A real-time basketball broadcasting system based on panoramic camera

Abstract

The present invention provides a real-time basketball broadcast directing system based on a panoramic camera, which belongs to the field of artificial intelligence technology and specifically comprises: an area division module, a change risk assessment module, a shooting probability determination module and a broadcast directing processing module; the area division module is responsible for screening monitoring areas and determining image change thresholds of the screening monitoring areas; the change risk assessment module is responsible for determining the comprehensive image change risk of a target monitoring scene; the shooting probability determination module is responsible for determining the probability of shooting and scoring; the broadcast directing processing module is responsible for moving the picture to a rectangular area with a basketball as the center and the smallest size that can contain all court personnel, and if the width and height of the rectangular area are not less than a preset size, the rectangular area is determined with the preset size as a constraint condition, thereby realizing the recognition of highlight moments and automatic broadcast directing processing.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to a real-time basketball broadcast directing system based on a panoramic camera. Background Art

[0002] Current basketball director broadcasts are all based on manual camera operation, with the direction and focus of the camera facing the direction of interest. However, in basketball, the situation on the court may reverse at any time, so the use of manual director processing may lead to problems such as missing exciting shots, which cannot meet the processing needs of real-time director broadcasts.

[0003] To solve the above technical problems, with the development of artificial intelligence technology, it has become possible to analyze the areas of interest to the audience based on the detection results of real-time video recording of basketball games and actively present the areas of interest to the audience. Therefore, how to combine image recognition results to automatically direct motion images has become a technical problem that needs to be solved urgently.

[0004] In view of the above technical problems, the present invention provides a real-time basketball broadcasting system based on a panoramic camera. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a real-time basketball broadcasting method based on a panoramic camera is provided.

[0007] A real-time basketball broadcasting method based on a panoramic camera, characterized by comprising:

[0008] S1 acquires monitoring images in a target monitoring scene through a panoramic camera, and divides the monitoring area in the target monitoring scene into a plurality of sub-areas according to the distance between the monitoring area and the corresponding target basket, and screens the monitoring area based on the historical shooting data, shooting hit data and the distance to the corresponding target basket of different sub-areas, and determines the image change threshold of the screened monitoring area;

[0009] S2 determines the image change amount of different screening monitoring areas by the change of different monitoring images in different screening monitoring areas within a preset time, and determines the comprehensive image change risk of the target monitoring scene in combination with the image change threshold of different screening monitoring areas. When the comprehensive image change risk of the target monitoring scene does not meet the requirement, proceed to the next step;

[0010] S3 obtains the sub-area where the basketball in the target monitoring scene is located, and determines the probability of shooting and scoring by combining the personnel data and personnel movement data in different screening monitoring areas. When the probability of shooting and scoring is greater than the preset scoring probability, proceeds to the next step;

[0011] S4 moves the image to a rectangular area centered on the basketball and containing all the players on the court. If the width and height of the rectangular area are not less than a preset size, the rectangular area is determined with the preset size as a constraint.

[0012] The beneficial effects of the present invention are:

[0013] 1. In the present invention, based on the historical shooting data, shooting hit data and the distances from the corresponding target baskets of different sub-areas, the screening monitoring areas and the determination of the image change thresholds of the screening monitoring areas are performed, and full consideration is given to the differences in the probabilities of shooting in different areas when image changes occur due to the differences in the distances from different sub-areas to the target baskets and the shooting data, thereby achieving the screening of high-risk screening monitoring areas and laying the foundation for further targeted directing processing.

[0014] 2. In the present invention, the comprehensive image change risk of the target monitoring scene is determined by the image change amount and image change threshold of different screening monitoring areas, thereby realizing the difference in the risk of shooting scores caused by image changes in the target monitoring scene, so that the image change conditions of different screening monitoring areas are associated with the results of shooting scores, and at the same time, through the monitoring of the screening monitoring areas, the overall monitoring processing efficiency is further improved.

[0015] 3. In the present invention, the probability of shooting and scoring is determined by combining the sub-area where the basketball is located, the personnel data in different screening and monitoring areas, and the personnel movement data. This takes into account the historical shooting data of the sub-area where the basketball is located and the difference in shooting and scoring probabilities caused by the difference in shooting scores. At the same time, the difference in shooting and scoring probabilities caused by the number of people and the difference in movement in different screening and monitoring areas is taken into account, thereby achieving accurate evaluation of the probability of shooting and scoring from both the perspectives of basketball and personnel.

