Automatic calibration target scoring method and device, electronic equipment and storage medium

Abstract

The invention provides an automatic calibration target scoring method and device, electronic equipment and a storage medium, and relates to the technical field of shooting training, the automatic calibration target scoring method and device are applied to image target shooting training equipment, the image target shooting training equipment comprises a projection device and a recognition device, the projection device is used for projecting a training picture comprising at least one preset original point to a display device, and the recognition device is used for recognizing the preset original point; the recognition device is used for shooting a picture on the display device. The automatic calibration target scoring method comprises the following steps: determining a target focal length of the recognition device according to a projection ratio and a current projection distance; in response to the shooting signal, controlling the recognition device to acquire a second target image on the display device at the target focal length; identifying a shooting bullet point corresponding to the shooting signal according to the second target image, and determining the bullet point position of the shooting bullet point according to the reference position of the preset original point in the second target image; and determining a target scoring result according to the bullet point position based on a preset conversion strategy. The image target shooting training device is suitable for different sites, and the adaptability of the image target shooting training device is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shooting training, and more particularly, to an automatic calibration target reporting method, device, electronic device, and storage medium. Background Art

[0002] In shooting training, image target shooting training equipment provides an efficient training experience for military, police, and competitive shooting training by simulating a real shooting environment. With its ability to highly simulate actual combat scenarios, image target shooting training equipment has become an indispensable important tool in modern shooting training.

[0003] With the diversification of training requirements, the situation of changing the venue of image target shooting training equipment is increasing. Currently, when the image target shooting training equipment changes the venue or its position changes, in order to ensure the target reporting accuracy of shooting training, cumbersome calibration operations need to be carried out again, which not only increases the operation complexity and workload, but also limits the portability and application range of the equipment. Since it is necessary to recalibrate every time the equipment is moved, it is difficult for shooting training equipment to be quickly deployed in different venues, greatly reducing its practicality and flexibility. Summary of the Invention

[0004] The problem solved by the present invention is how to improve the adaptability of image target shooting training equipment.

[0005] To solve the above problems, the present invention provides an automatic calibration target reporting method, device, electronic device, and storage medium.

[0006] In a first aspect, the present invention provides an automatic calibration target reporting method applied to image target shooting training equipment. The image target shooting training equipment includes a projection device and an identification device. The projection device is used to project a training image including at least one preset origin onto a display device, and the identification device is used to capture the image on the display device. The automatic calibration target reporting method includes:

[0007] Determine the target focal length of the identification device according to the projection ratio of the projection device and the current projection distance;

[0008] In response to a shooting signal, control the identification device to obtain a second target image on the display device with the target focal length;

[0009] Identify the shooting bullet point corresponding to the shooting signal according to the second target image, and determine the bullet point position of the shooting bullet point according to the reference position of the preset origin in the second target image;

[0010] Based on a preset conversion strategy, determine the target reporting result according to the bullet point position.

[0011] Optionally, determining the target focal length of the recognition device according to the projection ratio of the projection device and the current projection distance includes:

[0012] When the projection ratio is determined and the current projection distance increases, the target focal length increases;

[0013] When the projection ratio is determined and the current projection distance decreases, the target focal length decreases.

[0014] Optionally, recognizing the shooting bullet point corresponding to the shooting signal according to the second target image includes:

[0015] Determining the shooting bullet point according to the first target image and the second target image, where the first target image includes the picture on the display device captured by the recognition device before responding to the shooting signal.

[0016] Optionally, determining the shooting bullet point according to the first target image and the second target image includes:

[0017] Performing grayscale processing on the first target image to obtain a first grayscale image;

[0018] Performing grayscale processing on the second target image to obtain a second grayscale image;

[0019] Performing difference processing on the first grayscale image and the second grayscale image to obtain a grayscale difference image;

[0020] Determining the shooting bullet point according to the grayscale difference image.

[0021] Optionally, determining the shooting bullet point according to the grayscale difference image includes:

[0022] Performing feature extraction on the grayscale difference image to obtain the feature vectors of each target in the grayscale difference image;

[0023] Determining the similarity between the feature vectors of each target and the preset feature vector, where the preset feature vector includes the feature vector of the standard shooting bullet point;

[0024] Taking the target with the similarity less than or equal to the preset similarity as the shooting bullet point.

