[Paper] Improvement of Badminton-Player Tracking Applying Image Pixel Compensation

Abstract

Since the motion analysis of athletes is expected to provide critical information for improving training and strategy meetings, visual player-tracking techniques are being researched and developed 1)-4) . Since sporting matches are usually held over a long time period, the analysis time and effort can be drastically increased. On the other hand, however, assistant coaches and players want the analysis data as quickly as possible. Thus, high-speed automatic processing is critical. Putting a motion sensor on a target player makes it possible to automatically extract motion information. However, since it is impossible to ask the opposing team to wear sensors, visual tracking is expected to be a promising way to acquire positional information 5)-9) .In this paper, we focus on badminton. For badminton analysis, we need to estimate and record such information as player position and shot type in each frame 10) . By statistically analyzing the data, important information is provided for improving training and strategy meetings. However, the captured video contains such typical technical issues for visual tracking as small observation size (i.e., low resolution), large variation of player appearance, and partial occlusion. To easily acquire video data for on-site analysis, such data are usually captured by a monocular camera that is fixed at a relatively high place (such as a balcony) to observe all of the court's players (Fig. 1 (upper-left)). The camera needs a wide-angle lens or the distance between the camera and the target players should be long (in Fig. 1, the distance is about 25 m). As shown in Fig. 1 (bottom), the observed size of each player becomes small. Abstract Motion analysis of athletes often provides important information to improve training and strategy meetings. Visual player-tracking techniques are being developed that do not need devices. In this paper, we focus on racket sports, since they suffer from technical issues for visual tracking such as small observation size (low resolution) and large variation of player appearances. Moreover, racket sports video is usually captured by a monocular camera at a set position so that each player is observed at a top and a bottom region of the video across a net on the court. As a result, tracking accuracy is damaged by the net that often occludes players on the far side. As a solution, this paper proposes a method to improve the player-tracking accuracy in badminton video by applying an image pixel compensation technique, such as Image Inpainting. We confirm the effectiveness of our method using videos of badminton singles games.

A court line extraction algorithm for badminton tournament videos with horizontal line projection learning

“…For testing the robustness of the proposed algorithm, all of the test frames are doubles matches, in which total four players occlude the court lines more than those of singles matches. The scenarios of Figures 10,11,and 12 are the two players gathering at central, right, and left part in the lower court, respectively. In those scenarios, the players occlude the court lines severely, but the proposed algorithm can still extract the court line correctly.…”

“…It is essential to develop the sophisticated content‐based analysis techniques for retrieving sport videos efficiently. The researches on sport video analysis have increased largely [1‐23]. The paper [23] has done a comprehensive review of computer vision in sports.…”

“…According to the BWF (Badminton World Federation) event calendar [24], there are 195 and 154 tournaments in years 2022 and 2023, respectively. However, there are less number of papers in researching into the badminton videos since they have more challenges [8][9][10][11][12]22]. For example, the small-size shuttlecock moves in high speed in playing badminton and the court field is more compact.…”

Heatmap Analysis to Differentiate Diverse Player Types in Table Tennis—A Training and Tactical Strategy Development Potential

“…In badminton too, there are sport-specific problems that reduce the accuracy of player tracking. For example, the net often occludes players on the far side of the court, which can only be bypassed by using multiple, synchronized cameras [6]. Brumann and Kukuk (2017) used a camera position from vertically above the court to avoid the players blocking each other while shifting their positions variably [7].…”

Badminton stroke classification based on accelerometer data: from individual to generalized models

“…M ANY sports are being subject to data collection and machine learning techniques, with the aim of improving the skills and tactics of the players or to evaluate past games. Badminton, being one of the most popular racket sports worldwide, is no exception [1], and many researchers have invested effort into several aspects of the game, such as strategy identification [2], [3], [4], [5] or player tracking [6]. In particular, stroke type recognition is one of the cornerstones of data analysis in badminton, as they are crucial to further identify strategies that might allow the players to win the game.…”