Table Tennis Track Detection Based on Temporal Feature Multiplexing Network

Abstract

Recording the trajectory of table tennis balls in real-time enables the analysis of the opponent’s attacking characteristics and weaknesses. The current analysis of the ball paths mainly relied on human viewing, which lacked certain theoretical data support. In order to solve the problem of the lack of objective data analysis in the research of table tennis competition, a target detection algorithm-based table tennis trajectory extraction network was proposed to record the trajectory of the table tennis movement in video. The network improved the feature reuse rate in order to achieve a lightweight network and enhance the detection accuracy. The core of the network was the “feature store & return” module, which could store the output of the current network layer and pass the features to the input of the network layer at the next moment to achieve efficient reuse of the features. In this module, the Transformer model was used to secondarily process the features, build the global association information, and enhance the feature richness of the feature map. According to the designed experiments, the detection accuracy of the network was 96.8% for table tennis and 89.1% for target localization. Moreover, the parameter size of the model was only 7.68 MB, and the detection frame rate could reach 634.19 FPS using the hardware for the tests. In summary, the network designed in this paper has the characteristics of both lightweight and high precision in table tennis detection, and the performance of the proposed model significantly outperforms that of the existing models.

Optimization of table tennis target detection algorithm guided by multi-scale feature fusion of deep learning

“…Its competition process is fast, tense and high-tech, which requires athletes to respond quickly and accurately control the trajectory of the ball. In table tennis competition, it is very important to accurately detect the track of table tennis for improving the fairness and technical level of the competition 1 , 2 . Traditional target detection (TD) methods face many challenges in table tennis competition.…”

A study on table tennis landing point detection algorithm based on spatial domain information

“…Tan21 proposes to design the prior frame of YOLOv4 with K-means clustering, trim the network branches and compress the convolutional layers for table tennis ball size, and use the fast NMS algorithm to accelerate the prediction process and improve the computational speed of the model. Zhao22 proposes a table tennis table detection method based on the Temporal Feature Multiplexing Network (TFMN) and Kalman filter, which is capable of achieving high accuracy and real-time detection of table tennis tables.…”