[0025] Optionally, determining the bullet point position of the shooting bullet point according to the reference position of the preset origin in the second target image includes:

[0026] Determine a target recognition area according to a preset position of a preset origin on a training screen displayed by the display device, and determine first coordinates of each point in the target recognition area in the training screen according to the resolution of the training screen, where the shooting bullet point is located within the target recognition area;

[0027] Determine a mapping relationship between coordinates in the training screen and coordinates in the second target image according to the preset position and the reference position, and determine second coordinates of each point in the target recognition area in the second target image according to the mapping relationship and the first coordinates;

[0028] Determine the bullet point position according to the second coordinates corresponding to the position of the shooting bullet point in the target recognition area.

[0029] Optionally, the determining the target shooting result according to the bullet point position based on a preset conversion strategy includes:

[0030] Determine the center of the target in the second target image based on a circular detection algorithm;

[0031] Determine the center coordinates of the center based on the preset origin in the second target image;

[0032] Determine the distance from the shooting bullet point to the center according to the center coordinates and the bullet point position;

[0033] Determine the target shooting result according to the distance.

[0034] In a second aspect, the present invention provides an automatic target calibration device, which is applied to an image target shooting training device. The image target shooting training device includes a projection device and an identification device. The projection device is used to project a training screen including at least one preset origin onto a display device, and the identification device is used to capture the screen on the display device. The automatic target calibration device includes:

[0035] A determination module, configured to determine a target focal length of the identification device according to the projection ratio of the projection device and the current projection distance;

[0036] An acquisition module, configured to control the identification device to acquire a second target image on the display device with the target focal length in response to a shooting signal;

[0037] An identification module, configured to identify a shooting bullet point corresponding to the shooting signal according to the second target image, and determine the bullet point position of the shooting bullet point according to a reference position of the preset origin in the second target image;

[0038] A conversion module, configured to determine a target shooting result according to the bullet point position based on a preset conversion strategy.

[0039] In a third aspect, the present invention provides an electronic device, including a memory and a processor;

[0040] The memory is used to store a computer program;

[0041] The processor is configured to, when executing the computer program, implement the automatic calibration target reporting method as described in the first aspect.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the automatic calibration target reporting method as described in the first aspect is implemented.

[0043] The beneficial effects of the automatic calibration target reporting method of the present invention are as follows: Dynamically adjusting the focal length of the recognition device according to the projection ratio of the projection device and the current projection distance can ensure that the recognition device obtains an accurate and clear second target image under the conditions of changes in the site and projection distance, ensuring that the second target image captured by the recognition device can always cover the entire projection screen (i.e., the training screen projected by the projection device), avoiding the problem of incomplete collection of impact points due to an enlarged projection screen and the problem of decreased collection accuracy due to a reduced projection screen, thereby improving the adaptability and reliability of the image target shooting training device, and enhancing the portability and multi-scene adaptability of the image target shooting training device. Identifying the shooting bullet points according to the second target image, for example, target recognition algorithms can be used for identification, and the bullet point position of the shooting bullet points is determined according to the reference position of the preset origin in the second target image, for example, the bullet point position is determined according to the relative position relationship between the reference position and the shooting bullet points. By presetting the preset origin, the preset origin is projected onto the display device along with the training screen and changes synchronously with the projection screen. Furthermore, automatic point calibration can be realized according to the real-time position of the preset origin in the second target image, and the bullet point position of the shooting bullet points is further determined according to the preset origin, thus avoiding the problem of having to manually calibrate the points again after each movement of the device, so that the image target shooting training device can be quickly deployed in different sites, greatly enhancing the practicality and flexibility of the device. Converting the bullet point position into a target reporting result based on a preset conversion strategy realizes automatic target reporting, reduces manual intervention, and improves the efficiency and accuracy of the image target shooting training device. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic flowchart of an automatic calibration target reporting method according to an embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of automatic zooming of the recognition device when the projection ratio is 1:1 according to an embodiment of the present invention;

[0046] Figure 3An example diagram of an automatic calibration target reporting device according to an embodiment of the present invention;

[0047] Figure 4 An example diagram of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0048] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0049] It should be understood that the various steps recorded in the method embodiments of the present invention can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0050] The term "including" and its variants used herein are open-ended, that is, "including but not limited to"; the term "based on" is "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules, or units, and are not used to limit the order or mutual dependency relationship of the functions performed by these devices, modules, or units.

