A ski resort target image generation method, system and server

Abstract

The present application discloses a method, system and server for generating target images of a ski resort, the method comprising acquiring a full-time initial image through a first shooting device; generating identification features of the shooting target based on the full-time initial image, the identification features including at least one of shape features, color features and additional features; constructing a target feature library based on the identification features corresponding to multiple shooting targets; shooting the skiing process of the shooting target in real time through a shooting and editing device, and acquiring a first video containing the editing target in real time, the editing target being one of the multiple shooting targets; detecting each shooting target in the first video through a classifier based on the identification features in the target feature library; and generating a second video corresponding to the editing target in chronological order. The present application provides a method for accurately completing the shooting and automatic editing of the skiing process of a skier, which can prevent the phenomenon of losing the target, eliminate the problem of multi-target interference, and improve the robustness of recognition.

Description

Technical Field

[0001] The present application generally relates to the field of automatic photography technology, and specifically to a method, system and server for generating a target image of a ski resort. Background Art

[0002] With the development of technology, in indoor ski resorts, skiers often want to record the entire skiing process. With the improvement of the automation level of the video acquisition system, the cameras currently used for monitoring in ski resorts are all fixedly installed, and it is already possible to simply shoot and save the movement process of dynamic people.

[0003] However, due to the particularity of skiing, skiers use gloves, masks, helmets and other equipment to block the target, which reduces the recognition accuracy and has poor anti-interference ability. In addition, in ski resorts, uniform clothing is generally provided, which makes it more difficult to recognize features. In the specific implementation, there is also interference caused by multiple targets.

[0004] Therefore, how to eliminate the interference of automatic photography in ski resorts becomes an urgent problem to be solved. Summary of the invention

[0005] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, system and server for generating target images of a ski resort, which can realize target shooting and editing of the ski resort and improve the anti-interference ability.

[0006] In a first aspect, the present application provides a method for generating a target image of a ski resort by shooting the target image, comprising:

[0007] After receiving the shooting instruction, obtaining a full-time initial image including a plurality of shooting targets through a first shooting device;

[0008] generating an identification feature of the photographed target based on the full-time initial image, wherein the identification feature includes at least one of a shape feature, a color feature and an additional feature;

[0009] Building a target feature library based on the identification features corresponding to the plurality of photographed targets;

[0010] The skiing process of the shooting target is shot in real time by shooting and editing equipment, and a first video containing the editing target is obtained in real time, where the editing target is one of the multiple shooting targets;

[0011] Based on the identification features in the target feature library, detecting each of the shooting targets in the first video by a classifier;

[0012] Based on the first video, a second video corresponding to the editing target is generated in chronological order.

[0013] Further, the detecting each of the shooting targets in the first video image by a classifier based on the identification features in the target feature library includes:

[0014] Using a classifier to detect the shooting target on the image frames in the first video, to obtain a detection result of the shooting target;

[0015] According to the detection result of the shooting target, a rectangular frame is allocated to each shooting target;

[0016] The image frames in the first video are acquired in real time, and a plurality of shooting targets are shot simultaneously through a rectangular frame corresponding to each shooting target.

[0017] Further, the using a classifier to detect the photographed target on the image frames in the first video to obtain the detection result of the photographed target includes:

[0018] Extracting features of the current frame image in the first video to obtain several groups of image feature parameters;

[0019] Determine, by a classifier, whether the image feature parameter belongs to a matching coefficient of any identification feature in the target feature library;

[0020] Determining whether one of the matching coefficients is greater than a first set threshold;

[0021] If there is one of the matching coefficients that is greater than the first set threshold, marking the detection result of the image feature parameter corresponding to the matching coefficient as the photographed target corresponding to the identification feature;

[0022] If none of the matching coefficients is greater than the first set threshold, the detection result of the image feature parameter corresponding to the matching coefficient is marked as unmatched.

[0023] Furthermore, the method further comprises:

[0024] Calculating similarity between the unmatched image feature parameters and a rectangular frame of a target corresponding to a previous frame of the first video;

[0025] If the similarity is greater than a second set threshold, the detection result of the image feature parameter is marked as the shooting target corresponding to the rectangular frame.

