in the sub-regions, removes motion targets in overlapping regions, and then performs motion target tracking and assigns an identifier to each motion target; calculates the displacement and speed of each motion target, determines the motion state of each motion target, and thereby obtains regular targets; selects certain targets from the regular targets, obtains the current frame region and the previous frame region corresponding to the targets, performs smoothing processing on the current frame region and the previous frame region, and finally obtains a target region for observation focusing. The method is widely used in various scenes, simple to use, can save human resources, and can realize real-time positioning, reduce positioning delay, and improve user experience through smoothing processing of the focusing region.

[0017] In a second aspect, the present application provides a device for determining a focusing region, the device comprising:

[0018] an acquisition module configured to acquire m sub-regions based on a panoramic image, wherein m is an integer greater than 1, and the sub-regions contain motion targets;

[0019] a detection module configured to detect each motion target in the m sub-regions;

[0020] a determination module configured to determine a motion state value of each motion target, and sort the motion targets according to the size of the motion state value to obtain regular targets with motion state values;

[0021] a screening module configured to screen a preset number of motion targets from all the regular targets as preferred targets, and perform observation focusing on a target region corresponding to the preferred targets.

[0022] In a possible design, the acquisition module is specifically configured to divide the panoramic image into individual foreground regions containing moving targets by using a background modeling algorithm; perform fusion processing on two foreground regions when a distance between the two foreground regions is less than a preset distance; and obtain the m sub-regions after the fusion processing on the individual foreground regions.

[0023] In a possible design, the detection module is specifically configured to perform moving target detection on the m sub-regions by using a detection algorithm; perform deduplication processing on repeated moving targets when the repeated moving targets are detected in the m sub-regions, to obtain non-repeated each moving target; and perform tracking and location calibration on each moving target by using a tracking algorithm, and assign an identifier to each moving target.

[0024] In a possible design, the determination module is specifically configured to calculate an average displacement c a and an average speed v a of each moving target in N frames, where N is an integer greater than 1; and calculate a motion state value of each moving target based on the average displacement c a and the average speed v a .

[0025] In a possible design, the determination module is further configured to obtain the motion state value of each moving target by subtracting a negative average speed v a from an average displacement c a .

[0026] In a possible design, the screening module is specifically configured to acquire a current frame region corresponding to the preferred target, a center point coordinate cn of the current frame region, a previous frame region corresponding to the preferred target, and a center point coordinate cb of the previous frame region; perform smoothing processing on the current frame region and the previous frame region, to calculate a center point displacement c and a width-height change rate r; and obtain the target region by using the center point displacement c and the width-height change rate r, and perform observation focusing on the target region.

[0027] In a possible design, the screening module is further configured to obtain a center point coordinate absolute value function of the center point coordinate cb of the previous frame region and the center point coordinate cn of the current frame region, and a width absolute value function of a width wb of the previous frame region and a width wn of the current frame region; perform minimum value solving on the center point coordinate absolute value function and one tenth of the width wb of the previous frame region, to obtain the center point displacement c; and perform minimum value solving on the width absolute value function and one tenth of the width wb of the previous frame region, to obtain the width-height change rate r.

[0028] Through the above device, the selection of the focusing area of the sports field can be optimized, real-time positioning can be realized, and positioning delay can be reduced. In addition, the focusing area is processed through smoothing, which can improve the user's visual experience.

[0029] In a third aspect, the present application provides an electronic device, comprising:

[0030] a memory for storing a computer program;

[0031] a processor for executing the computer program stored on the memory to realize the method steps of determining the focusing area.

[0032] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the method steps of determining the focusing area.

[0033] The technical effects of each aspect and each aspect that can be achieved in the above second aspect to fourth aspect can refer to the technical effect description of the first aspect or the various possible schemes in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 a flowchart of the method for determining the focusing area provided by the present application;

[0035] Figure 2 a schematic diagram of a possible application scenario provided by the present application;

[0036] Figure 3 a schematic diagram of the device for determining the focusing area provided by the present application;

[0037] Figure 4 a schematic diagram of the structure of the electronic device provided by the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The specific operation method in the method embodiment can also be applied to the device embodiment or system embodiment, and the computer program product.

[0039] In the description of the present application, "multiple" is understood as "at least two". The association relationship of "and / or" describing the associated objects means that there can be three relationships, for example, A and / or B can represent the three cases of A existing alone, A and B existing together, and B existing alone. A is connected with B, which can represent two cases: A is directly connected with B and A is connected with B through C. In addition, in the description of the present application, "first", "second", and the like are used only for the purpose of distinguishing the description, and cannot be understood as indicating or implying relative importance, nor indicating or implying order.