[0051] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless clearly indicated otherwise in the context, it should be understood as "one or more".

[0052] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0053] In the related art, when using an image target shooting training device for shooting training, it is necessary to set multiple calibration and positioning coordinate points in multiple rows and columns to achieve target reporting. Among them, the staff manually sets multiple calibration and positioning coordinate points, and then determines the mapping relationship based on the actual positions of the calibration and positioning coordinate points and their positions in the captured image, and then determines the position of the bullet point. Since the mapping relationship changes when the position of the image target shooting training device changes, it is necessary to re-calibrate the points. After each position change, the staff needs to re-calibrate the points, which has a large workload and low efficiency.

[0054] In view of the problems existing in the above related art, this embodiment provides an automatic calibration target reporting method, device, electronic device and storage medium.

[0055] As Figure 1 shown, an automatic calibration target reporting method provided by an embodiment of the present invention is applied to an image target shooting training device. The image target shooting training device includes a projection device and an identification device. The projection device is used to project a training image including at least one preset origin onto a display device, and the identification device is used to capture the image on the display device. The automatic calibration target reporting method includes:

[0056] Step S100, determine the target focal length of the identification device according to the projection ratio of the projection device and the current projection distance.

[0057] Specifically, the projection ratio is the ratio of the projection distance of the projection device to the width of the projection image. The smaller the projection ratio, the larger the projection image can be projected by the projection device within a shorter distance; the larger the projection ratio, the longer the projection distance is required to obtain the same image size. For example, a projection device with a projection ratio of 1:1 can project a 1-meter-wide image at a projection distance of 1 meter; a projection device with a projection ratio of 2:1 requires a projection distance of 2 meters to project a 1-meter-wide image. The projection device projects the projection image onto the display device (such as a projection screen, a projection panel), and the current projection distance represents the distance from the projection device to the display device. The projection ratio of the projection device and the current projection distance can determine the size of the current projection image, so that the focal length of the identification device can be adjusted according to the projection ratio of the projection device and the current projection distance, so that the change of the identification image of the identification device is consistent with the change of the projection image of the projection device, that is, when the projection image increases, the identification image of the identification device is controlled to increase.

[0058] Step S200, in response to a shooting signal, control the identification device to obtain a second target image on the display device with the target focal length.

[0059] Specifically, the recognition device performs zoom processing according to the obtained target focal length to capture the target image at the best viewing angle. When the recognition device completes zooming according to the target focal length, the recognition screen of the recognition device covers the projection screen of the projection device. When a shooting signal is received (such as a live bullet hitting the target surface or a signal emitted by a laser gun), the recognition device captures an image on the current display device (i.e., the second target image), ensuring that the position of each bullet impact point on the display device can be accurately recorded even in the case of rapid continuous shooting. The second target image includes the image on the display device captured by the recognition device in response to the shooting signal, containing information about the shooting bullet points.

[0060] Step S300, recognize the shooting bullet points corresponding to the shooting signal according to the second target image, and determine the bullet point position of the shooting bullet points according to the reference position of the preset origin in the second target image.

[0061] Specifically, the second target image includes the image on the display device captured by the recognition device in response to the shooting signal, containing information about the shooting bullet points. To recognize the shooting bullet points according to the second target image, target recognition algorithms and the like can be used for recognition. For example, the edge information in the image can be extracted through an edge detection algorithm (such as the Canny algorithm), the formed contours are analyzed, the contour of the bullet hole is found, and the shooting bullet points are determined. Then, according to the reference position of the preset origin in the second target image, the bullet point position of the shooting bullet points is determined. For example, the bullet point position is determined according to the relative position relationship between the shooting bullet points and the reference position. At least one reference point is preset as the preset origin in the training screen, and the preset origin is projected onto the display device along with the training screen. Regardless of how the size or position of the projection screen changes, the preset origin and the projection screen change synchronously. Furthermore, according to the real-time position of the preset origin in the second target image, the bullet point position of the shooting bullet points can be further determined.