[0026] Furthermore, the method further comprises:

[0027] After receiving the shooting instruction, obtaining the bird's-eye view characteristics of the shooting target through the second shooting device;

[0028] Based on the bird's-eye view editing device, real-time shooting of the position corresponding to the shooting and editing device is performed from a bird's-eye view perspective, and a third video containing a plurality of the shooting targets is obtained in real time;

[0029] Based on the bird's-eye view feature, detecting each of the shooting targets in the third video by a classifier;

[0030] According to the shooting target in the third video, the shooting target corresponding to the image feature parameters that are not matched in the first video is obtained.

[0031] Furthermore, the method further comprises:

[0032] Preset a plurality of shooting and editing devices to shoot the skiing process of the editing target in sections;

[0033] Determining whether the editing target leaves the shooting field of view of the corresponding shooting and editing device;

[0034] If it leaves, the corresponding shooting and editing equipment is stopped to detect the editing target that leaves the field of view.

[0035] Furthermore, the step of generating a second video corresponding to a single shooting target in chronological order includes:

[0036] In real time, intercepting a second video frame including the clipping target from each frame of the first video frame;

[0037] The captured second video frames are formed into a continuous second video.

[0038] Furthermore, the method comprises:

[0039] generating motion features of the photographed target through the second video, and constructing a motion feature library of the photographed target based on the motion features;

[0040] The respective shooting targets in the first video are detected by combining the established motion feature library of the shooting targets and the identification features in the target feature library.

[0041] In a second aspect, the present application provides a ski resort target image generation system for executing any of the above methods, the system comprising:

[0042] A first photographing device is arranged at the entrance of the ski resort, and is used to obtain identification features of a photographing target after receiving a photographing instruction;

[0043] A second shooting device, configured to obtain a bird's-eye view feature of a shooting target after receiving the shooting instruction;

[0044] A plurality of bird's-eye view editing devices, used for identifying a shooting target for the acquired third video based on the bird's-eye view perspective features corresponding to the shooting target;

[0045] A plurality of shooting and editing devices are used to shoot the shooting target based on the identification features corresponding to the shooting target and generate a second image of the editing target.

[0046] In a third aspect, the present application provides a server for executing any of the methods described above.

[0047] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0048] The ski resort target image generation method provided in the embodiment of the present application recognizes the shooting target through the first shooting device and establishes a real-time target feature library, which facilitates the recognition of the shooting target during the shooting and editing process; obtains the bird's-eye view feature through the second shooting device, and assists in the recognition during the shooting and editing process through the bird's-eye view editing device. The present application can accurately complete the shooting and automatic editing of the entire skiing process of the skier, which can prevent the phenomenon of losing the target, eliminate the problem of multi-target interference, and improve the robustness of recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0050] Figure 1 A flowchart of a method for generating a target image of a ski resort provided in an embodiment of the present application;

[0051] Figure 2 A flowchart of a method for detecting each of the shooting targets in a first video image provided by an embodiment of the present application;

[0052] Figure 3 A flowchart of a method for obtaining a detection result of the photographed target provided in an embodiment of the present application;

[0053] Figure 4 A flowchart of a processing method provided for an embodiment of the present application;

[0054] Figure 5 A flowchart of another processing method provided for an embodiment of the present application;

[0055] Figure 6 A schematic diagram of the arrangement of a ski resort target image generation system provided in an embodiment of the present application;

[0056] Figure 7A schematic diagram of the structure of a computer system suitable for implementing a server of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0058] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0059] Please see Figure 1 , the present application provides a method for generating a ski resort target image, comprising:

[0060] S02. After receiving the shooting instruction, a full-time initial image of the shooting target is obtained through a first shooting device.

[0061] In the embodiment of the present application, the first camera is set at the entrance of the ski resort, or at the starting position of the ski slope, for full-time shooting of the entrance or starting position. In the embodiment of the present application, the number of the first camera can be one or more, and the present application does not limit this. Of course, multiple first cameras can be set at different shooting angles, which can facilitate obtaining the identification features of the shooting object from different angles.

