Visual support and match analysis system for ping-pong match and method for running same

Abstract

The invention provides a visual support and match analysis system for a ping-pong match. The system comprises the following modules: an image acquiring and ping-pong ball target recognizing and positioning module, a KALMAN filter module, a track data fitter module, a characteristic analyzing module, a kinematic parameter learning machine module, a single path judging module, a three-dimensional virtual scene reappearing module, a match characteristic data storing module and a user interaction module. A set of system with friendly and complete information extraction and storage, user interaction support and capability of performing track recording well and extracting characteristic information on ball hit of an athlete is developed through real-time visual acquisition. The system can process data in real time and filter and record the processed data in ping-pong trainings and matches, automatically extracts ping-pong ball path characteristic, bring convenience to a judge to replay, is applied to automatic judging and television relaying in the ping-pong match, has a complete, effective and overall analyzing function after the match and can automatically extract and store the characteristic information in a match process and intuitively counts and displays ball throwing and ball winning path characteristics of the ping-pong athlete.

Description

technical field [0001] The invention relates to a table tennis game visual support and game analysis system, which is used for the real-time detection, positioning, tracking, motion trajectory prediction and processing of the table tennis flight trajectory in the table tennis competition or training, as well as the movement trajectory and analysis of the table tennis ball. Real-time display and historical playback of the 3D virtual scene based on table tennis drop point information. Background technique [0002] The "Hawkeye" system has been used in referees and simulation demonstrations of tennis matches for six or seven years. It has been widely promoted in tennis broadcasts, and has played a very positive role in the study of tennis and the fairness of tennis games. The official name of the "Eagle Eye" system is "Instant Replay System", which consists of 8 or 10 high-speed cameras, four computers and a large screen. The amount of image data collected by the "Eagle Eye" s...

AI Technical Summary

Problems solved by technology

The table tennis stroke is very short, and the entire effective stroke lasts only about 0.5s when moving at high speed (3-5m / s), making it very difficult to accurately detect and identify the table tennis task

And because the table tennis ball is relatively light and thin, its flight trajectory is more affected by many factors such as the rotation of the table tennis ball, air temperature, humidity conditions, and on-site ventilation, so it is difficult to establish a general motion model. and forecasting poses great difficulty

Therefore, in the identification of table tennis from the image, the established model is difficult to guarantee the accuracy of prediction

The deviation response to the initial velocity is extremely sensitive, which causes the accuracy of the entire system to predict positioning and trajectory processing to reach the bottleneck

[0005] Secondly, the system sets up multiple cameras for observation according to the needs of the venue and the environment, focusing on data collection. In actual competitions and training, the operability is not strong; for referees and coaches concerned about score information, track replay, The display of the landing point and its distribution probability, and the extraction of the sports feature value of each athlete have not yet established a complete support system

[0006] Therefore, it is very difficult for the actual operation of the table tennis vision system

Images