[0040] In addition, the technical features contained in the embodiments of the present application can be arbitrarily combined, and those skilled in the art should understand that the technical solutions obtained by reasonably combining the technical features in the embodiments of the present application can also solve the same technical problems or achieve the same technical effects.

[0041] The method provided by the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0042] Referring to Figure 1 As shown in the drawings, the embodiments of the present application provide a method for determining a focusing area, which can be used in a region optimization system for focusing on athletes in a sports field. The system includes four modules, namely: a dynamic region extraction module, a dynamic target detection module, a target motion state determination module, and a region optimization module. The specific process of the method is as follows:

[0043] Step 101: Based on the panoramic image, m sub-regions are obtained;

[0044] In the embodiments of the present application, m is an integer greater than 1, and the sub-region contains a moving target. The moving target can be, but is not limited to, an athlete.

[0045] Specifically, the panoramic image of the sports field is collected by an image collector, and the collected panoramic image is divided into each foreground region containing a moving target by a background modeling algorithm. In the embodiments of the present application, each foreground region can include one or more moving targets. The background modeling algorithm can include, but is not limited to, BGModel (background model) algorithm, GMM (Gaussian mixture model) algorithm, ViBE (foreground detection) algorithm, and ABM (Agent-based modeling, individual-based modeling) algorithm.

[0046] After obtaining each foreground region, distances between each foreground region are compared, which can be distances between outer contours of each foreground region or distances between center points of each foreground region. When the distance between two foreground regions is less than a preset distance, for example, the distance between the outer contours of the two foreground regions is less than 2 m, or the distance between the center points of the two foreground regions is less than 6 m, the two foreground regions are fused. In the embodiments of the present application, the fusion scheme can include but is not limited to image erosion and image dilation.

[0047] After each foreground region that meets the fusion processing condition is fused, m sub-regions are obtained.

[0048] The division of the panoramic image and the fusion of the foreground regions described above can be realized by a dynamic region extraction module. After m sub-regions are obtained, the following step 102 can be executed by a moving target detection module.

[0049] Step 102: detecting each moving target in the m sub-regions;

[0050] Specifically, the m sub-regions obtained are scaled to a uniform size, and a detection algorithm is used to detect moving targets in the m sub-regions. In the embodiments of the present application, the detection algorithm can include but is not limited to R-CNN (Region-CNN, a target detection algorithm based on a convolutional neural network), SSD (Single Shot MultiBox Detector, a multi-frame prediction target detection algorithm), YOLO v1 (a single-stage target detection algorithm), YOLO v2, and YOLO v3.

[0051] When repeated moving targets are detected in the m sub-regions, the repeated moving targets are de-duplicated to obtain each non-repeated moving target. In the embodiments of the present application, the de-duplication algorithm used for de-duplication can include but is not limited to NMS algorithm and SOFT-NMS algorithm. Specifically, after the m sub-regions are de-duplicated by the de-duplication algorithm, the generated results include but are not limited to target frame, target category, and target score. The target frame is an image outer frame that locks the moving target; the target category is the category of the detected moving target, for example, the moving target is a person or a motor vehicle or an animal; and the target score is the category score of the detected moving target, for example, the score of the moving target as a person is 70%, the score of the moving target as a motor vehicle is 10%, and the score of the moving target as an animal is 20%. According to the overlap state, the target category, and the target score, the moving targets that are suspected to overlap are de-duplicated.

[0052] After deduplication, each unique moving target is obtained. A tracking algorithm is then used to track each moving target, and the appearance and motion information of each target are modeled to predict its motion state and pinpoint its position. Each target is also assigned an ID identifier. In this embodiment, the tracking algorithm may include, but is not limited to, optical flow and Kalman filtering.

[0053] After tracking and calibrating each detected moving target, the following step 103 can be performed through the target motion state determination module.

[0054] Step 103: Determine the motion state value of each moving target, sort each moving target according to the magnitude of its motion state value, and obtain a regularized target with motion state values;

[0055] Specifically, based on the ID of the moving target, the current frame state and previous frame state of the moving target with the same ID are obtained, and the displacement *c* and velocity *v* of the current frame are calculated. By analyzing the displacement and velocity changes of each moving target within N frames (where N is an integer greater than 1), the average displacement *c* of each moving target within N frames is calculated. a and average velocity v a .

[0056] In the embodiments of this application, the specific process of analyzing the displacement and velocity changes of each moving target can be referred to Figure 2 ,like Figure 2 As shown, s represents displacement length, v represents velocity, a represents acceleration, and T represents the interval length of each frame. Where v0 = (s1 - s0) / T, v1 = (s2 - s1) / T, and a0 = (v1 - v0) / T.