[0062] Step S400, determine the target reporting result according to the bullet point position based on a preset conversion strategy.

[0063] Specifically, determine the target center coordinates and the radius information of each ring based on a preset conversion strategy, and combine the actual coordinates of the shooting bullet points to determine the ring number or score where the shooting bullet points are located. For example, if the distance of the shooting bullet point from the target center falls within the range of the 6th ring, it is determined that its score is 6 points.

[0064] In the embodiment, the focal length of the recognition device is dynamically adjusted according to the projection ratio of the projection device and the current projection distance, which can ensure that the recognition device obtains an accurate and clear second target image under the conditions of site and projection distance changes, and ensure that the second target image captured by the recognition device can always cover the entire projection screen (i.e., the training screen projected by the projection device), avoiding the problem of incomplete collection of impact points caused by the increase of the projection screen and the problem of decreased collection accuracy caused by the reduction of the projection screen, thereby improving the adaptability and reliability of the image target shooting training equipment, and enhancing the portability and multi-scene adaptation ability of the image target shooting training equipment. The shooting impact points are recognized according to the second target image. For example, a target recognition algorithm can be used for recognition, and the impact point position of the shooting impact points is determined according to the reference position of the preset origin in the second target image. For example, the impact point position is determined according to the relative position relationship between the reference position and the shooting impact points. By presetting the preset origin, the preset origin is projected onto the display device along with the training screen and changes synchronously with the projection screen. Furthermore, automatic point calibration can be realized according to the real-time position of the preset origin in the second target image, and the impact point position of the shooting impact points is further determined according to the preset origin, thereby avoiding the problem of manual re-calibration after each movement of the device, so that the image target shooting training equipment can be quickly deployed in different sites, greatly improving the practicability and flexibility of the equipment. Based on the preset conversion strategy, the impact point position is converted into a target reporting result, realizing automatic target reporting, reducing manual intervention, and improving the efficiency and accuracy of the image target shooting training equipment.

[0065] Optionally, the determining the target focal length of the recognition device according to the projection ratio of the projection device and the current projection distance includes:

[0066] When the projection ratio is determined and the current projection distance increases, the target focal length increases.

[0067] When the projection ratio is determined and the current projection distance decreases, the target focal length decreases.

[0068] Specifically, as Figure 2As shown, when the projection ratio of the projection device is determined to be unchanged and the projection distance increases, the size of the projection screen will increase accordingly. By controlling the recognition device to increase the focal length, it is ensured that the recognition device can accurately collect the impact point information within the entire projection screen. For example, the projection ratio of the projection device is 1:1, the initial projection distance is 1 meter, and the corresponding width of the projection screen is 1 meter. When the projection distance increases to 2 meters, the width of the projection screen will become 2 meters. At this time, through the impact point recognition software in the recognition device, according to the projection ratio and the new projection distance, the focal length of the recognition device is automatically adjusted so that it can cover a larger projection screen range, thereby ensuring the accurate collection of impact points, enabling the image target shooting training device to work under new site conditions. Correspondingly, when the projection distance decreases, the size of the projection screen will decrease accordingly. By controlling the recognition device to decrease the focal length, it is ensured that the recognition device can obtain image information more accurately.

[0069] In this optional embodiment, when the projection distance increases, automatically increasing the focal length of the recognition module can ensure that the recognition screen of the recognition device can always cover the entire projection screen, avoiding the problem of incomplete collection of impact points due to the increase in the screen, thereby improving the adaptability and reliability of the image target shooting training device. When the projection distance decreases, automatically decreasing the focal length of the recognition module can ensure that the recognition device covers the reduced projection screen, avoiding the problem of decreased collection accuracy due to the reduction of the screen, and further improving the accuracy of the image target shooting training device. When the projection distance changes, it can quickly respond and adjust the focal length, ensuring the stability of impact point collection and target reporting, enabling the image target shooting training device to be quickly deployed in different sites, thereby improving the overall performance and application range of the image target shooting training device.