[0062] S04. Generate identification features of the photographed target based on the full-time initial image, wherein the identification features include shape features and color features.

[0063] Wherein, in step S04, the identification features include at least one of body features, color features and additional features; the body features in the embodiment of the present application include not only overall features such as height, but also the structural features of the parts obtained by separating the dynamic contour of the human body, head, hands, and feet information and extracting the image information by dividing the blocks. The color features in the embodiment of the present application include the overall color comprehensive features of the photographed target, and also include the color information of the parts such as the dynamic contour of the human body, head, hands, feet, etc.

[0064] The identification features in the embodiments of the present application also include additional features. Of course, for skiers, generally effective additional features include: individual features of the target such as backpack, clothes, hat, glasses, and numbers and text on clothes, etc., which are used to distinguish the target from other targets, thereby accurately obtaining the identification features of the target.

[0065] However, there are some special cases. For the clothing provided by the ski resort, the style is unified in most cases, including the same size and color. Therefore, during the shooting and editing process, some objects may be confused due to the recognition of external body features, that is, it is impossible to distinguish the shooting target from multiple targets. In addition, the target is in motion, which further increases the difficulty of identifying body features, color features and additional features.

[0066] S06: construct a target feature library based on the identification features corresponding to multiple photographed targets.

[0067] In the embodiment of the present application, the target feature library is a real-time target feature library established by the shooting target existing after the shooting instruction is formed for the shooting target and before the stop shooting instruction is received, which is convenient for judging the person who is currently skiing on the slide or in the shooting area. When the shooting target finishes skiing and stops shooting and editing, the identification features of him are removed from the real-time target feature library. Of course, the identification features of the shooting target can be stored in the history library, which is convenient for calling its historical identification features.

[0068] S08. Real-time shooting of the skiing process of the shooting target is performed by using a plurality of shooting and editing devices, and a first video containing the editing target is acquired in real time, where the editing target is one of the plurality of shooting targets.

[0069] When applied, the image is first processed and the color histogram is used to describe the characteristics of the target area; then the characteristics of the target candidate area are extracted in the subsequent frames; finally, the similarity function is used to determine whether the candidate area in the current frame is a real target.

[0070] It should be noted that in the embodiments of the present application, a variety of image processing methods are used to obtain identification features. For example, computer vision, computer graphics, digital image processing and other methods are used to segment, analyze, transform and extract images to complete related functions; AI algorithms, such as machine learning and deep learning (neural networks), are also used to construct a physical statistical model, and image signal samples are continuously input into it for training and evaluation until a model that can efficiently and accurately identify a given target is generated. Of course, a fusion of multiple methods can also be used to improve recognition performance and efficiency.

[0071] In addition, in the embodiment of the present application, by setting a selected clipping target, each shooting target can also be used as a separate clipping target. The present application does not limit this. The target image generation method provided in the embodiment of the present application can be set to identify the clipping target in real time as the shooting progresses, and generate the shooting image of the clipping target in real time. Of course, after the shooting is completed, a separate clipping target can be specified to extract the image of the skiing process that has been shot. The present application does not limit this.

[0072] S10. Based on the identification features in the target feature library, detect each of the shooting targets in the first video through a classifier.

[0073] like Figure 2 As shown, in the step S08, the detecting each of the shooting targets in the first video image by a classifier based on the identification features in the target feature library includes:

[0074] ST10, using a classifier to detect the shooting target on the image frames in the first video to obtain a detection result of the shooting target;

[0075] ST20, assigning a rectangular frame to each of the photographed objects according to the detection result of the photographed objects;

[0076] ST30. Acquire image frames in the first video in real time, and simultaneously shoot several shooting targets through the rectangular frame corresponding to each shooting target.