[0057] After obtaining the average displacement c of each moving target within N frames... a and average velocity v a Then, based on the average displacement c a and average velocity v a The motion state value S of each moving target is calculated. Specifically, this is achieved through the average displacement c. a Subtract the negative average velocity v from the natural logarithm a The power is used to obtain the motion state value of each moving target. The specific calculation formula is as follows:

[0058]

[0059] After calculating the motion state value S of each moving target, a sorting algorithm is used to sort each moving target according to the magnitude of its motion state value, resulting in sorted moving targets with motion state values, which are then used as regularized targets.

[0060] Step 104: Selecting a preset number of moving targets from all the regularized targets as preferred targets, and taking the area corresponding to the preferred targets as a target area for observation focus.

[0061] In the embodiments of the present application, the area preferred module can be used to select the regularized targets to determine the target area that needs to be focused.

[0062] Specifically, a preset number of moving targets are selected from the regularized targets obtained in step 103 as preferred targets. For example, according to the golden section principle, the first 61.8% of the moving targets are selected as preferred targets.

[0063] According to the selected preferred targets, the area corresponding to the outer contour of the preferred targets is obtained as a target area. It should be noted that the shape of the outer contour of the area can be rectangular, circular, or the like, and the shape is not specifically limited. According to the shape of the outer contour of the area, the center point coordinates of the area are obtained. If the area is rectangular, the center point is the intersection point of the diagonal lines of the rectangle. If the area is circular, the center point is the center of the circle. The center point coordinates of the area are controlled to keep the area size unchanged, and the width and height are adjusted to a preset ratio, such as a 4:3 ratio.

[0064] The current frame area corresponding to the preferred target after the above-mentioned ratio adjustment is obtained, the center point coordinates cn of the current frame area, and the last frame area corresponding to the preferred target, the center point coordinates cb of the last frame area. The current frame area and the last frame area are smoothed to calculate the center point displacement c and the width and height change rate r. Specifically, the center point coordinate absolute value function of the center point coordinates cb of the last frame area and the center point coordinates cn of the current frame area, and the width absolute value function of the width wb of the last frame area and the width wn of the current frame area are obtained. The center point coordinate absolute value function and one-tenth of the width wb of the last frame area are solved by the minimum value to obtain the center point displacement c. The width absolute value function and one-tenth of the width wb of the last frame area are solved by the minimum value to obtain the width and height change rate r. The specific calculation formula is as follows:

[0065] c = MIN(wb / 10, abs(cb-cn)),

[0066] r = MIN(wb / 10, abs(wb-wn)),

[0067] wherein wb is the width of the last frame area, wn is the width of the current frame area, abs is the absolute value function, and MIN is the minimum value function.

[0068] After the center point displacement c and the width-height change rate r are obtained, the target region can be obtained according to the center point displacement c and the width-height change rate r, and the target region is observed and focused.

[0069] In summary, the method for determining a focusing region provided in the application divides the panoramic image region into multiple sub-regions through a dynamic region extraction module to complete small target detection of a super large image; a dynamic target detection module is used to detect the motion target of the sub-regions, remove the motion target of the overlapping region, then perform motion target tracking, and assign an id to each motion target; a target motion state judgment module is used to calculate the mean value of displacement, speed, etc. and judge the motion state of each motion target to obtain a regular target; a region optimization module is used to select a certain target from the regular target, obtain the current frame region and the previous frame region corresponding to the target, and perform smoothing processing on the current frame region and the previous frame region to finally obtain the target region for observation and focusing. This method is widely used in various scenes, is simple to use, can save human resources, and can realize real-time positioning, reduce positioning delay, and improve user experience through smoothing processing of the focusing region.

[0070] Based on the same inventive concept, the application further provides a device for determining a focusing region to optimize the selection of a motion field focusing region, realize real-time positioning, reduce positioning delay, and improve user experience, as described in Figure 3 The device comprises:

[0071] An acquisition module 301 obtains m sub-regions based on a panoramic image, wherein m is an integer greater than 1, and the sub-regions contain motion targets;

[0072] A detection module 302 detects each motion target in the m sub-regions;

[0073] A determination module 303 determines the motion state value of each motion target, sorts each motion target according to the size of the motion state value of each motion target, and obtains a regular target with a motion state value;

[0074] A screening module 304 screens a preset number of motion targets from all regular targets as preferred targets, and performs observation and focusing on the region corresponding to the preferred target as a target region.

