Automated Wicket-Taking Delivery Segmentation and Trajectory-Based Dismissal-Zone Analysis in Cricket Videos Using OCR-Guided YOLOv8
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917350716997632 |
|---|---|
| author | Karmoker, Joy Billah, Masum Ferdous, Mst Jannatun Islam, Akif Ameen, Mohd Ruhul Faruqe, Md. Omar |
| author_facet | Karmoker, Joy Billah, Masum Ferdous, Mst Jannatun Islam, Akif Ameen, Mohd Ruhul Faruqe, Md. Omar |
| contents | Cricket generates a rich stream of visual and contextual information, yet much of its tactical analysis still depends on slow and subjective manual review. Motivated by the need for a more efficient and data-driven alternative, this paper presents an automated approach for cricket video analysis that identifies wicket-taking deliveries, detects the pitch and ball, and models ball trajectories for post-match assessment. The proposed system combines optical character recognition (OCR) with image preprocessing techniques, including grayscale conversion, power transformation, and morphological operations, to robustly extract scorecard information and detect wicket events from broadcast videos. For visual understanding, YOLOv8 is employed for both pitch and ball detection. The pitch detection model achieved 99.5% mAP50 with a precision of 0.999, while the transfer learning-based ball detection model attained 99.18% mAP50 with 0.968 precision and 0.978 recall. Based on these detections, the system further models ball trajectories to reveal regions associated with wicket-taking deliveries, offering analytical cues for trajectory-based dismissal-zone interpretation and potential batting vulnerability assessment. Experimental results on multiple cricket match videos demonstrate the effectiveness of the proposed approach and highlight its potential for supporting coaching, tactical evaluation, and data-driven decision-making in cricket. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18405 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated Wicket-Taking Delivery Segmentation and Trajectory-Based Dismissal-Zone Analysis in Cricket Videos Using OCR-Guided YOLOv8 Karmoker, Joy Billah, Masum Ferdous, Mst Jannatun Islam, Akif Ameen, Mohd Ruhul Faruqe, Md. Omar Computer Vision and Pattern Recognition Artificial Intelligence Cricket generates a rich stream of visual and contextual information, yet much of its tactical analysis still depends on slow and subjective manual review. Motivated by the need for a more efficient and data-driven alternative, this paper presents an automated approach for cricket video analysis that identifies wicket-taking deliveries, detects the pitch and ball, and models ball trajectories for post-match assessment. The proposed system combines optical character recognition (OCR) with image preprocessing techniques, including grayscale conversion, power transformation, and morphological operations, to robustly extract scorecard information and detect wicket events from broadcast videos. For visual understanding, YOLOv8 is employed for both pitch and ball detection. The pitch detection model achieved 99.5% mAP50 with a precision of 0.999, while the transfer learning-based ball detection model attained 99.18% mAP50 with 0.968 precision and 0.978 recall. Based on these detections, the system further models ball trajectories to reveal regions associated with wicket-taking deliveries, offering analytical cues for trajectory-based dismissal-zone interpretation and potential batting vulnerability assessment. Experimental results on multiple cricket match videos demonstrate the effectiveness of the proposed approach and highlight its potential for supporting coaching, tactical evaluation, and data-driven decision-making in cricket. |
| title | Automated Wicket-Taking Delivery Segmentation and Trajectory-Based Dismissal-Zone Analysis in Cricket Videos Using OCR-Guided YOLOv8 |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.18405 |