[0070] Optionally, the recognizing the shooting bullet point corresponding to the shooting signal according to the second target image includes:

[0071] Determining the shooting bullet point according to the first target image and the second target image, wherein the first target image includes the image on the display device captured by the recognition device before responding to the shooting signal.

[0072] Specifically, before the shooting signal is triggered, the recognition device continuously captures the projection screen and selects the last stable image as the first target image. The first target image includes the image on the display device captured by the recognition device before the shooting signal. After the shooting signal is triggered (such as the signal of the laser emitter or the trigger sensor signal), the recognition device immediately captures one or more frames of images and selects the clear image as the second target image. For example, in laser simulated shooting, an image is captured with a 10 ms delay after the signal is triggered to ensure that the bullet hole is fully imaged. By comparing the differences between the first target image and the second target image, the specific position of the shooting bullet point is obtained. For example, the image subtraction method is used to subtract the gray values of the corresponding pixel points of the two images to highlight the newly emerged bullet hole area. For example, the shooter conducts multiple rounds of shooting, and corresponding images are taken before and after each round of shooting. By analyzing the changes in these images, the position of each bullet hole can be marked and converted into the position in the actual coordinate system for subsequent calculation of the ring score.

[0073] In this alternative embodiment, by separately obtaining two images before and after shooting, precise comparison before and after the formation of the bullet hole is achieved. If there are old bullet holes or stains on the target surface, it is difficult to distinguish new and old bullet points with a single-frame image. However, after comparing the two frames of images, only the new bullet holes will appear in the difference area, thereby avoiding misidentification caused by environmental factors and improving the accuracy of bullet point recognition. The method of image comparison can adapt to different lighting conditions and environmental backgrounds, enhancing the reliability of the recognition results of the image target shooting training equipment. Based on the coordinate mapping algorithm for bullet point positioning, the exact position of each bullet hole can be determined with high precision. Even in the face of a complex background or pattern, through an effective coordinate mapping algorithm, the position of the newly emerged bullet hole can still be accurately identified, avoiding misjudgment, and thus enhancing the adaptability and stability of the image target shooting training equipment.

[0074] Optionally, determining the shooting bullet point according to the first target image and the second target image includes:

[0075] Performing grayscale processing on the first target image to obtain a first grayscale image;

[0076] Performing grayscale processing on the second target image to obtain a second grayscale image;

[0077] Performing difference processing on the first grayscale image and the second grayscale image to obtain a grayscale difference image;

[0078] Determining the shooting bullet point according to the grayscale difference image.

[0079] Specifically, grayscale processing can convert a color image into a grayscale image, reducing the complexity of the image data, lowering the computational load of subsequent image processing, and improving the processing efficiency of the image. The first target image is the target surface image captured by the recognition device before shooting, including the background information of the target surface. Grayscale processing converts the first target image from a color image into a grayscale image, obtaining the first grayscale image. The second target image is the target surface image captured by the recognition device after shooting, including the bullet hole information after shooting. Similarly, grayscale processing is used to convert the second target image from a color image into a grayscale image, obtaining the second grayscale image. Subtracting pixel by pixel between the first grayscale image and the second grayscale image yields a grayscale difference image. In the grayscale difference image, the bullet hole usually appears as an area with obvious grayscale changes. By analyzing the grayscale difference image, the position of the shooting bullet point can be determined.

[0080] In this optional embodiment, the first target image and the second target image are processed by grayscale, reducing the amount of image data, lowering the complexity of subsequent processing, and at the same time retaining the necessary luminance information, which helps to improve the image processing speed and efficiency. Grayscale processing can highlight the grayscale difference between the target surface background and the bullet hole, providing a clearer contrast for bullet point recognition and improving the accuracy of bullet point recognition. The difference processing can prominently display the changes in the target surface image before and after shooting (such as the appearance of the bullet hole), facilitating the rapid positioning of the bullet hole position. It can also effectively remove the interference of the target surface background, only retaining the image change information after shooting, thereby improving the accuracy of bullet point recognition.

