Optimized deep learning-based cricket activity focused network and medium scale benchmark
The recognition of different activities in sports has gained attention in recent years for its applications in various athletic events, including soccer and cricket. Cricket, in particular, presents a challenging task for automatic activity recognition methods due to its closely overlapped activitie...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016823003368 |
| _version_ | 1797803976944517120 |
|---|---|
| author | Waqas Ahmad Muhammad Munsif Habib Ullah Mohib Ullah Alhanouf Abdulrahman Alsuwailem Abdul Khader Jilani Saudagar Khan Muhammad Muhammad Sajjad |
| author_facet | Waqas Ahmad Muhammad Munsif Habib Ullah Mohib Ullah Alhanouf Abdulrahman Alsuwailem Abdul Khader Jilani Saudagar Khan Muhammad Muhammad Sajjad |
| author_sort | Waqas Ahmad |
| collection | DOAJ |
| description | The recognition of different activities in sports has gained attention in recent years for its applications in various athletic events, including soccer and cricket. Cricket, in particular, presents a challenging task for automatic activity recognition methods due to its closely overlapped activities such as cover drive, and pull short, to name a few. Existing methods often rely on hand-crafted features as the limited availability of public data has restricted the scope of research to only the significant categories of cricket activities. To this end, we proposed a cricket activities dataset and an intuitive end-to-end deep learning model for cricket activity recognition. The data is collected from online sources and pre-processed through cleaning, resizing, and organizing. Similarly, an intuitive deep model is designed with a combination of time-distributed 2D CNN layers and LSTM cells for extracting and learning the spatiotemporal information from the input sequences. For benchmarking, we evaluated the model on our cricket datasets and four standard datasets namely UCF101, HMDB51, YouTube action, and Kinetics. The quantitative results show that the proposed model outperforms different variants of recurrent neural networks and achieved an accuracy of 92%, recall of 91%, and F1 score of 91%. Our code and dataset is publicly available for further research on https://drive.google.com/file/d/1c9qcAz4q00qvx4yFA3pSudWFczm1cWUL/view?usp=sharing. |
| first_indexed | 2024-03-13T05:30:13Z |
| format | Article |
| id | doaj.art-2ba30d9ac981404da3f895ae4a2f3c6e |
| institution | Directory Open Access Journal |
| issn | 1110-0168 |
| language | English |
| last_indexed | 2024-03-13T05:30:13Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj.art-2ba30d9ac981404da3f895ae4a2f3c6e2023-06-15T04:54:20ZengElsevierAlexandria Engineering Journal1110-01682023-07-0173771779Optimized deep learning-based cricket activity focused network and medium scale benchmarkWaqas Ahmad0Muhammad Munsif1Habib Ullah2Mohib Ullah3Alhanouf Abdulrahman Alsuwailem4Abdul Khader Jilani Saudagar5Khan Muhammad6Muhammad Sajjad7Department of Computer Science, Islamia College Peshawar, 25000 Peshawar, Pakistan; Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, NorwayDepartment of Computer Science, Islamia College Peshawar, 25000 Peshawar, PakistanFaculty of Science and Technology, Norwegian University of Life Sciences, Gjøvik, NorwayDepartment of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, NorwayInformation Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaInformation Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaVIS2KNOW Lab, Department of Applied Artificial Intelligence, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, 03063 Seoul, South Korea; Corresponding authors.Department of Computer Science, Islamia College Peshawar, 25000 Peshawar, Pakistan; Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway; Corresponding authors.The recognition of different activities in sports has gained attention in recent years for its applications in various athletic events, including soccer and cricket. Cricket, in particular, presents a challenging task for automatic activity recognition methods due to its closely overlapped activities such as cover drive, and pull short, to name a few. Existing methods often rely on hand-crafted features as the limited availability of public data has restricted the scope of research to only the significant categories of cricket activities. To this end, we proposed a cricket activities dataset and an intuitive end-to-end deep learning model for cricket activity recognition. The data is collected from online sources and pre-processed through cleaning, resizing, and organizing. Similarly, an intuitive deep model is designed with a combination of time-distributed 2D CNN layers and LSTM cells for extracting and learning the spatiotemporal information from the input sequences. For benchmarking, we evaluated the model on our cricket datasets and four standard datasets namely UCF101, HMDB51, YouTube action, and Kinetics. The quantitative results show that the proposed model outperforms different variants of recurrent neural networks and achieved an accuracy of 92%, recall of 91%, and F1 score of 91%. Our code and dataset is publicly available for further research on https://drive.google.com/file/d/1c9qcAz4q00qvx4yFA3pSudWFczm1cWUL/view?usp=sharing.http://www.sciencedirect.com/science/article/pii/S1110016823003368Activity recognitionCricket sports activitiesConvolutional neural networkSequence learningSpatiotemporal network |
| spellingShingle | Waqas Ahmad Muhammad Munsif Habib Ullah Mohib Ullah Alhanouf Abdulrahman Alsuwailem Abdul Khader Jilani Saudagar Khan Muhammad Muhammad Sajjad Optimized deep learning-based cricket activity focused network and medium scale benchmark Alexandria Engineering Journal Activity recognition Cricket sports activities Convolutional neural network Sequence learning Spatiotemporal network |
| title | Optimized deep learning-based cricket activity focused network and medium scale benchmark |
| title_full | Optimized deep learning-based cricket activity focused network and medium scale benchmark |
| title_fullStr | Optimized deep learning-based cricket activity focused network and medium scale benchmark |
| title_full_unstemmed | Optimized deep learning-based cricket activity focused network and medium scale benchmark |
| title_short | Optimized deep learning-based cricket activity focused network and medium scale benchmark |
| title_sort | optimized deep learning based cricket activity focused network and medium scale benchmark |
| topic | Activity recognition Cricket sports activities Convolutional neural network Sequence learning Spatiotemporal network |
| url | http://www.sciencedirect.com/science/article/pii/S1110016823003368 |
| work_keys_str_mv | AT waqasahmad optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT muhammadmunsif optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT habibullah optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT mohibullah optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT alhanoufabdulrahmanalsuwailem optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT abdulkhaderjilanisaudagar optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT khanmuhammad optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark AT muhammadsajjad optimizeddeeplearningbasedcricketactivityfocusednetworkandmediumscalebenchmark |