[0077] In step ST10, the classifier is used to detect the shooting target on the image frame in the first video to obtain the detection result of the shooting target, such as Figure 3 As shown, including:

[0078] ST101, extracting features of the current frame image in the first video to obtain several groups of image feature parameters;

[0079] ST102, determining, by a classifier, whether the image feature parameter belongs to a matching coefficient of any identification feature in the target feature library;

[0080] ST103, determining whether one of the matching coefficients is greater than a first set threshold;

[0081] ST104, if there is one of the matching coefficients that is greater than the first set threshold, marking the detection result of the image feature parameter corresponding to the matching coefficient as the photographed target corresponding to the recognition feature;

[0082] ST105. If none of the matching coefficients is greater than the first set threshold, the detection result of the image feature parameter corresponding to the matching coefficient is marked as unmatched.

[0083] In one embodiment of the present application, Figure 4 As shown, when the image feature parameters of the current frame do not match the shooting target it represents, a processing method includes:

[0084] ST201, calculating the similarity between the unmatched image feature parameters and the rectangular frame of the target corresponding to the previous frame image of the first video;

[0085] ST202: If the similarity is greater than a second set threshold, mark the detection result of the image feature parameter as the photographed target corresponding to the rectangular frame.

[0086] It is worth noting that in the embodiment of the present application, the matching coefficient and the similarity are judged by the first set threshold and the second set threshold. In the embodiment of the present application, since the shooting target is a skier, the large range of skiing movements during skiing will cause problems with recognition accuracy. In the embodiment of the present application, by setting the threshold, flexible judgment is made during the recognition process. Of course, different thresholds can be set according to different application environments or different skiing movements, and in the embodiment of the present application, there is no specific limitation on the setting size of the threshold.

[0087] In another embodiment of the present application, Figure 5 As shown, when the image feature parameters of the current frame do not match the shooting target they represent, another processing method includes:

[0088] ST301, after receiving a shooting instruction, obtaining a bird's-eye view feature of the shooting target through a second shooting device;

[0089] ST302, based on the bird's-eye view editing device, real-time shooting of the position corresponding to the shooting and editing device from a bird's-eye view perspective is performed to obtain a third video containing a plurality of the shooting targets in real time;

[0090] ST303, based on the bird's-eye view feature, detecting each of the shooting targets in the third video by a classifier;

[0091] ST304: According to the shooting target in the third video, obtain the shooting target corresponding to the image feature parameters that are not matched in the first video.

[0092] It should be noted that in the present application, the different processing methods provided in the embodiments of the present application can be executed in a certain order, for example, first by tracing back the image of the previous frame, if the shooting target is identified in this way, then continue shooting and editing; if the shooting target is not identified in this way, then assist by combining the bird's-eye view editing device until the shooting target is found. Of course, it can also be carried out in several ways at the same time. This application does not limit this.

[0093] It should be noted that in the embodiment of the present application, if the shooting target is not found after executing the two methods, the two methods are repeated until the shooting target is identified. This is based on the embodiment of the present application, through the bird's-eye view image as an aid, through the bird's-eye view, multiple target characters will be effectively captured, even if multiple shooting and editing devices 40 do not identify the shooting target in a certain image, but in the embodiment of the present application, the bird's-eye view editing device 30 used for shooting the bird's-eye view is a plurality of cameras arranged along the ski slope, and the arrangement method of overviewing the whole situation can perform all-round auxiliary identification. Combined with the prediction of path continuity, the efficiency of target tracking can be improved.

[0094] In addition, in an embodiment of the present application, multiple shooting and editing devices 40 can be set up to shoot the ski slopes in sections. By segmenting, the viewing angle of a single shooting and editing device can be expanded to achieve comprehensive shooting of each section of the slope.

[0095] In a specific application, the method includes:

[0096] Preset a plurality of shooting and editing devices to shoot the skiing process of the shooting target in sections;

[0097] Determining whether the shooting target leaves the shooting field of view of the corresponding shooting and editing device;

[0098] If it leaves, stop the corresponding shooting and editing equipment to detect the editing target that leaves the field of view.

[0099] S12. Generate a second video corresponding to the editing target in chronological order.

[0100] In application, in step S10, generating a second video corresponding to a single shooting target in chronological order includes:

[0101] In real time, intercepting a second video frame including the clipping target from each frame of the first video frame;

[0102] The captured second video frames are formed into a continuous second video.