[0016] A further technical solution is that the monitoring area and its corresponding target basket are determined according to the basket corresponding to the half-court area of ​​the court where the monitoring area is located in the target monitoring scene.

[0017] A further technical solution is that the historical shooting data of the different sub-areas are determined based on the historical monitoring images of the sub-areas, wherein the historical shooting data include the average number of historical shots per game, the number of historical shooters, and the historical number of shots.

[0018] A further technical solution is that the method for determining the image change amount of the screening monitoring area is:

[0019] Extracting image features by screening the surveillance images of the surveillance area within a preset time, and determining the number of changed surveillance images and the amount of change of image features of different changed surveillance images according to the image features of different adjacent surveillance images within the preset time;

[0020] The image baseline change amount of the filtered monitoring area is determined based on the change amount of image features between the last frame and the first frame of the monitoring image of the filtered monitoring area within a preset time, and the image change amount of the filtered monitoring area is determined in combination with the number of changed monitoring images and the change amount of image features of different changed monitoring images.

[0021] On the other hand, the present invention provides a real-time basketball broadcasting system based on a panoramic camera, which adopts the above-mentioned real-time basketball broadcasting method based on a panoramic camera, and is characterized in that it specifically includes:

[0022] Area division module, change risk assessment module, shooting probability determination module, director processing module;

[0023] The area division module is responsible for acquiring monitoring images in the target monitoring scene through a panoramic camera, and dividing the monitoring area in the target monitoring scene into multiple sub-areas according to the distance between the monitoring area and the corresponding target basket, screening the monitoring area based on the historical shooting data, shooting hit data and the distance to the corresponding target basket of different sub-areas, and determining the image change threshold of the screening monitoring area;

[0024] The change risk assessment module is responsible for determining the image change amount of different screening monitoring areas by the change of different monitoring images in different screening monitoring areas within a preset time, and determining the comprehensive image change risk of the target monitoring scene in combination with the image change thresholds of different screening monitoring areas;

[0025] The shooting probability determination module is responsible for obtaining the sub-area where the basketball is located in the target monitoring scene, and determining the probability of shooting and scoring by combining the personnel data and personnel movement data in different screening monitoring areas;

[0026] The director processing module is responsible for moving the picture to a rectangular area centered on the basketball, which is the smallest area that can contain all the people on the court. If the width and height of the rectangular area are not less than the preset size, the rectangular area is determined based on the preset size as a constraint.

[0027] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings;

[0030] Figure 1 It is a flow chart of a real-time basketball broadcasting method based on a panoramic camera;

[0031] Figure 2 is a flow chart of a method for determining a probability of scoring a shot;

[0032] Figure 3 It is a framework diagram of a real-time basketball broadcasting system based on a panoramic camera. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification. Example 1

[0034] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a real-time basketball broadcasting method based on a panoramic camera is provided, which is characterized by specifically comprising:

[0035] S1 acquires monitoring images in a target monitoring scene through a panoramic camera, and divides the monitoring area in the target monitoring scene into a plurality of sub-areas according to the distance between the monitoring area and the corresponding target basket, and screens the monitoring area based on the historical shooting data, shooting hit data and the distance to the corresponding target basket of different sub-areas, and determines the image change threshold of the screened monitoring area;

[0036] Specifically, the monitoring area and its corresponding target basket are determined according to the basket corresponding to the half-court area of ​​the court where the monitoring area is located in the target monitoring scene.

[0037] It should be noted that the historical shooting data of the different sub-areas are determined based on the historical monitoring images of the sub-areas, wherein the historical shooting data include the average number of historical shots per game, the number of historical shooters, and the historical number of shots.

[0038] In one possible embodiment, the method for determining the screening monitoring area in step S1 is:

[0039] Determine whether the distance between the sub-area and the corresponding target basket is greater than a preset distance, if so, determine that the sub-area does not belong to the screening monitoring area, if not, proceed to the next step;

[0040] Determine the historical shooting number of the sub-region based on the historical shooting data of the sub-region, and judge whether the historical shooting number of the sub-region is less than the preset shooting number. If so, determine that the sub-region does not belong to the screening monitoring area. If not, proceed to the next step.

