Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Object Detection in Hockey Sport Video via Pretrained YOLOV3 Based Deep Learning Model


Affiliations
1 Department of Electronics and Communication Engineering, Gujarat Technological University, India., India
2 Department of Electronics and Communication Engineering, V.V.P. Engineering College, India., India
     

   Subscribe/Renew Journal


Object detection is the most common task in Sports Video Analysis. This task requires accurate object detection that can handle a variety of objects of different sizes that are partially occluded, have poor lighting, or are presented in complicated surroundings. Object in field sports includes player’s team and ball detection; this is a difficult task resulting from the rapid movement of the player and speed of the object of concern. This paper proposes a pre-trained YOLOv3, deep learningbased object detection model. We have prepared a hockey dataset consisting of four main entities: Team 1 (AUS), Team 2 (BEL), Hockey Ball, and Umpire. We constructed own dataset because there are no existing field hockey datasets available. Experimental results indicate that the pre-trained YOLOV3 deep learning model generates comparative results on this dataset by modifying the hyperparameters of this pre-trained model.

Keywords

Sport Video Analysis, Deep Learning, YOLOv1, YOLOv2, YOLOv3, Object Detection.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Y. Wang, J.F. Doherty and R.E. Van Dyck, “Moving Object Tracking in Video”, Proceedings of International Conference on Applied Image Pattern Recognition, pp. 95- 101, 2000.
  • C. Zhu, R. Shao, X. Zhang, S. Gao and B. Li, “Application of Virtual Reality Based on Computer Vision in Sports Posture Correction”, Wireless Communication and Mobile Computing, Vol. 2022, pp. 1-15, 2022.
  • L. Zhu, “Computer Vision-Driven Evaluation System for Assisted Decision-Making in Sports Training”, Wireless Communication and Mobile Computing, Vol. 2021, pp. 1- 15, 2021.
  • M. Buric, M. Pobar, and M. Ivasic-Kos, “Object Detection in Sports Videos”, Proceedings of International Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 1034-1039, 2018.
  • P. Salvo, A. Pingitore, A. Barbini and F. Di Francesco, “A Wearable Sweat Rate Sensor to Monitor the Athletes’ Performance During Training”, Scientific Sports, Vol. 33, No. 2, pp. 51-58, 2018.
  • M. Stein, “Bring It to the Pitch: Combining Video and Movement Data to Enhance Team Sport Analysis”, IEEE Transactions on Visualization and Computer Graphics, Vol. 24, No. 1, pp. 13-22, 2018.
  • I. McKeown, K. Taylor-McKeown, C. Woods, and N. Ball, “Athletic Ability Assessment: A Movement Assessment Protocol for Athletes”, International Journal of Sports Physical Therapy, Vol. 9, No. 7, pp. 862-873, 2014.
  • K. Rangasamy, M. A. As’ari, N. A. Rahmad, N. F. Ghazali and S. Ismail, “Deep learning in sport video analysis: a review”, Telecommunication Computer and Electronics Control, Vol. 18, No. 4, pp. 1926-1946, 2020.
  • G. Yao, T. Lei and J. Zhong, “A Review of ConvolutionalNeural-Network-based Action Recognition,” Pattern Recognition Letters, Vol. 118, pp. 14-22, 2019.
  • R.G. Abbott and L.R. Williams, “Multiple Target Tracking with Lazy Background Subtraction and Connected Components Analysis”, Machine Vision and Applications, Vol. 20, No. 2, pp. 93-101, 2009.
  • A. Lehuger, “A Robust Method for Automatic Player Detection in Sport Videos 2 System Architecture 1 Introduction 3 Training Methodology 4 Player Localization”, Analysis, Vol. 34, No. 1, pp. 1-14, 2007.
  • S. Mackowiak, M. Kurc, J. Konieczny and P. Mackowiak, “A Complex System for Football Player Detection in Broadcasted Video”, Proceedings of International Conference on Signals and Electronics Systems, pp. 119- 122, 2010.
  • D. Zhang, “Vehicle Target Detection Methods based on Color Fusion Deformable Part Model”, EURASIP Journal on Wireless Communications and Networking, Vol. 2018, No. 1, pp. 1-5, 2018.
  • V. Pallavi, J. Mukherjee, A.K. Majumdar and S. Sural, “Ball Detection from Broadcast Soccer Videos using Static and Dynamic Features”, Journal of Visual Communication and Image Representation, Vol. 19, No. 7, pp. 426-436, 2008.
  • M. Leo, P. L. Mazzeo, M. Nitti and P. Spagnolo, “Accurate Ball Detection in Soccer Images using Probabilistic Analysis of Salient Regions”, Machine Vision and Applications, Vol. 24, No. 8, pp. 1561-1574, 2013.
  • Wei-Lwun Lu, J.A. Ting, J.J. Little and K.P. Murphy, “Learning to Track and Identify Players from Broadcast Sports Videos”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 7, pp. 1704-1716, 2013.
  • M. Manafifard, H. Ebadi and H. Abrishami Moghaddam, “A Survey on Player Tracking in Soccer Videos”, Computer Vision and Image Understanding, Vol. 159, pp. 19-46, 2017.
  • A. Dhillon and G.K. Verma, “Convolutional Neural Network: A Review of Models, Methodologies and Applications to Object Detection”, Progress in Artificial Intelligence, Vol. 9, No. 2, pp. 85-112, 2020.
  • B. Dwyer and J. Nelson, “Roboflow (Version 1.0) [Software]”, Available at https://roboflow.com, Accessed at 2022.
  • J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement”, Available at https://pjreddie.com/media/files/papers/YOLOv3.pdf , Accessed at 2018.
  • J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection”, Proceedings of International Conference on Pattern Recognition, pp. 779-788, 2016.
  • J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger”, Proceedings of International Conference on Pattern Recognition, pp. 6517-6525, 2017.

Abstract Views: 161

PDF Views: 0




  • Object Detection in Hockey Sport Video via Pretrained YOLOV3 Based Deep Learning Model

Abstract Views: 161  |  PDF Views: 0

Authors

Suhas H. Patel
Department of Electronics and Communication Engineering, Gujarat Technological University, India., India
Dipesh Kamdar
Department of Electronics and Communication Engineering, V.V.P. Engineering College, India., India

Abstract


Object detection is the most common task in Sports Video Analysis. This task requires accurate object detection that can handle a variety of objects of different sizes that are partially occluded, have poor lighting, or are presented in complicated surroundings. Object in field sports includes player’s team and ball detection; this is a difficult task resulting from the rapid movement of the player and speed of the object of concern. This paper proposes a pre-trained YOLOv3, deep learningbased object detection model. We have prepared a hockey dataset consisting of four main entities: Team 1 (AUS), Team 2 (BEL), Hockey Ball, and Umpire. We constructed own dataset because there are no existing field hockey datasets available. Experimental results indicate that the pre-trained YOLOV3 deep learning model generates comparative results on this dataset by modifying the hyperparameters of this pre-trained model.

Keywords


Sport Video Analysis, Deep Learning, YOLOv1, YOLOv2, YOLOv3, Object Detection.

References