[0081] Optionally, determining the shooting bullet point based on the grayscale difference image includes:

[0082] Performing feature extraction on the grayscale difference image to obtain the feature vector of each target in the grayscale difference image;

[0083] Determining the similarity between the feature vector of each target and the preset feature vector, where the preset feature vector includes the feature vector of the standard shooting bullet point;

[0084] Taking the target with the similarity less than or equal to the preset similarity as the shooting bullet point.

[0085] Specifically, the grayscale difference image contains the change information of the target surface before and after shooting, and the bullet hole usually appears as an obvious grayscale change area. Feature extraction of the grayscale difference image can accurately identify the shooting bullet points. Feature vectors of each target are extracted from the grayscale difference image through a feature extraction algorithm, and the feature vectors can include information such as the shape, size, and grayscale distribution of the target. The target includes the potential bullet hole area extracted from the grayscale difference image through an image processing algorithm, and the target is used for subsequent analysis and recognition. After feature extraction is completed, for each potential bullet hole area (target) in the grayscale difference image, the similarity between its feature vector and the standard feature vector is obtained. The preset feature vector is predefined according to the characteristics such as the shape, size, and grayscale distribution of the standard bullet hole, and is used to determine whether the target is a shooting bullet hole. According to the obtained similarity, it is determined whether the target is a shooting bullet point. The preset similarity is used to distinguish real bullet holes from interference factors, and the target with a similarity less than or equal to the preset similarity is regarded as a shooting bullet point.

[0086] In this optional embodiment, feature vectors of each potential bullet hole area in the grayscale difference image are obtained through feature extraction. Feature extraction can exclude interference factors in the image and only retain the feature information of the target, thereby providing a more accurate basis for subsequent bullet point recognition. Through the similarity, the difference degree between each potential target and the standard bullet hole can be accurately quantified, which can effectively distinguish real shooting bullet points from interference points, reduce the possibility of false alarms, and thus more accurately locate real shooting bullet points. By setting a reasonable preset similarity, real shooting bullet holes and interference factors can be effectively distinguished, and shooting bullet points can be accurately identified, thereby improving the accuracy of the image target shooting training device.

[0087] Optionally, the determining the bullet point position of the shooting bullet point according to the reference position of the preset origin in the second target image includes:

[0088] Determine a target recognition area according to the preset position of the preset origin on the training screen displayed by the display device, and determine the first coordinates of each point in the target recognition area in the training screen according to the resolution of the training screen, where the shooting bullet point is located in the target recognition area;

[0089] Determine the mapping relationship between the coordinates in the training screen and the coordinates in the second target image according to the preset position and the reference position, and determine the second coordinates of each point in the target recognition area in the second target image according to the mapping relationship and the first coordinates;

[0090] Determine the bullet point position according to the second coordinates corresponding to the position of the shooting bullet point in the target recognition area.

[0091] Specifically, a preset origin is set in the training screen in advance. The preset origin is projected onto the display device along with the training screen and changes synchronously with the projection screen. The target recognition area is determined according to the position of the preset origin on the training screen displayed on the display device. The target recognition area includes a target, and the shooting bullet point is within the target recognition area. According to the resolution of the training screen (for example, if the resolution is 1920x1080, it means that the training screen has 1920 pixel points in the horizontal width and 1080 pixel points in the vertical height), the coordinates (i.e., the first coordinates) of each pixel point within the target recognition area in the training screen are determined. According to the position of the preset origin on the training screen displayed on the display device (i.e., the preset position) and the reference position of the preset origin in the second target image captured by the recognition device, the mapping relationship between the coordinates in the training screen and the coordinates in the second target image is determined through a coordinate mapping algorithm. Furthermore, according to the mapping relationship and the first coordinates, the coordinates (i.e., the second coordinates) of each point in the target recognition area in the second target image are determined. The bullet point position of the shooting bullet point in the second target image is determined according to the second coordinates corresponding to the position of the shooting bullet point in the target recognition area. The second coordinates of each point in the target corresponding to the first coordinates in the training screen and the mapping relationship can also be determined, and target reporting can be achieved by comparing the bullet point position and the range of the target in the second image.