[0103] In an embodiment of the present application, the generation of the second video may further include intercepting a third video screen including the editing target from the third video, and inserting the third video screen into the second video. For example, when the shooting target is not recognized in the first video screen, it can be determined from the third video screen whether the identification features of the shooting target are recognized, and if recognized, the screen is intercepted. Of course, when screening the screen in the third video, it can also be judged in combination with the bird's-eye view feature. The present application is not limited here.

[0104] It is worth noting that in the embodiment of the present application, in the second video of the obtained editing target, other shooting targets can be eliminated and only a single editing target is retained, and the present application does not limit this. In specific applications, professional computer software can be compiled to select all materials of the target tourists from the material library, and then the materials can be screened according to big data analysis to find the favorite materials that meet the general consensus of people (such as beautiful, embarrassing, funny moments, etc.), and synthesize them into a complete video.

[0105] In the embodiment of the present application, the second video corresponding to each clip target is uploaded to the server for storage. Of course, it can also be sent to the customer through the client. Before sending to the client, it can also include judging whether the customer has purchased the corresponding service. If it has been purchased, it will be sent directly to the customer and saved on the server. If the customer has not purchased the service, the second video will be encrypted after adding a watermark and the like and sent to the customer. It will also be saved briefly in the server, for example, the saving time is 1-2 days. By setting different saving schemes, the server storage pressure can be reduced. The second video that the customer has purchased or the second video that the customer has not purchased but has exceeded the saving time will be deleted from the server to free up server space and improve server usage efficiency.

[0106] In another embodiment provided in the present application, the method includes:

[0107] generating motion features of the photographed target through the second video, and constructing a motion feature library of the photographed target based on the motion features;

[0108] The respective shooting targets in the first video are detected by combining the established motion feature library of the shooting targets and the identification features in the target feature library.

[0109] It should be noted that in the embodiment of the present application, a skiing image of a single target is extracted from the first video shot of the shooting target, and a second image of the full skiing shooting clip of the shooting target is obtained. The motion features are extracted through the second image to form different motion features belonging to the individual. When applied, the method for extracting motion features includes extracting the motion vector of each pixel based on continuous frames; extracting feature points with strong changes in pixel values ​​in the X, Y, and T directions; constructing a cubic feature vector based on the direction-amplitude histogram of the motion vector with the feature point as the center; and forming a coding vector for the local descriptor through a clustering algorithm. Multiple coding vectors are formed for each shooting target and stored in a specific module.

[0110] After forming the motion features corresponding to the target, when the target moves next time, during real-time shooting, the motion features can be analyzed by calling the encoding vector, and the target can be identified in combination with the recognition features, which can improve the robustness of the system and improve the shooting and editing effects.

[0111] Please refer to Figure 6 The present application provides a ski resort target image generation system for executing any of the above methods, the system comprising:

[0112] The first photographing device 10 is used to obtain identification features of the photographing target after receiving the photographing instruction;

[0113] The second shooting device 20 is used to obtain the bird's-eye view characteristics of the shooting target after receiving the shooting instruction;

[0114] A plurality of bird's-eye view editing devices 30, configured to identify a shooting target for the acquired third video based on the bird's-eye view perspective features corresponding to the shooting target;

[0115] A plurality of shooting and editing devices 40 are used to shoot the shooting target based on the identification features corresponding to the shooting target and generate a second image of the editing target.

[0116] The ski resort target image generation system provided in the embodiment of the present application obtains different identification features through the first shooting device and the second shooting device, which are used to perform feature recognition on skiers during the shooting process to obtain various shooting targets. Through the system in the embodiment of the present application, skiing images can be extracted for a single shooting target, i.e., a clipping target, in real time as the shooting process progresses. Of course, in the embodiment of the present application, images can also be extracted after the clipping target has finished skiing, and the present application does not limit this.

[0117] The present application also provides a server 500, including a processor and a memory, wherein the processor and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute any of the methods described above.

