Billiard ball hitting key information detection method and system
A technology of key information and detection methods, applied in the field of sports science and technology, can solve problems such as inability to move billiards and reasonable judgment of collision situations, and achieve the effects of avoiding trajectory judgment errors, improving detection accuracy, and reducing the amount of calculation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0039] In this embodiment, a method for detecting key information of billiard hitting is provided, and the flow chart is as follows figure 1 shown, including the following steps:
[0040] (1) When there is no billiard ball, extract the characteristic parameter information of the billiard table, including extracting the coordinate information of the table, the edge of the table, and the pocket. Based on the above information, an encoding model of the pool table is established.
[0041] (2) According to the video image before hitting the ball, obtain the characteristic parameter information of the ball on the billiard table at the front of the ball, including the position and color of the billiard ball on the table. According to the coding model of the billiard table, use the perspective transformation matrix from the video data Get the position coordinates of the billiard ball on the table.
[0042] (3) According to the video image of hitting the ball, process and analyze the...
Embodiment 2
[0051] In this embodiment, a method for detecting key information of billiard hitting is provided. The equipment used includes a video acquisition camera (more than 30 frames per second), a computer and an image output device. The method can be mainly divided into the following two parts:
[0052] 1. Calibrate the system before the system runs.
[0053] The calibration steps are:
[0054] (1) Manually measure the actual physical coordinates of the pocket mouth, use the physical coordinates to establish the image coordinates, and determine the corresponding relationship between the physical coordinates and the image coordinates.
[0055] (2) Using the corresponding relationship between physical coordinates and image coordinates, through computer automatic learning, a perspective transformation matrix is formed, which is used for image deformation correction during the detection process.
[0056] (3) Collect the image of the empty ball table, and conduct statistical analysis ...
Embodiment 3
[0071] In this embodiment, on the basis of the above-mentioned embodiments 1 and 2, after the billiard ball is detected and the color is recognized in the transformation area, an error recovery process is also included, which is used to judge whether the billiard ball is detected and the color is recognized in the previous step. An error occurs, and if an error occurs, recovery is performed, and it is restored to before the error occurred, and if no error occurs, subsequent motion trajectory generation is performed. By means of error recovery, it not only avoids detection errors leading to follow-up trajectory judgment errors, and the accuracy of recognition, but also restores to the previous correct state by means of recovery, without re-processing the previous data, which improves the processing efficiency.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com