To understand human behaviors, action recognition based on videos is a common approach. Compared with image-based action recognition, videos provide much more information. Reducing the ambiguity of actions and in the last decade, many works focused on datasets, novel models and learning approaches have improved video action recognition to a higher level. However, there are challenges and unsolved problems, in particular in sports analytics where data collection and labeling are more sophisticated, requiring sport professionals to annotate data. In addition, the actions could be extremely fast and it becomes difficult to recognize them. Moreover, in team sports like football and basketball, one action could involve multiple players, and to correctly recognize them, we need to analyse all players, which is relatively complicated. In this paper, we present a survey on video action recognition for sports analytics. We introduce more than ten types of sports, including team sports, such as football, basketball, volleyball, hockey and individual sports, such as figure skating, gymnastics, table tennis, tennis, diving and badminton. Then we compare numerous existing frameworks for sports analysis to present status quo of video action recognition in both team sports and individual sports. Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Experimental investigation on the influence of a single structural plane on rockburst

Experimental Study on the Effects of Water Saturation on the Microseismic and Acoustic Emission Characteristics of Sandstone in Different Stress States

Study of mechanical behavior and cracking mechanism of prefabricated fracture cemented paste backfill under different loading rates from the perspective of energy evolution

This paper analyzes the basis of badminton special feature, energy supply characteristics, relationship between physical fitness and special quality, and evaluation theory to establish special quality evaluation index architecture, which can provide better distinction and reliability for badminton players. We adopt standard percentage method and deviation method to establish representative index score standard of sports quality based on original data. Then it is integrated with factor weight to make single scoring and comprehensive scoring. After theoretical and actual test, the special sport quality evaluation index architecture of badminton players are proved to be reliable to be taken as reference for current evaluation for special sport quality training level of badminton players.

http://www.computer.org/csdl/proceedings/isdea/2015/9393/00/9393a239.pdf

Construction Scheme Research of Special Sport Quality Evaluation System for Badminton Players

Extracting acoustic emission features that precede hard rock instability with unsupervised learning

Experimental research on the evolutionary characteristics of acoustic signals for concrete cracking under uniaxial compression

The badminton sports training process surveillance system that this paper purports to build takes over modern information technical media measures to make real-time statistical analysis on the technical and tactical performance during the badminton training process for the diagnosis and evaluation on the badminton technical and tactical levels promptly; actualize online transmission and online forums to solve difficult problems arisen from training by gathering many peoples wisdom, revise and improve tactical arrangement; collect and build a database of excellent badminton players technical movements; check in real-time badminton training and live competitions.

Jing Jing Huang

Papers

Extracting acoustic emission features that precede hard rock instability with unsupervised learning

Experimental research on the evolutionary characteristics of acoustic signals for concrete cracking under uniaxial compression

Real-Time Surveillance Systems in Badminton Training