Title: Survey on sport video analysis and event detection

Authors: Suhas H. Patel; Dipesh Kamdar

Addresses: Electronics and Communication Engineering Department, Government Engineering College, Gandhinagar, 382028, Gujarat, India ' Electronics and Communication Engineering Department, V.V.P. Engineering College, Rajkot, 360005, Gujarat, India

Abstract: In recent years, sports video analysis has gained prominence in areas such as sports coaching, player tracking, and event detection. This survey focuses on two main approaches: handcrafted features and deep learning methods. Handcrafted feature-based methods like scale-invariant feature transform (SIFT), histogram of oriented gradients (HOG), and speeded up robust features (SURF) show promise in sports video analysis, but have limitations in handling complex actions and require manual parameter tuning. In contrast, deep learning methods, including convolutional neural networks (CNNs) and long short-term memorys (LSTMs), offer automated feature learning and high accuracy in action recognition and event detection. This survey offers insights into the latest techniques, their performance, and future research possibilities. By reviewing research on handcrafted features and deep learning in sports video analysis, it provides a comprehensive understanding of state-of-the-art techniques and research gaps. Sports video analysis can extract crucial information from large video datasets, including action recognition, event detection, and team behaviour analysis. Advanced computer vision and machine learning automate analysis for valuable insights.

Keywords: sports video analysis; event detection; CNN; convolutional neural network; RNN; recurrent neural network; VGG-16; hand crafted features; deep learning.

DOI: 10.1504/IJAACS.2025.144266

International Journal of Autonomous and Adaptive Communications Systems, 2025 Vol.18 No.1, pp.67 - 98

Received: 04 Jan 2023
Accepted: 12 Jun 2023
Published online: 04 Feb 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article