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

Abstract

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.

Surface Characteristics Measurement Using Computer Vision: A Review

“…Similarly, Authors have also discussed the importance of machine vision techniques and artificial intelligence (AI) based technique for implementation of intelligent manufacturing [306,307]. Farukh et al [308][309][310][311][312][313][314] have compressively emphasized the importance of compute vision techniques using image processing for various field of engineering applications. These techniques may useful for manufacturing applications i.e., surface characteristics measurement using computer vision techniques.…”

COVID-19 Social Distancing Tracking and Monitoring System (SDMOS-19)

“…The approach by [16] is classified into four techniques: feature pyramid network, multi-scale feature fusion, doublebranch structure, and network architecture. The first approach is a pyramid network, which seems to have more decadent interpretations at all stages and is formed rapidly from a single input scale without representational power, performance, or capacity.…”

“…Additionally, they stated that a double-branch structure could increase and optimize the algorithm's effectiveness. The alternate approach includes network architecture, which could also capture the image's features and build a depth map [16]. The limitation caused by multi-scale feature fusion shows that there is still a high risk of data loss throughout this approach, indicating that this method requires regular maintenance.…”

AI-powered Badminton Video Detection: Enhancing Gameplay Analysis and Training

“…This technology can provide players with personalized feedback and recommendations for improvement based on their strengths and weaknesses. It can also help coaches to identify patterns and trends in their players' performance, and adjust their training programs accordingly [2]. However, while AI video analyzers have great potential in sports like badminton, there are some challenges and potential problems that should be addressed.…”