[0075] In a possible design, the acquisition module 301 is specifically configured to divide the panoramic image into various foreground regions containing motion targets through a background modeling algorithm; when the distance between two foreground regions is less than a preset distance, the two foreground regions are fused; and the m sub-regions are obtained after the fusion processing of the various foreground regions.

[0076] In a possible design, the detection module 302 is specifically configured to perform motion target detection on the m sub-regions by using a detection algorithm; when repeated motion targets are detected in the m sub-regions, the repeated motion targets are removed to obtain non-repeated motion targets; and the tracking algorithm is used to track and position the non-repeated motion targets, and the non-repeated motion targets are assigned with identifiers.

[0077] In a possible design, the determination module 303 is specifically configured to calculate the average displacement c a and the average speed v a of each motion target in N frames, where N is an integer greater than 1; and calculate the motion state value of each motion target based on the average displacement c a and the average speed v a .

[0078] In a possible design, the determination module 303 is further configured to obtain the motion state value of each motion target by subtracting the average displacement c a from the natural logarithm of the average speed v a .

[0079] In a possible design, the screening module 304 is specifically configured to obtain a current frame region corresponding to the preferred target, a center point coordinate cn of the current frame region, a previous frame region corresponding to the preferred target, and a center point coordinate cb of the previous frame region; perform smoothing processing on the current frame region and the previous frame region to calculate a center point displacement c and a width-height change rate r; and obtain the target region by using the center point displacement c and the width-height change rate r, and focus on observing the target region.

[0080] In a possible design, the screening module 304 is further configured to obtain a center point coordinate absolute value function of the center point coordinate cb of the previous frame region and the center point coordinate cn of the current frame region, and a width absolute value function of a width wb of the previous frame region and a width wn of the current frame region; perform minimum value solving on the center point coordinate absolute value function and one tenth of the width wb of the previous frame region to obtain the center point displacement c; and perform minimum value solving on the width absolute value function and one tenth of the width wb of the previous frame region to obtain the width-height change rate r.

[0081] By using the above apparatus, the selection of the focus region of the motion field can be optimized, real-time positioning can be implemented, positioning delay can be reduced, and the focus region can be improved by using smoothing processing, thereby improving the user experience.

[0082] Based on the same inventive concept, the embodiment of the present application further provides an electronic device, which can realize the functions of the foregoing device for determining a focus area, and the device is configured to Figure 4 , and the electronic device comprises:

[0083] at least one processor 401 and a memory 402 connected with the at least one processor 401, and the specific connection medium between the processor 401 and the memory 402 is not limited in the embodiment of the present application, Figure 4 In the embodiment, the connection between the processor 401 and the memory 402 is taken as an example of connection through a bus 400. The bus 400 is used to connect Figure 4 other components in the embodiment, and the connection mode between other components is only schematically illustrated and is not limited. The bus 400 can be divided into an address bus, a data bus, a control bus and the like, and for the convenience of representation, Figure 4 In the 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. Alternatively, the processor 401 can also be referred to as a controller, and the name is not limited.

[0084] In the embodiment of the present application, the memory 402 stores instructions executable by the at least one processor 401, and the at least one processor 401 can execute the method for determining a focus area discussed above by executing the instructions stored in the memory 402. The processor 401 can realize the functions of various modules in the device as shown in Figure 3 .

[0085] The processor 401 is the control center of the device, can utilize various interfaces and lines to connect various parts of the entire control device, and through running or executing instructions stored in the memory 402 and calling data stored in the memory 402, the device can process various functions and data, thereby monitoring the device as a whole.

[0086] In a possible design, the processor 401 can include one or more processing units, and the processor 401 can integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program and the like, and the modem processor mainly processes wireless communication. It can be understood that the foregoing modem processor can also not be integrated into the processor 401. In some embodiments, the processor 401 and the memory 402 can be realized on the same chip, and in some embodiments, they can also be realized on independent chips respectively.

[0087] The processor 401 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 method for determining a focus area disclosed in the embodiments of the present application can be directly embodied as execution completed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0088] The memory 402 is a non-volatile computer readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 402 can include at least one type of storage medium, such as flash memory, a hard disk, a multimedia card, a 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), a magnetic storage, a magnetic disk, an optical disk, and the like. The memory 402 can be any other medium capable of carrying or storing desired program codes in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory 402 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.

[0089] By designing and programming the processor 401, the codes corresponding to the method for determining a focus area introduced in the foregoing embodiments can be fixed into the chip, so that the chip can execute the steps of the method for determining a focus area of the embodiments shown in the running time. Figure 1 How to design and program the processor 401 is a technology known to those skilled in the art, which will not be described here.

