Ball and Player Detection & Tracking in Soccer Videos Using Improved YOLOV3 Model

Over the past few years, there has been a tremendous increase in the interest and enthusiasm for sports among people. This has led to an increase in the importance given to video recording of various sports that capture even the minutest detail using high-end equipment. Recording and analysis have thereby become extremely crucial in sports like soccer that involve several complex and fast events. Ball detection and tracking along with player analysis have emerged as an area of interest among a lot of analysts and researchers. This is because it helps coaches in performance assessment of the team and in decision making to obtain optimized results. Video analysis can additionally be used by coaches and recruiters to look for new, talented players based on their previously played games. Ball detection also plays a pivotal role in assisting the referees in making decisions at game-changing moments. However, as the ball is almost always moving, its shape-appearance keeps changing over time and it is frequently occluded by players, it makes it difficult to track it throughout the game. We propose a deep learning-based YOLOv3 model for the ball and player detection in broadcast soccer videos. Initially, the videos are processed and unnecessary parts like zoom-ins, replays, etc., are removed to obtain only the relevant frames from each game. Tracking is achieved using the SORT algorithm which employs a Kalman filtering and bounding box overlap.

Active Player Detection in Handball Scenes Based on Activity Measures

In team sports training scenes, it is common to have many players on the court, each with his own ball performing different actions. Our goal is to detect all players in the handball court and determine the most active player who performs the given handball technique. This is a very challenging task, for which, apart from an accurate object detector, which is able to deal with complex cluttered scenes, additional information is needed to determine the active player. We propose an active player detection method that combines the Yolo object detector, activity measures, and tracking methods to detect and track active players in time. Different ways of computing player activity were considered and three activity measures are proposed based on optical flow, spatiotemporal interest points, and convolutional neural networks. For tracking, we consider the use of the Hungarian assignment algorithm and the more complex Deep SORT tracker that uses additional visual appearance features to assist the assignment process. We have proposed the evaluation measure to evaluate the performance of the proposed active player detection method. The method is successfully tested on a custom handball video dataset that was acquired in the wild and on basketball video sequences. The results are commented on and some of the typical cases and issues are shown.

Badminton player detection using faster region convolutional neural network

Nowadays, coaches and sport analyst are concerning about sport performance analysis through sport video match. However, they still used conventional method which is through manual observation of the full video that is very troublesome because they might miss some meaningful information presence in the video. Several previous studies have discussed about tracking ball movements, identification of player based on jersey color and number as well as player movement detection in various type of sport such as soccer and volleyball but not in badminton. Therefore, this study focused on developing an automated system using Faster Region Convolutional Neural Network (Faster R-CNN) to track the position of the badminton player from the sport broadcast video. In preparing the dataset for training and testing, several broadcast videos were converted into image frames before labelling the region which indicate the players. After that, several different trained Faster R-CNN detectors were produced from the dataset before tested with different set of videos to evaluate the detector performance. In evaluating the performance of each detector model, the average precision was obtained from precision recall graph. As a result, this study revealed that the detector successfully detects the player when the detector is being fed with more generalized dataset.

Soccer Players Detection Using GDLS Optimization and Spatial Bitwise Operation Filter

Advancement computer vision technology in order to help coach creates strategy has been affecting the sport industry evolving very fast. Players movement patterns and other important behavioral activities regarding the tactics during playing the game are the most important data obtained in applying computer vision in Sport Industry. The basic technique for extracting those information during the game is player detection. Three fundamental challenges of computer vision in detecting objects are random object’s movement, noise and shadow. Background subtraction is an object’s detection method that used widely for separating moving object as foreground and non moving object as background. This paper proposed a method for removing shadow and unwanted noise by improving traditional background subtraction technique. First, we employed GDLS algorithm to optimize background-foreground separation. Then, we did filter shadows and crumbs-like object pixels by applying digital spatial filter which is created from implementation of digital arithmetic algorithm (bitwise operation). Finally, our experimental result demonstrated that our algorithm outperform conventional background subtraction algorithms. The experiments result proposed method has obtained 80.5% of F1-score with average 20 objects were detected out of 24 objects.

Detection Accuracy of Soccer Players in Aerial Images Captured from Several Viewpoints

In the fields of professional and amateur sports, players’ health, physical and physiological conditions during exercise should be properly monitored and managed. The authors of this paper previously proposed a real-time vital-sign monitoring system for players using a wireless multi-hop sensor network that transmits their vital data. However, existing routing schemes based on the received signal strength indicator or global positioning system do not work well, because of the high speeds and the density of sensor nodes attached to players. To solve this problem, we proposed a novel scheme, image-assisted routing (IAR), which estimates the locations of sensor nodes using images captured from cameras mounted on unmanned aerial vehicles. However, it is not clear where the best viewpoints are for aerial player detection. In this study, the authors investigated detection accuracy from several viewpoints using an aerial-image dataset generated with computer graphics. Experimental results show that the detection accuracy was best when the viewpoints were slightly distant from just above the center of the field. In the best case, the detection accuracy was very good: 0.005524 miss rate at 0.01 false positive-per-image. These results are informative for player detection using aerial images and can facilitate to realize IAR.