International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
Basketball Virtual Referee Janhavi Banarase1, Mayuri Gawande2, Shreyash Kale3, Shashank Mahalle4 1Student, Dept. of CSE Engineering, PRMIT&R College, Maharashtra, India 2Student, Dept. of CSE Engineering, PRMIT&R College, Maharashtra, India 3Student, Dept. of CSE Engineering, PRMIT&R College, Maharashtra, India 4Student, Dept. of CSE Engineering, PRMIT&R College, Maharashtra, India
---------------------------------------------------------------------***--------------------------------------------------------------------two techniques, the Basketball Virtual Referee is capable of Abstract - Sports are evolving day by day and the technology
accurately identifying travels and double dribbles in basketball games.
that supports these sports is evolving at an exponential rate. Many sports have implemented computer vision to improve referee calls and the overall fairness of the game. Basketball is a fast-paced and dynamic sport that relies heavily on accurate and consistent officiating for fair play and a smooth game flow. However, traditional officiating methods depend on human referees, who are susceptible to errors in judgment due to factors like limited viewing angles, fatigue, and the pressure of split-second decisions. These inconsistencies can lead to frustration among players, coaches, and fans, potentially impacting the game's outcome. Virtual Basketball Referees use artificial intelligence that can distinguish between two major infractions in basketball games: double dribbling and travel. The system tracks players and the basketball in real time by utilizing the YOLOv8 object detection methodology. The system can precisely identify critical body spots on players, allowing for detection of double dribble violations, by combining pose estimate techniques with object identification. By combining these technologies, a reliable method for automating the identification of these frequent basketball infractions is offered, improving the accuracy and fairness of game officiating.
2. LITERATURE REVIEW 2.1 Computer Vision Computer vision is a field of artificial intelligence that enables machines to interpret and understand visual information from the real world. Over the past few decades, significant advancements have been made in computer vision algorithms and technologies, leading to a wide range of applications in various industries. Computer vision aims to replicate the human visual system's ability to interpret and understand the visual world. It encompasses a broad range of tasks, including image recognition, object detection, image segmentation, and scene understanding. Recent advancements in deep learning have significantly improved the performance of computer vision systems, enabling them to achieve human-level performance on many visual recognition tasks. The key concepts in computer vision include image preprocessing, feature extraction, feature representation, and machine learning algorithms for classification and regression tasks. Convolutional Neural Networks (CNNs) have emerged as a dominant approach in computer vision, achieving state-of-the-art performance on tasks such as image classification and object detection.
Key Words: You Only Look Once (YOLO), Convolutional Neural Networks (CNN), Computer Vision, Object Detection, Pose Estimation
1. INTRODUCTION
2.2 OpenCV (Open Source Computer Vision Library)
Basketball is a very dynamic game where the movements the players make can be fast and subtle, yet fine-grained. As such the difference between an event occurring and not occurring can be small and occasionally unnoticeable, and the sequence of frames of which the dribble is done matters tremendously to determine whether a violation takes place. As such, a spatio-temporal action verification model is needed to assist referees in making decisions, as it is almost instantaneous in nature. The challenge is to achieve the balance between speed and accuracy since the violation detection has to be fast enough for real-time use. The Basketball Virtual Referee is a system that uses a YOLOv8 (You Only Look Once) machine learning model trained on annotated images to detect basketball, players in real-time. Additionally, it utilizes YOLOV8 pose estimation to detect key points on the body of the players. By combining these
© 2024, IRJET
|
Impact Factor value: 8.226
OpenCV (Open Source Computer Vision Library) is an opensource computer vision and machine learning software library. It has a comprehensive collection of algorithms and tools for a wide range of applications, making it one of the most popular libraries in the field of computer vision. OpenCV provides a rich set of features for image and video analysis, including image processing algorithms such as filtering, edge detection, and morphological operations. Feature detection and description algorithms such as SIFT, SURF, and ORB. Object detection algorithms such as Haar cascades and HOG (Histogram of Oriented Gradients). Machine learning algorithms for classification, regression, clustering, and dimensionality reduction. Deep learning capabilities through integration with frameworks like TensorFlow and PyTorch. OpenCV has made significant contributions to the field of computer vision research,
|
ISO 9001:2008 Certified Journal
|
Page 1434