Double-person diving synchronism analysis method based on camera cooperation and three-dimensional skeleton estimation

Abstract

The invention provides a double-person diving synchronism analysis method based on camera cooperation and three-dimensional skeleton estimation. The method comprises the steps of cooperatively acquiring action images of a diving athlete by using cameras at multiple viewing angles, sequentially sending the action images to an attitude extraction network to obtain a key point thermodynamic diagram of the diving athlete, obtaining two-dimensional key point information according to the key point thermodynamic diagram, and sending the two-dimensional key point information to a time convolution network to obtain three-dimensional skeleton information; calculating the take-off height of the two diving athletes, the horizontal distance between the two diving athletes and the bedplate and the cosine value of the angle when the two diving athletes enter water according to the three-dimensional skeleton information, and evaluating the action similarity and the action time consistency; collectinga water surface image by using a camera in the overlooking direction, calculating the area of water spots in the water surface image, and analyzing the synchronism of double-person diving in combination with the result. According to the method, the influence of subjective factors during referee scoring can be eliminated, and the analysis result is more objective and fair.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a synchronization analysis method for double diving based on camera coordination and three-dimensional skeleton estimation. Background technique [0002] In the invention patent with the application number 200710304226.0, an automatic analysis method for synchronism of double diving is proposed. This method proposes a consistency feature JFF, which needs to extract the consistency features of take-off height, air movement coordination time and water entry time. The extraction process is too complicated. It is complicated and the accuracy is difficult to guarantee, and the determination of the take-off height, the coordination time of aerial movements and the time of entering the water is relatively vague. Contents of the invention [0003] In order to solve the above problems, the present invention proposes a synchronization analysis method for double diving based on came...

AI Technical Summary

Problems solved by technology

[0002] In the invention patent with the application number 200710304226.0, an automatic analysis method for synchronism of double diving is proposed. This method proposes a consistency feature JFF, which needs to extract the consistency features of take-off height, air movement coordination time and water entry time. The extraction process is too complicated. It is complicated and the accuracy is difficult to guarantee, and the determination of the take-off height, air movement coordination time and water entry time is relatively vague

Images