A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier
This paper presents an approach for event recognition in sequential images using human body part features and their surrounding context. Key body points were approximated to track and monitor their presence in complex scenarios. Various feature descriptors, including MSER (Maximally Stable Extremal...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/441 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587478614147072 |
|---|---|
| author | Muhammad Tayyab Sulaiman Abdullah Alateyah Mohammed Alnusayri Mohammed Alatiyyah Dina Abdulaziz AlHammadi Ahmad Jalal Hui Liu |
| author_facet | Muhammad Tayyab Sulaiman Abdullah Alateyah Mohammed Alnusayri Mohammed Alatiyyah Dina Abdulaziz AlHammadi Ahmad Jalal Hui Liu |
| author_sort | Muhammad Tayyab |
| collection | DOAJ |
| description | This paper presents an approach for event recognition in sequential images using human body part features and their surrounding context. Key body points were approximated to track and monitor their presence in complex scenarios. Various feature descriptors, including MSER (Maximally Stable Extremal Regions), SURF (Speeded-Up Robust Features), distance transform, and DOF (Degrees of Freedom), were applied to skeleton points, while BRIEF (Binary Robust Independent Elementary Features), HOG (Histogram of Oriented Gradients), FAST (Features from Accelerated Segment Test), and Optical Flow were used on silhouettes or full-body points to capture both geometric and motion-based features. Feature fusion was employed to enhance the discriminative power of the extracted data and the physical parameters calculated by different feature extraction techniques. The system utilized a hybrid CNN (Convolutional Neural Network) + RNN (Recurrent Neural Network) classifier for event recognition, with Grey Wolf Optimization (GWO) for feature selection. Experimental results showed significant accuracy, achieving 98.5% on the UCF-101 dataset and 99.2% on the YouTube dataset. Compared to state-of-the-art methods, our approach achieved better performance in event recognition. |
| format | Article |
| id | doaj-art-16c4c801a7f84356aa93022fa6b3fcfc |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-16c4c801a7f84356aa93022fa6b3fcfc2025-01-24T13:48:56ZengMDPI AGSensors1424-82202025-01-0125244110.3390/s25020441A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning ClassifierMuhammad Tayyab0Sulaiman Abdullah Alateyah1Mohammed Alnusayri2Mohammed Alatiyyah3Dina Abdulaziz AlHammadi4Ahmad Jalal5Hui Liu6Department of Computer Science, Air University, Islamabad 44000, PakistanDepartment of Computer Engineering, College of Computer, Qassim University, Buraydah 52571, Saudi ArabiaDepartment of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72388, Saudi ArabiaDepartment of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 16278, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaDepartment of Computer Science, Air University, Islamabad 44000, PakistanCognitive Systems Lab, University of Bremen, 28359 Bremen, GermanyThis paper presents an approach for event recognition in sequential images using human body part features and their surrounding context. Key body points were approximated to track and monitor their presence in complex scenarios. Various feature descriptors, including MSER (Maximally Stable Extremal Regions), SURF (Speeded-Up Robust Features), distance transform, and DOF (Degrees of Freedom), were applied to skeleton points, while BRIEF (Binary Robust Independent Elementary Features), HOG (Histogram of Oriented Gradients), FAST (Features from Accelerated Segment Test), and Optical Flow were used on silhouettes or full-body points to capture both geometric and motion-based features. Feature fusion was employed to enhance the discriminative power of the extracted data and the physical parameters calculated by different feature extraction techniques. The system utilized a hybrid CNN (Convolutional Neural Network) + RNN (Recurrent Neural Network) classifier for event recognition, with Grey Wolf Optimization (GWO) for feature selection. Experimental results showed significant accuracy, achieving 98.5% on the UCF-101 dataset and 99.2% on the YouTube dataset. Compared to state-of-the-art methods, our approach achieved better performance in event recognition.https://www.mdpi.com/1424-8220/25/2/441machine learningsilhouettesextremal regionsjoint pointsscalable key points |
| spellingShingle | Muhammad Tayyab Sulaiman Abdullah Alateyah Mohammed Alnusayri Mohammed Alatiyyah Dina Abdulaziz AlHammadi Ahmad Jalal Hui Liu A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier Sensors machine learning silhouettes extremal regions joint points scalable key points |
| title | A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier |
| title_full | A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier |
| title_fullStr | A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier |
| title_full_unstemmed | A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier |
| title_short | A Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier |
| title_sort | hybrid approach for sports activity recognition using key body descriptors and hybrid deep learning classifier |
| topic | machine learning silhouettes extremal regions joint points scalable key points |
| url | https://www.mdpi.com/1424-8220/25/2/441 |
| work_keys_str_mv | AT muhammadtayyab ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT sulaimanabdullahalateyah ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT mohammedalnusayri ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT mohammedalatiyyah ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT dinaabdulazizalhammadi ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT ahmadjalal ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT huiliu ahybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT muhammadtayyab hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT sulaimanabdullahalateyah hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT mohammedalnusayri hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT mohammedalatiyyah hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT dinaabdulazizalhammadi hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT ahmadjalal hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier AT huiliu hybridapproachforsportsactivityrecognitionusingkeybodydescriptorsandhybriddeeplearningclassifier |