[0090] Based on the same inventive concept, the embodiments of the present application also provide a storage medium storing computer instructions, when the computer instructions run on a computer, the computer executes the method for determining a focus area discussed above.

[0091] In some possible implementation, each of the aspects of the method for determining the focusing area provided in the present application can also be implemented in the form of a program product, which includes program codes for causing the control device to perform the steps of the method for determining the focusing area according to various exemplary embodiments of the present application described above in the specification when the program product is run on the device.

[0092] Those skilled in the art should understand that the embodiments of the present application can be provided in the form of 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, CD-ROMs, optical storage devices, etc.) containing computer-usable program codes.

[0093] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as a 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 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct the 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 manufactured product including instruction means, which implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0095] These computer program instructions can also be loaded onto 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 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0096] 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 determining a focus area, characterized by, The method is used for a region preference system of focusing on athletes in a sports field, the region preference system comprising a dynamic region extraction module, a dynamic target detection module, a target motion state determination module and a region preference module, the method comprising: dividing, by the dynamic region extraction module, a panoramic image collected into each foreground region containing a motion target through a background modeling algorithm, and obtaining m sub-regions after each foreground region meeting a fusion processing condition is subjected to fusion processing; wherein m is an integer greater than 1, and the sub-regions contain motion targets; detecting each motion target in the m sub-regions by the motion target detection module; determining a motion state value of each motion target by the target motion state determination module, and sorting each motion target according to the size of the motion state value of each motion target to obtain a regular target with a motion state value; selecting a preset number of motion targets from all regular targets as preferred targets by the region preference module, and observing and focusing on a region corresponding to the outer contour of the preferred targets as a target region.

2. The method of claim 1, wherein, The method further comprises: when the distance between two foreground regions is less than a preset distance, the two foreground regions are subjected to fusion processing; after the fusion processing of each foreground region, the m sub-regions are obtained.

3. The method of claim 1, wherein, The method further comprises: using a detection algorithm to detect motion targets in the m sub-regions; when repeated motion targets are detected in the m sub-regions, the repeated motion targets are subjected to de-duplication processing to obtain each motion target without repetition; tracking and position calibration of each motion target are performed by a tracking algorithm, and each motion target is assigned an identifier.

4. The method of claim 1, wherein, The method further comprises: calculating the average displacement c of each of the moving objects in N frames a and the average velocity v a wherein N is an integer greater than 1; Based on the average displacement c a and the average velocity v a , the motion state value of each moving object is calculated.

5. The method of claim 4, wherein, The average displacement c a And the average speed v a The motion state value of each moving target is calculated, including: By averaging the displacement c a Subtracting the natural logarithm of the negative average velocity v a Power, the motion state value of each moving target is obtained.

6. The method of claim 1, wherein, The method further comprises: obtaining a current frame region corresponding to the preferred target, a center point coordinate cn of the current frame region, a previous frame region corresponding to the preferred target, and a center point coordinate cb of the previous frame region; smoothly processing the current frame region and the previous frame region to calculate a center point displacement c and a width-height change rate r; the target region is obtained through the center point displacement c and the width-height change rate r, and the target region is observed and focused on.

7. The method of claim 6, wherein, The method further comprises: obtaining a center point coordinate absolute value function of the center point coordinate cb of the previous frame region and the center point coordinate cn of the current frame region, and a width absolute value function of the width wb of the previous frame region and the width wn of the current frame region; the center point displacement c is obtained by solving the minimum value of the center point coordinate absolute value function and one-tenth of the width wb of the previous frame region; and The wide absolute value function and the tenth of the wide wb of the last frame region are solved by minimum value to obtain the width-height change rate r.

8. An apparatus for determining a focus area, the apparatus comprising: The device comprises: An acquisition module divides the panoramic image collected through a background modeling algorithm into each foreground region containing a moving target, and performs fusion processing on each foreground region meeting the fusion processing condition to obtain m sub-regions; wherein m is an integer greater than 1, and the sub-regions contain moving targets; A detection module detects each moving target in the m sub-regions; A determination module determines the motion state value of each moving target, sorts each moving target according to the size of the motion state value of each moving target to obtain a regular target with a motion state value; A screening module screens a preset number of moving targets from all regular targets as preferred targets, and observes and focuses on a region corresponding to the outer contour of the preferred target as a target region.

9. An electronic device, comprising: Comprise: A memory for storing a computer program; A processor for executing the computer program stored on the memory to implement the method steps of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer program is stored in the computer readable storage medium, and the computer program is executed by the processor to implement the method steps of any one of claims 1-7.

Images