Entropy-Aware Activity Recognition for Sports: Case Study on Cricket

Abstract

In the digital era, activity recognition substantially impacts everyone’s day-to-day lives. Multiple people and their activities can be seen in the video, and their routines depend on video devices, specifically in sports. Video datasets in sports face several challenges, such as intra-class similarity, inter-class ambiguity, noise and motion transitions. The research proposed an entropy-aware deep learning method for activity recognition that integrates a pre-trained CNN with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for Cricket keyframe selection. A synthesized dataset of 25,000 annotated cricket clips is generated across five fine-grained activity classes. These keyframes are uniformly sampled, encoded into CNN embeddings, and clustered using DBSCAN. The chosen keyframes are then fine-tuned using a CNN to optimize using categorical cross-entropy loss. The extensive experiments show that the proposed method achieves an accuracy of 96.4% and provides a reliable 6% improvement over unclustered data. The findings show that frame selection using DBSCAN improves generalization across a variety of broadcasting conditions and provides a scalable framework for automated cricket video analysis, with real-time applications in highlight generation, intelligent sports surveillance, and player performance monitoring.

Keywords

• Activity recognition
• DBSCAN
• Deep learning
• Entropy
• Spatial clustering

Ethical Statement

This study does not involve any human or animal participants and does not require ethical committee approval. It is declared that during the preparation process of this study, scientific and ethical principles were followed, and all the studies benefited from are stated in the bibliography.

References

1. P. Narwal, N. Duhan, and K. K. Bhatia, “Dynamic and personalized video summarization towards sports entertainment,” Entertain. Comput., Art. no. 100999, 2025.
2. K. Jiang, “Optimization study of badminton sports training system based on MobileNet OpenPose lightweight human posture estimation model,” Entertain. Comput., Art. no. 100975, 2025.
3. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 770–778, 2016.
4. J. Liu, “Application of entertainment and fitness robots based on game interaction in sports training data analysis,” Entertain. Comput., vol. 52, Art. no. 100837, 2025.
5. K. Singh and A. S. Parihar, “BFF: Bi-stream feature fusion for object detection in hazy environment,” Signal Image Video Process., vol. 18, no. 4, pp. 3097–3107, 2024.
6. M. A. Ansari, D. K. Singh, and V. P. Singh, “Detecting abnormal behavior in megastore for crime prevention using a deep neural architecture,” Int. J. Multimedia Inf. Retrieval, vol. 12, no. 2, Art. no. 25, 2023.
7. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 25, 2012.
8. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,”, arXiv:1409.1556, 2014.

9. G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 4700–4708, 2017.
10. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 248–255, 2009.
11. N. Dhanachandra, K. Manglem, and Y. J. Chanu, “Image segmentation using K-means clustering algorithm and subtractive clustering algorithm,” Procedia Comput. Sci., vol. 54, pp. 764–771, 2015.
12. D. Deng, “DBSCAN clustering algorithm based on density,” in Proc. 7th Int. Forum Electr. Eng. Autom. (IFEEA), pp. 949–953, 2020.
13. T. Tsunoda, Y. Komori, M. Matsugu, and T. Harada, “Football action recognition using hierarchical LSTM,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), pp. 99–107, 2017.
14. I. A. Showmik, T. F. Sanam, and H. Imtiaz, “Human activity recognition from Wi-Fi CSI data using principal component-based wavelet CNN,” Digit. Signal Process., vol. 138, Art. no. 104056, 2023.
15. D. Wang, W. Xie, Y. Cai, and X. Liu, “Adaptive data augmentation network for human pose estimation,” Digit. Signal Process., vol. 129, Art. no. 103681, 2022.
16. M. Tabish, Z.-u.-R. Tanooli, and M. Shaheen, “Activity recognition framework in sports videos,” Multimedia Tools Appl., vol. 83, no. 5, pp. 15101–15123, 2024.
17. K. Simonyan and A. Zisserman, “Two-stream convolutional networks for action recognition in videos,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 27, 2014.
18. D. Tran, L. Bourdev, R. Fergus, L. Torresani, and M. Paluri, “Learning spatiotemporal features with 3D convolutional networks,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 4489–4497, 2015.
19. J. Carreira and A. Zisserman, “Quo vadis, action recognition? A new model and the Kinetics dataset,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 6299–6308, 2017.
20. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) , pp. 2818–2826, 2016.
21. U. Kazemi and S. Soleimani, “A new approach data processing: Density-based spatial clustering of applications with noise (DBSCAN) clustering using game-theory,” Soft Comput., vol. 29, no. 3, pp. 1331–1346, 2025.
22. R. Hari and M. Wilscy, “Event detection in cricket videos using intensity projection profile of umpire gestures,” in Proc. IEEE India Conf. (INDICON), pp. 1–6, 2014.
23. R. Singh and A. Sharma, “Occluded skeleton-based multi-stream model using Part-Aware Spatial–Temporal Graph Convolutional Network for human activity recognition,” Eng. Appl. Artif. Intell., vol. 156, Art. no. 111183, 2025.