[0041] Determine the number of historical shooters in the sub-region through the historical shooting data of the sub-region, and determine the shooting frequency of the sub-region in combination with the average historical shooting number per game of the sub-region and the average number of historical shooters and the historical shooting number per game, and judge whether the shooting frequency of the sub-region is less than a preset frequency of use. If so, determine that the sub-region does not belong to the screening monitoring area, if not, proceed to the next step;

[0042] The number of successful shots and the successful shot percentage of the sub-area are obtained, and the shooting correlation of the sub-area is determined in combination with the shooting frequency of the sub-area and the distance between the sub-area and its corresponding target basket, and whether the sub-area is a screening monitoring area is determined by the shooting correlation of the sub-area.

[0043] Furthermore, when the shooting correlation of the sub-area is greater than a preset correlation threshold, the sub-area is determined to be a screening monitoring area.

[0044] Specifically, the preset distance is determined according to the area of ​​the court in the target monitoring scene, wherein the larger the area of ​​the court is, the larger the preset distance is.

[0045] In another possible embodiment, the method for determining the screening monitoring area in the above step S1 is:

[0046] When the distance between the sub-area and the corresponding target basket is greater than a preset distance, it is determined that the sub-area does not belong to the screening monitoring area;

[0047] When the distance between the sub-region and the corresponding target basket is not greater than a preset distance, determining the number of historical games in which the number of historical shots of the sub-region is greater than the limit value of the average number of shots per game based on the historical shooting data of the sub-region, and when the number of historical games does not meet the requirement, determining that the sub-region does not belong to the screening monitoring area;

[0048] When the number of historical games meets the requirement, the number of historical shooters in the sub-area and the number of historical games in which the number of historical shots is greater than the limit value of the average number of shots per game are determined through the historical shooting data of the sub-area, and the shooting frequency of the sub-area is determined in combination with the average number of historical shots per game in the sub-area and the number of historical shooters and the historical number of shots per game;

[0049] The number of successful shots and the successful shot percentage of the sub-area are obtained, and the shooting correlation of the sub-area is determined in combination with the shooting frequency of the sub-area and the distance between the sub-area and its corresponding target basket, and whether the sub-area is a screening monitoring area is determined by the shooting correlation of the sub-area.

[0050] It can be understood that the image change threshold of the screening monitoring area is determined according to the shooting correlation of the screening monitoring area, wherein the greater the shooting correlation of the screening monitoring area, the smaller the image change threshold of the screening monitoring area.

[0051] S2 determines the image change amount of different screening monitoring areas by the change of different monitoring images in different screening monitoring areas within a preset time, and determines the comprehensive image change risk of the target monitoring scene in combination with the image change threshold of different screening monitoring areas. When the comprehensive image change risk of the target monitoring scene does not meet the requirement, proceed to the next step;

[0052] In one possible embodiment, the method for determining the image change amount of the screening monitoring area in the above step S2 is:

[0053] Extracting image features by screening the surveillance images of the surveillance area within a preset time, and determining the number of changed surveillance images and the amount of change of image features of different changed surveillance images according to the image features of different adjacent surveillance images within the preset time;

[0054] The image baseline change amount of the filtered monitoring area is determined based on the change amount of image features between the last frame and the first frame of the monitoring image of the filtered monitoring area within a preset time, and the image change amount of the filtered monitoring area is determined in combination with the number of changed monitoring images and the change amount of image features of different changed monitoring images.