[0092] In this optional embodiment, by presetting a preset origin in the training screen in advance and ensuring its synchronous change with the training screen, the mapping relationship between the training screen coordinate system and the second target image coordinate system can be accurately established. Through the coordinate mapping relationship, the position of the shooting bullet point in the training screen can be accurately converted into the bullet point position in the second target image. Even if the position of the image target shooting training device changes, a high positioning accuracy can be maintained, and the accuracy of bullet point recognition is improved. The image target shooting training device can automatically adjust the target recognition area and the coordinate mapping relationship according to the position of the preset origin without manual intervention, greatly reducing the calibration workload and improving the portability and usability of the image target shooting training device.

[0093] Optionally, based on the preset conversion strategy, determining the target reporting result according to the bullet point position includes:

[0094] Determining the center of the target in the second target image based on a circular detection algorithm;

[0095] Determining the center coordinates of the center based on the preset origin in the second target image;

[0096] Determining the distance from the shooting bullet point to the center according to the center coordinates and the bullet point position;

[0097] Determining the target reporting result according to the distance.

[0098] Specifically, the circular detection algorithm can be the Hough transform algorithm, which is used to detect geometric shapes in images, such as straight lines, circles, etc. The target surface contains multiple concentric circles, and the center of the concentric circles is the bull's-eye. The target is located within the target recognition area. After determining the second coordinates of each point in the target recognition area in the second target image, the target can be detected through the target recognition algorithm, and then the second coordinates corresponding to each point in the target can be determined, and further the ranges of each scoring ring of the target can be determined. Determine the center coordinates and the position of the bullet impact point, and determine the distance from the shooting bullet impact point to the center of the circle through a simple mathematical formula (such as the Euclidean distance formula). Based on the obtained distance, judge the ring number or score where the shooting bullet impact point is located. For example, if the target surface is divided into multiple scoring rings, and the radii of each ring are 10 cm, 20 cm, 30 cm, etc., then it is possible to determine which ring the bullet impact point falls into according to the distance from the bullet impact point to the center of the circle, and give the corresponding score. The radius of each ring can be determined according to the Hough transform algorithm.

[0099] In this alternative embodiment, circular detection is performed through the circular detection algorithm, which can efficiently and accurately identify all concentric circles and their center positions on the target surface, ensuring that the data for subsequent processing is more reliable. Determining the target reporting result based on the distance from the bullet impact point to the center of the circle realizes automatic target reporting, reduces manual intervention, and improves the efficiency and accuracy of the image target shooting training equipment.

[0100] As Figure 3 shown, an automatic calibration target reporting device 300 provided by an embodiment of the present invention is applied to an image target shooting training device. The image target shooting training device includes a projection device and an identification device. The projection device is used to project a training image including at least one preset origin onto a display device, and the identification device is used to capture the image on the display device. The automatic calibration target reporting device 300 includes:

[0101] A determination module 310, configured to determine the target focal length of the identification device according to the projection ratio of the projection device and the current projection distance;

[0102] An acquisition module 320, configured to control the identification device to acquire a second target image on the display device with the target focal length in response to a shooting signal;

[0103] An identification module 330, configured to identify the shooting bullet impact point corresponding to the shooting signal according to the second target image, and determine the bullet impact position of the shooting bullet impact point according to the reference position of the preset origin in the second target image;

[0104] A conversion module 340, configured to determine a target reporting result according to the bullet impact position based on a preset conversion strategy.

[0105] As Figure 4As shown in the figure, an electronic device 400 provided by an embodiment of the present invention includes a memory 410 and a processor 420; the memory 410 is used to store a computer program; the processor 420 is used to implement the automatic calibration target reporting method as described above when executing the computer program.

[0106] A computer-readable storage medium provided by an embodiment of the present invention has a computer program stored thereon, and when the computer program is executed by a processor, the automatic calibration target reporting method as described above is implemented.

[0107] An electronic device 400 that can be used as a server or a client of the present invention will now be described. It is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device 400 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 400 can also represent various forms of mobile devices, such as assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0108] The electronic device 400 includes a computing unit that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0109] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention. In addition, the functional units in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0110] Although the present invention is disclosed as above, the scope of protection of the present invention is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will all fall within the scope of protection of the present invention.

