Computer vision approach to automatic linesman

Abstract

To date, there is no implementation of an automatic linesman system (ALS) in any official badminton game. An ALS is important in assisting the game umpire/referee to make a better judgment in a dispute. Just like the Hawkeye system in tennis, the ALS is anticipated to play more important role in big games that require high standard refereeing quality like the Olympic, Badminton World Championships (BWF) etc. This paper proposed an algorithm to model the shuttlecock position so as to track and determine its landing point either inside or outside the boundaries of the court line. It involves background subtraction method in hue space, analysis of the shuttlecock trajectory and a decision making process to determine the shuttlecock landing point. Performance is evaluated based on three metrics namely, accuracy, sensitivity and specificity. Initial results showed that the proposed algorithm works well with low error values. However, further works is required to refine the proposed ALS before it can be fully implemented in an official game.

A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions

“…The recognition accuracy of player actions in badminton games [191] can be improved by SOTA computer vision algorithms and fine-tuning in an end-to-end manner with a larger dataset on features extracted at different fully connected layers. In the implementation of an automatic linesman system in badminton games [295], algorithm is robust to the far views of the camera, where illumination conditions heavily impact the system while the speed of the shuttlecock is also a major factor for poor accuracy. So, it is necessary to track the path, which becomes simpler for the referee to decide if a shuttle lands out or in as shown in Figure 21.…”

NeuroHSMD: Neuromorphic Hybrid Spiking Motion Detector

“…airports, train stations, seaports) [21], [22]; monitoring specific people/objects in mass events (e.g. sports games, music concerts, manifestations and gatherings) [23], [24], [25]; and indoor/outdoor behaviour analysis (e.g. track people in closed public spaces, bodycameras installed police forces) [26], [27].…”

Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches

“…Combining with computer vision, these techniques allow for the detection of objects of interest based on the images captured from camera systems using an advanced computer algorithm. Recently, computer vision and object detection techniques have also found applications in sports technology for match analysis [ 20 , 21 , 22 , 23 ], player’s performance analysis [ 24 ], and electronic umpiring [ 25 , 26 ]. In a recent study on video analysis of table tennis, the researchers have successfully demonstrated the real-time detection of the position of the tennis ball and players, and the types of events (bounces and net hits) [ 23 ].…”