[0055] In one possible embodiment, the method for determining the comprehensive image change risk of the target monitoring scene in step S2 is:

[0056] According to the image change amount and the image change threshold of the screened monitoring area, the changing monitoring area whose image change amount is greater than the image change threshold and the stable monitoring area whose image change amount is not greater than the image change threshold are determined, and it is judged whether the number of the changing monitoring areas of the target monitoring scene is greater than the preset number of areas. If so, it is determined that the comprehensive image change risk of the target monitoring scene does not meet the requirements. If not, proceed to the next step;

[0057] Obtain the image change amount of different change monitoring areas and the deviation of the image change amount from the image change threshold, and determine the image change risk of the change monitoring area of ​​the target monitoring scene in combination with the number of the change monitoring areas, and judge whether the image change risk of the change monitoring area meets the requirements, if so, proceed to the next step, if not, determine that the comprehensive image change risk of the target monitoring scene does not meet the requirements;

[0058] Obtaining image change amounts of different stable monitoring areas and deviations between the image change amounts and the image change threshold, and determining the image change risk of the stable monitoring area of ​​the target monitoring scene in combination with the number of the stable monitoring areas;

[0059] Based on the image change amounts of different filtered monitoring areas in the target scene, the mean image change amounts of the filtered monitoring areas and the number of filtered monitoring areas are determined; and the comprehensive image change risk of the target monitoring scene is determined through the mean image change amounts of the filtered monitoring areas and the number of filtered monitoring areas, the image change risk of the stable monitoring areas and the image change risk of the changing monitoring areas.

[0060] Furthermore, the number of preset areas is determined based on the number of screened monitoring areas of the target monitoring scene and the number of personnel in the target monitoring scene, wherein the more the number of screened monitoring areas of the target monitoring scene and the more the number of personnel in the target monitoring scene, the greater the number of preset areas.

[0061] In one possible embodiment, the method for determining the comprehensive image change risk of the target monitoring scene in step S2 is:

[0062] Determine the changing monitoring area whose image change amount is greater than the image change threshold and the stable monitoring area whose image change amount is not greater than the image change threshold according to the image change amount and the image change threshold of the screened monitoring area, determine the image change deviation amount of different image change areas according to the image change amount and the image change threshold of different image change areas, and when any one of the number of image change areas and the maximum value of the image change deviation amount of the image change area does not meet the requirements, determine that the comprehensive image change risk of the target monitoring scene does not meet the requirements;

[0063] When the number of the image change areas and the maximum value of the image change deviation of the image change areas meet the requirements, determine whether the number of the image change areas is less than the preset area number threshold, if so, determine that the comprehensive image change risk of the target monitoring scene meets the requirements, if not, proceed to the next step;

[0064] Obtain the image change amount of different change monitoring areas and the deviation of the image change amount from the image change threshold, and determine the image change risk of the change monitoring area of ​​the target monitoring scene in combination with the number of the change monitoring areas, and judge whether the image change risk of the change monitoring area meets the requirements, if so, proceed to the next step, if not, determine that the comprehensive image change risk of the target monitoring scene does not meet the requirements;

[0065] Obtaining image change amounts of different stable monitoring areas and deviations between the image change amounts and the image change threshold, and determining the image change risk of the stable monitoring area of ​​the target monitoring scene in combination with the number of the stable monitoring areas;

[0066] Based on the image change amounts of different filtered monitoring areas in the target scene, the mean image change amounts of the filtered monitoring areas and the number of filtered monitoring areas are determined; and the comprehensive image change risk of the target monitoring scene is determined through the mean image change amounts of the filtered monitoring areas and the number of filtered monitoring areas, the image change risk of the stable monitoring areas and the image change risk of the changing monitoring areas.

[0067] S3 obtains the sub-area where the basketball in the target monitoring scene is located, and determines the probability of shooting and scoring by combining the personnel data and personnel movement data in different screening monitoring areas. When the probability of shooting and scoring is greater than the preset scoring probability, proceeds to the next step;

[0068] In one possible embodiment, the method for determining the shooting score probability in step S3 is:

[0069] Determine whether the basketball in the target monitoring scene is in the screening monitoring area, if so, proceed to the next step, if not, determine the shooting score probability according to the historical shooting times and shooting hit rate of the sub-area where the basketball is located;

[0070] Determine the number of screening monitoring areas in which the basketball is located in the same half of the court within a preset time and the retention time of different screening monitoring areas through the sub-area where the basketball is located, determine the movement risk of the basketball according to the number of screening monitoring areas in which the basketball is located in the same half of the court within the preset time and the retention time of different screening monitoring areas, and judge whether the movement risk of the basketball meets the requirements, if so, proceed to the next step, if not, determine that the shooting score probability is greater than the preset score probability;