Claims

1. An automatic calibration target reporting method, characterized in that Applied to an image target shooting training device, the image target shooting training device includes a projection device and an identification device. The projection device is used to project a training image including at least one preset origin onto a display device, and the identification device is used to capture the image on the display device. The automatic calibration target reporting method includes: Determining the target focal length of the identification device according to the projection ratio of the projection device and the current projection distance; In response to a shooting signal, controlling the identification device to obtain a second target image on the display device with the target focal length; Identifying the shooting bullet point corresponding to the shooting signal according to the second target image, and determining the bullet point position of the shooting bullet point according to the reference position of the preset origin in the second target image; Based on a preset conversion strategy, determining a target reporting result according to the bullet point position.

2. The automatic target reporting method according to claim 1, characterized in that, The determining the target focal length of the identification device according to the projection ratio of the projection device and the current projection distance includes: When the projection ratio is determined and the current projection distance increases, the target focal length increases; When the projection ratio is determined and the current projection distance decreases, the target focal length decreases.

3. The automatic target reporting method according to claim 1, wherein The identifying the shooting bullet point corresponding to the shooting signal according to the second target image includes: Determining the shooting bullet point according to a first target image and the second target image, where the first target image includes the image on the display device captured by the identification device before the shooting signal.

4. The automatic target reporting method according to claim 3, characterized in that, The determining the shooting bullet point according to the first target image and the second target image includes: Performing grayscale processing on the first target image to obtain a first grayscale image; Performing grayscale processing on the second target image to obtain a second grayscale image; Performing difference processing on the first grayscale image and the second grayscale image to obtain a grayscale difference image; Determining the shooting bullet point according to the grayscale difference image.

5. The automatic target-reporting calibration method according to claim 4, wherein The determining the shooting bullet point according to the grayscale difference image includes: Performing feature extraction on the grayscale difference image to obtain feature vectors of each target in the grayscale difference image; Determining the similarity between the feature vector of each target and a preset feature vector, where the preset feature vector includes the feature vector of a standard shooting bullet point; Taking the target with the similarity less than or equal to a preset similarity as the shooting bullet point.

6. The automatic target-reporting calibration method according to claim 1, wherein The determining the bullet point position of the shooting bullet point according to the reference position of the preset origin in the second target image includes: Determining a target recognition area according to the preset position of the preset origin on the training image displayed on the display device, and determining the first coordinates of each point in the target recognition area in the training image according to the resolution of the training image, where the shooting bullet point is located in the target recognition area; Determining the mapping relationship between the coordinates in the training image and the coordinates in the second target image according to the preset position and the reference position, and determining the second coordinates of each point in the target recognition area in the second target image according to the mapping relationship and the first coordinates; Determining the bullet point position according to the second coordinates corresponding to the position of the shooting bullet point in the target recognition area.

7. The automatic target reporting method according to claim 1, wherein Determining the target reporting result according to the preset conversion strategy based on the bullet point position includes: Determining the center of the target in the second target image based on the circular detection algorithm; Determining the center coordinates of the center of the circle based on the preset origin in the second target image; Determining the distance from the shooting bullet point to the center of the circle according to the center coordinates and the bullet point position; Determining the target reporting result according to the distance.

8. An automatic target calibration device, characterized in that, Applied to an image target shooting training device, the image target shooting training device includes a projection device and an identification device. The projection device is used to project a training image including at least one preset origin onto a display device, and the identification device is used to capture the image on the display device. The automatic calibration target reporting device includes: A determination module, configured to determine the target focal length of the identification device according to the projection ratio of the projection device and the current projection distance; An acquisition module, configured to control the identification device to acquire a second target image on the display device with the target focal length in response to a shooting signal; An identification module, configured to identify the shooting bullet point corresponding to the shooting signal according to the second target image, and determine the bullet point position of the shooting bullet point according to the reference position of the preset origin in the second target image; A conversion module, configured to determine the target reporting result according to the bullet point position based on a preset conversion strategy.

9. An electronic device, characterized in that, Including a memory and a processor; The memory is used to store a computer program; The processor is configured to implement the automatic calibration target reporting method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is executed by the processor, the automatic calibration target reporting method according to any one of claims 1 to 7 is implemented.

Images