[0118] Among them, it should be noted that the executor of the ski resort target image generation method of this embodiment is the ski resort target image generation method, and the ski resort target image generation method can be implemented by software and / or hardware. The ski resort target image generation method in this embodiment can be configured in an electronic device, and can also be configured in a server for controlling the electronic device, and the server communicates with the electronic device and then controls it.

[0119] Among them, the electronic device where the server is located in this embodiment may include but is not limited to personal computers, system computers, smart phones, smart speakers and other devices. This embodiment does not specifically limit the electronic device.

[0120] In the embodiment of the present application, the processor is a processing device that performs logical operations, such as a central processing unit (CPU), a field programmable logic array (FPGA), a digital signal processor (DSP), a single-chip microcomputer (MCU), an application-specific logic circuit (ASIC), an image processing unit (GPU), etc., which have data processing capabilities and / or program execution capabilities. It is easy to understand that the processor is usually connected to the memory in communication, and any combination of one or more computer program products is stored on the memory. The memory may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), USB memory, flash memory, etc. One or more computer instructions may be stored on the memory, and the processor may run the computer instructions to implement related analysis functions. Various applications and various data, such as various data used and / or generated by the application, may also be stored in the computer-readable storage medium.

[0121] In the embodiments of the present application, each module can be implemented by a processor executing relevant computer instructions. For example, the image processing module can be implemented by a processor executing instructions of an image transformation algorithm, the machine learning module can be implemented by a processor executing instructions of a machine learning algorithm, and the neural network can be implemented by a processor executing instructions of a neural network algorithm.

[0122] In the embodiments of the present application, each module can run on the same processor or on multiple processors; each module can run on a processor of the same architecture, for example, all running on a processor of the X86 system, or can run on processors of different architectures, for example, the image processing module runs on the CPU of the X86 system, and the machine learning module runs on the GPU. Each module can be encapsulated in a computer product, for example, each module is encapsulated in a computer software and runs on a computer (server), or each or part of it can be encapsulated in different computer products, for example, the image processing module is encapsulated in a computer software and runs on a computer (server), and the machine learning modules are respectively encapsulated in separate computer software and run on another or more computers (servers); the computing system when each module is executed can be local computing, cloud computing, or a hybrid computing consisting of local computing and cloud computing.

[0123] like Figure 7 As shown, the electronic device includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In RAM 503, various programs and data required for the operation instructions of the system are also stored. CPU 501, ROM 502 and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0124] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 505 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0125] In particular, according to an embodiment of the present application, the above reference flow chart Figure 1The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present application are executed.

[0126] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the methods described above.

[0127] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0128] In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device, or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium that is a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0129] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation instruction of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or code, and the part of the aforementioned module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur differently from the order marked in the accompanying drawings. For example, the square boxes represented by two connections can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the functions involved.

[0130] It should also be noted that each box in the block diagram and / or flow chart, and the combination of boxes in the block diagram and / or flow chart, can be implemented by a dedicated hardware-based system that performs the specified functions or operating instructions, or can be implemented by a combination of dedicated hardware and computer instructions. The above description is only a preferred embodiment of the present application and an explanation of the technical principles used.

[0131] Those skilled in the art should understand that the scope of disclosure involved in this application is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in this application.

[0132] It should be understood that the orientation or position relationship indicated by terms such as "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0133] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0134] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art in the technical field of the present invention. The terms used herein are only for describing specific implementation purposes and are not intended to limit the present invention. Terms such as "setting" and the like appearing in this article can mean that one component is directly attached to another component, or that one component is attached to another component through an intermediate. Features described in this article in one embodiment may be applied to another embodiment alone or in combination with other features, unless the feature is not applicable in the other embodiment or otherwise specified.

[0135] The present invention has been described through the above-mentioned embodiments, but it should be understood that the above-mentioned embodiments are only for the purpose of example and illustration, and are not intended to limit the present invention to the described embodiments. It can be understood by those skilled in the art that more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the scope of the protection claimed by the present invention.