[0071] Obtain the number of people in the screening and monitoring area in the same half, the number of basketball appearances within a preset time, and the number of people moving, and determine the personnel flow risks of different screening and monitoring areas according to the number of people in different screening and monitoring areas, the number of basketball appearances within a preset time, the number of people moving, and the number of people moving, and determine whether the personnel flow risks of the screening and monitoring areas meet the requirements. If so, proceed to the next step; if not, determine that the shooting score probability is greater than the preset score probability;

[0072] The historical number of shots and the shooting success rate of the sub-area where the basketball is located are obtained, and the probability of shooting and scoring is determined in combination with the personnel flow risks and the movement risks of the basketball in different screening and monitoring areas.

[0073] In another possible embodiment, Figure 2 As shown, the method for determining the shooting score probability in the above step S3 is:

[0074] Determine the number of screening monitoring areas in which the basketball is located in the same half of the court within a preset time and the retention time of different screening monitoring areas through the sub-area where the basketball is located, and determine the movement risk of the basketball according to the number of screening monitoring areas in which the basketball is located in the same half of the court within the preset time and the retention time of different screening monitoring areas;

[0075] Obtain the number of people in the screening and monitoring area in the same half, the number of basketball appearances within a preset time, and the number of people moving, and determine the personnel flow risks of different screening and monitoring areas based on the number of people in different screening and monitoring areas, the number of basketball appearances within a preset time, the number of people moving, and the number of people moving;

[0076] The historical number of shots and the shooting success rate of the sub-area where the basketball is located are obtained, and the probability of shooting and scoring is determined in combination with the personnel flow risks and the movement risks of the basketball in different screening and monitoring areas.

[0077] S4 moves the image to a rectangular area centered on the basketball and containing all the players on the court. If the width and height of the rectangular area are not less than a preset size, the rectangular area is determined with the preset size as a constraint.

[0078] On the other hand, Figure 3 As shown, the present invention provides a real-time basketball broadcasting system based on a panoramic camera, which adopts the above-mentioned real-time basketball broadcasting method based on a panoramic camera, and is characterized in that it specifically includes:

[0079] Area division module, change risk assessment module, shooting probability determination module, director processing module;

[0080] The area division module is responsible for acquiring monitoring images in the target monitoring scene through a panoramic camera, and dividing the monitoring area in the target monitoring scene into multiple sub-areas according to the distance between the monitoring area and the corresponding target basket, screening the monitoring area based on the historical shooting data, shooting hit data and the distance to the corresponding target basket of different sub-areas, and determining the image change threshold of the screening monitoring area;

[0081] The change risk assessment module is responsible for determining the image change amount of different screening monitoring areas by the change of different monitoring images in different screening monitoring areas within a preset time, and determining the comprehensive image change risk of the target monitoring scene in combination with the image change thresholds of different screening monitoring areas;

[0082] The shooting probability determination module is responsible for obtaining the sub-area where the basketball is located in the target monitoring scene, and determining the probability of shooting and scoring by combining the personnel data and personnel movement data in different screening monitoring areas;

[0083] The director processing module is responsible for moving the picture to a rectangular area centered on the basketball, which is the smallest area that can contain all the people on the court. If the width and height of the rectangular area are not less than the preset size, the rectangular area is determined based on the preset size as a constraint.

[0084] Through the above embodiments, the present invention achieves the following beneficial effects:

[0085] 1. In the present invention, based on the historical shooting data, shooting hit data and the distances from the corresponding target baskets of different sub-areas, the screening monitoring areas and the determination of the image change thresholds of the screening monitoring areas are performed, and full consideration is given to the differences in the probabilities of shooting in different areas when image changes occur due to the differences in the distances from different sub-areas to the target baskets and the shooting data, thereby achieving the screening of high-risk screening monitoring areas and laying the foundation for further targeted directing processing.

[0086] 2. In the present invention, the comprehensive image change risk of the target monitoring scene is determined by the image change amount and image change threshold of different screening monitoring areas, thereby realizing the difference in the risk of shooting scores caused by image changes in the target monitoring scene, so that the image change conditions of different screening monitoring areas are associated with the results of shooting scores, and at the same time, through the monitoring of the screening monitoring areas, the overall monitoring processing efficiency is further improved.

[0087] 3. In the present invention, the probability of shooting and scoring is determined by combining the sub-area where the basketball is located, the personnel data in different screening and monitoring areas, and the personnel movement data. This takes into account the historical shooting data of the sub-area where the basketball is located and the difference in shooting and scoring probabilities caused by the difference in shooting scores. At the same time, the difference in shooting and scoring probabilities caused by the number of people and the difference in movement in different screening and monitoring areas is taken into account, thereby achieving accurate evaluation of the probability of shooting and scoring from both the perspectives of basketball and personnel.

[0088] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0089] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A real-time basketball broadcasting method based on a panoramic camera, characterized in that: Specifically include: Acquiring monitoring images in a target monitoring scene through a panoramic camera, dividing the monitoring area in the target monitoring scene into a plurality of sub-areas according to the distance between the monitoring area and the corresponding target basket, screening the monitoring area based on historical shooting data, shooting hit data and the distance to the corresponding target basket of different sub-areas, and determining the image change threshold for screening the monitoring area; Determine the image change amount of different screening monitoring areas by the change of different monitoring images in different screening monitoring areas within a preset time, and determine the comprehensive image change risk of the target monitoring scene in combination with the image change threshold of different screening monitoring areas. When the comprehensive image change risk of the target monitoring scene does not meet the requirement, proceed to the next step; Obtaining the sub-area where the basketball in the target monitoring scene is located, and determining the probability of scoring a shot by combining the personnel data and personnel movement data in different screening monitoring areas, and when the probability of scoring a shot is greater than the preset scoring probability, proceeding to the next step; Move the screen to a rectangular area centered on the basketball and containing all the players on the court. If the width and height of the rectangular area are not less than a preset size, determine the rectangular area with the preset size as a constraint. Determine, according to the image change amount and the image change threshold of the screened monitoring area, the change monitoring area whose image change amount is greater than the image change threshold and the stable monitoring area whose image change amount is not greater than the image change threshold; when the number of change monitoring areas of the target monitoring scene is greater than the preset number of areas, determine that the comprehensive image change risk of the target monitoring scene does not meet the requirement; The method for determining the probability of scoring a shot is: Determine the number of screening monitoring areas in which the basketball is located in the same half of the court within a preset time and the retention time of different screening monitoring areas through the sub-area where the basketball is located, and determine the movement risk of the basketball according to the number of screening monitoring areas in which the basketball is located in the same half of the court within the preset time and the retention time of different screening monitoring areas; Obtain the number of people in the screening and monitoring area in the same half, the number of basketball appearances within a preset time, and the number of people moving, and determine the personnel flow risks of different screening and monitoring areas based on the number of people in different screening and monitoring areas, the number of basketball appearances within a preset time, the number of people moving, and the number of people moving; The historical number of shots and the shooting success rate of the sub-area where the basketball is located are obtained, and the probability of shooting and scoring is determined in combination with the personnel flow risks and the movement risks of the basketball in different screening and monitoring areas.

2. The method for real-time basketball broadcasting based on a panoramic camera according to claim 1, characterized in that: The monitoring area and its corresponding target basket are determined according to the basket corresponding to the half-court area of ​​the court where the monitoring area is located in the target monitoring scene.

3. The real-time basketball broadcasting method based on a panoramic camera according to claim 1, characterized in that: The historical shooting data of the different sub-areas are determined based on the historical monitoring images of the sub-areas, wherein the historical shooting data include the historical average number of shots per game, the number of historical shooters, and the historical number of shots.

4. The real-time basketball broadcasting method based on a panoramic camera according to claim 1, characterized in that: The method for determining the screening monitoring area is: Determine whether the distance between the sub-area and the corresponding target basket is greater than a preset distance, if so, determine that the sub-area does not belong to the screening monitoring area, if not, proceed to the next step; Determine the historical shooting number of the sub-region based on the historical shooting data of the sub-region, and judge whether the historical shooting number of the sub-region is less than the preset shooting number. If so, determine that the sub-region does not belong to the screening monitoring area. If not, proceed to the next step. Determine the number of historical shooters in the sub-region through the historical shooting data of the sub-region, and determine the shooting frequency of the sub-region in combination with the average historical shooting number per game of the sub-region and the average number of historical shooters and the historical shooting number per game, and judge whether the shooting frequency of the sub-region is less than a preset frequency of use. If so, determine that the sub-region does not belong to the screening monitoring area, if not, proceed to the next step; The number of successful shots and the successful shot percentage of the sub-area are obtained, and the shooting correlation of the sub-area is determined in combination with the shooting frequency of the sub-area and the distance between the sub-area and its corresponding target basket, and whether the sub-area is a screening monitoring area is determined by the shooting correlation of the sub-area.