Claims

1. A method for generating a target image of a ski resort, characterized in that: include: After receiving the shooting instruction, obtaining a full-time initial image including a plurality of shooting targets through a first shooting device; Generate identification features of the photographed target based on the full-time initial image, wherein the identification features include at least one of shape features, color features and additional features; Building a target feature library based on the identification features corresponding to the plurality of photographed targets; The skiing process of the shooting target is shot in real time by shooting and editing equipment, and a first video containing the editing target is obtained in real time, where the editing target is one of the multiple shooting targets; Based on the identification features in the target feature library, detecting each of the shooting targets in the first video by a classifier; Based on the first video, generating a second video corresponding to the editing target in chronological order; The detecting each of the shooting targets in the first video by a classifier based on the identification features in the target feature library includes: detecting the shooting targets on the image frames in the first video by a classifier to obtain the detection results of the shooting targets; assigning a rectangular frame to each of the shooting targets according to the detection results of the shooting targets; acquiring the image frames in the first video in real time, and shooting a plurality of shooting targets simultaneously by using the rectangular frames corresponding to each shooting target; The method of using a classifier to detect the shooting target on the image frame in the first video to obtain the detection result of the shooting target includes: performing feature extraction on the current frame image in the first video to obtain a plurality of groups of image feature parameters; judging by a classifier that the image feature parameters belong to the matching coefficient of any identification feature in the target feature library; judging whether one of the matching coefficients is greater than a first set threshold; if one of the matching coefficients is greater than the first set threshold, marking the detection result of the image feature parameter corresponding to the matching coefficient as the shooting target corresponding to the identification feature; if one of the matching coefficients is not greater than the first set threshold, marking the detection result of the image feature parameter corresponding to the matching coefficient as unmatched.

2. The ski resort target image generation method according to claim 1, characterized in that: The method further comprises: Calculate the similarity between the unmatched image feature parameters and a rectangular frame of a corresponding target in a previous frame of the first video; If the similarity is greater than a second set threshold, the detection result of the image feature parameter is marked as the shooting target corresponding to the rectangular frame.

3. The ski resort target image generation method according to claim 1, characterized in that: The method further comprises: After receiving the shooting instruction, obtaining the bird's-eye view characteristics of the shooting target through the second shooting device; Based on the bird's-eye view editing device, real-time shooting of the position corresponding to the shooting and editing device is performed from a bird's-eye view perspective, and a third video containing a plurality of the shooting targets is obtained in real time; Based on the bird's-eye view feature, detecting each of the shooting targets in the third video by a classifier; According to the shooting target in the third video, the shooting target corresponding to the image feature parameters that are not matched in the first video is obtained.

4. The ski resort target image generation method according to claim 1, characterized in that: The method further comprises: Preset a plurality of shooting and editing devices to shoot the skiing process of the editing target in sections; Determining whether the editing target leaves the shooting field of view of the corresponding shooting and editing device; If the target leaves the field of view, the corresponding shooting and editing equipment stops detecting the editing target that leaves the field of view.

5. The ski resort target image generation method according to claim 1, characterized in that: The step of generating a second video corresponding to a single shooting target in chronological order includes: In real time, intercepting a second video frame including the clipping target from each frame of the first video frame; The captured second video frames are formed into a continuous second video.

6. The ski resort target image generation method according to claim 1, characterized in that: The method comprises: generating motion features of the photographed target through the second video, and constructing a motion feature library of the photographed target based on the motion features; The respective shooting targets in the first video are detected by combining the established motion feature library of the shooting targets and the identification features in the target feature library.

7. A ski resort target image generation system, characterized in that: For executing the method according to any one of claims 1 to 6, the system comprises: A first photographing device is arranged at the entrance of the ski resort, and is used to obtain identification features of a photographing target after receiving a photographing instruction; A second shooting device, configured to obtain a bird's-eye view feature of a shooting target after receiving the shooting instruction; A plurality of bird's-eye view editing devices, used for identifying a shooting target for the acquired third video based on the bird's-eye view perspective features corresponding to the shooting target; A plurality of shooting and editing devices are used to shoot the shooting target based on the identification features corresponding to the shooting target and generate a second image of the editing target.

8. A server, characterized in that: Used to execute the method according to any one of claims 1 to 6.

Images