5. The method for real-time basketball broadcasting based on a panoramic camera as claimed in claim 4, characterized in that: When the shooting correlation degree of the sub-area is greater than a preset correlation degree threshold, the sub-area is determined to be a screening monitoring area.

6. The real-time basketball broadcasting method based on a panoramic camera as claimed in claim 4, characterized in that: The preset distance is determined according to the area of ​​the court in the target monitoring scene, wherein the larger the area of ​​the court is, the larger the preset distance is.

7. The real-time basketball broadcasting method based on a panoramic camera as claimed in claim 1, characterized in that: The method for determining the image change amount of the screening monitoring area is: Extracting image features by screening the surveillance images of the surveillance area within a preset time, and determining the number of changed surveillance images and the amount of change of image features of different changed surveillance images according to the image features of different adjacent surveillance images within the preset time; The image baseline change amount of the filtered monitoring area is determined based on the change amount of image features between the last frame and the first frame of the monitoring image of the filtered monitoring area within a preset time, and the image change amount of the filtered monitoring area is determined in combination with the number of changed monitoring images and the change amount of image features of different changed monitoring images.

8. A real-time basketball broadcasting system based on a panoramic camera, using a real-time basketball broadcasting method based on a panoramic camera according to any one of claims 1 to 7, characterized in that: Specifically include: Area division module, change risk assessment module, shooting probability determination module, director processing module; The area division module is responsible for acquiring monitoring images in the target monitoring scene through a panoramic camera, and dividing the monitoring area in the target monitoring scene into multiple sub-areas according to the distance between the monitoring area and the corresponding target basket, screening the monitoring area based on the historical shooting data, shooting hit data and the distance to the corresponding target basket of different sub-areas, and determining the image change threshold of the screening monitoring area; The change risk assessment module is responsible for determining the image change amount of different screening monitoring areas by the change of different monitoring images in different screening monitoring areas within a preset time, and determining the comprehensive image change risk of the target monitoring scene in combination with the image change thresholds of different screening monitoring areas; The shooting probability determination module is responsible for obtaining the sub-area where the basketball is located in the target monitoring scene, and determining the probability of shooting and scoring by combining the personnel data and personnel movement data in different screening monitoring areas; The director processing module is responsible for moving the screen to a rectangular area centered on the basketball and containing all the players on the court. If the width and height of the rectangular area are not less than a preset size, the rectangular area is determined based on the preset size as a constraint condition. Determine, according to the image change amount and the image change threshold of the screened monitoring area, the change monitoring area whose image change amount is greater than the image change threshold and the stable monitoring area whose image change amount is not greater than the image change threshold; when the number of change monitoring areas of the target monitoring scene is greater than the preset number of areas, determine that the comprehensive image change risk of the target monitoring scene does not meet the requirement; The method for determining the probability of scoring a shot is: Determine the number of screening monitoring areas in which the basketball is located in the same half of the court within a preset time and the retention time of different screening monitoring areas through the sub-area where the basketball is located, and determine the movement risk of the basketball according to the number of screening monitoring areas in which the basketball is located in the same half of the court within the preset time and the retention time of different screening monitoring areas; Obtain the number of people in the screening and monitoring area in the same half, the number of basketball appearances within a preset time, and the number of people moving, and determine the personnel flow risks of different screening and monitoring areas based on the number of people in different screening and monitoring areas, the number of basketball appearances within a preset time, the number of people moving, and the number of people moving; The historical number of shots and the shooting success rate of the sub-area where the basketball is located are obtained, and the probability of shooting and scoring is determined in combination with the personnel flow risks and the movement risks of the basketball in different screening and monitoring areas.

Images