Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier
This paper presents an advanced approach to Human Pose Estimation (HPE) and Semantic Event Classification (SEC), emphasizing the need for sophisticated human skeleton models, context-aware feature extraction, and machine learning techniques for precise event recognition in daily life logs. HPE, cruc...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10752949/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850115301086068736 |
|---|---|
| author | Wasim Wahid Aisha Ahmed AlArfaj Ebtisam Abdullah Alabdulqader Touseef Sadiq Hameedur Rahman Ahmad Jalal |
| author_facet | Wasim Wahid Aisha Ahmed AlArfaj Ebtisam Abdullah Alabdulqader Touseef Sadiq Hameedur Rahman Ahmad Jalal |
| author_sort | Wasim Wahid |
| collection | DOAJ |
| description | This paper presents an advanced approach to Human Pose Estimation (HPE) and Semantic Event Classification (SEC), emphasizing the need for sophisticated human skeleton models, context-aware feature extraction, and machine learning techniques for precise event recognition in daily life logs. HPE, crucial in applications like sports analysis and surveillance systems, involves predicting human joint locations from images and videos. Recent deep learning advancements have significantly improved HPE, particularly in crowded scenes and occlusion challenges. Despite many surveys, a comprehensive review of HPE, especially with recent deep learning innovations, is still needed. Our research addresses this by proposing a novel HPE and SEC system. The system begins with preprocessing steps, including converting videos into image sequences, applying sliding window techniques, and converting images to grayscale, then extracting human silhouettes using binary masks. We use the GrabCut algorithm for human detection and perform skeletonization with Hough transform algorithm. Keypoint detection is achieved through pose estimation, and full-body feature extraction includes using OpenPose for movable body parts, the Lucas-Kanade method for a 3D Cartesian view, and Texton Map techniques. Key point features are further characterized using motion histograms, pose landmark visualization and Local Intensity Order Pattern (LIOP) features. The system is optimized with adaptive moment estimations and classified using the XGBoost Classifier. Evaluation on the COCO, UCF50, and YouTube datasets showed classification accuracies of 92.90%, 90.9%, and 91.2%, respectively, demonstrating our approach’s superior performance and effectiveness compared to existing state-of-the-art techniques. |
| format | Article |
| id | doaj-art-e2cfa2a3516e4ac98b258ac8012410e3 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-e2cfa2a3516e4ac98b258ac8012410e32025-08-20T02:36:35ZengIEEEIEEE Access2169-35362024-01-011217983917985610.1109/ACCESS.2024.349809310752949Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost ClassifierWasim Wahid0Aisha Ahmed AlArfaj1https://orcid.org/0000-0002-5078-2579Ebtisam Abdullah Alabdulqader2https://orcid.org/0000-0002-8539-5560Touseef Sadiq3https://orcid.org/0000-0001-6603-3639Hameedur Rahman4https://orcid.org/0000-0001-8892-9911Ahmad Jalal5https://orcid.org/0009-0000-8421-8477Faculty of Computing and AI, Air University, Islamabad, PakistanDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi ArabiaComputer Science Department, College of Art and Humanities Sciences, Qassim University, Buraydah, Saudi ArabiaDepartment of Information and Communication Technology, Centre for Artificial Intelligence Research, University of Agder, Grimstad, NorwayFaculty of Computing and AI, Air University, Islamabad, PakistanFaculty of Computing and AI, Air University, Islamabad, PakistanThis paper presents an advanced approach to Human Pose Estimation (HPE) and Semantic Event Classification (SEC), emphasizing the need for sophisticated human skeleton models, context-aware feature extraction, and machine learning techniques for precise event recognition in daily life logs. HPE, crucial in applications like sports analysis and surveillance systems, involves predicting human joint locations from images and videos. Recent deep learning advancements have significantly improved HPE, particularly in crowded scenes and occlusion challenges. Despite many surveys, a comprehensive review of HPE, especially with recent deep learning innovations, is still needed. Our research addresses this by proposing a novel HPE and SEC system. The system begins with preprocessing steps, including converting videos into image sequences, applying sliding window techniques, and converting images to grayscale, then extracting human silhouettes using binary masks. We use the GrabCut algorithm for human detection and perform skeletonization with Hough transform algorithm. Keypoint detection is achieved through pose estimation, and full-body feature extraction includes using OpenPose for movable body parts, the Lucas-Kanade method for a 3D Cartesian view, and Texton Map techniques. Key point features are further characterized using motion histograms, pose landmark visualization and Local Intensity Order Pattern (LIOP) features. The system is optimized with adaptive moment estimations and classified using the XGBoost Classifier. Evaluation on the COCO, UCF50, and YouTube datasets showed classification accuracies of 92.90%, 90.9%, and 91.2%, respectively, demonstrating our approach’s superior performance and effectiveness compared to existing state-of-the-art techniques.https://ieeexplore.ieee.org/document/10752949/Pose estimationevent recognitionremote sensingmulti-level feature extractionLucas-Kanadeskeletonization |
| spellingShingle | Wasim Wahid Aisha Ahmed AlArfaj Ebtisam Abdullah Alabdulqader Touseef Sadiq Hameedur Rahman Ahmad Jalal Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier IEEE Access Pose estimation event recognition remote sensing multi-level feature extraction Lucas-Kanade skeletonization |
| title | Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier |
| title_full | Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier |
| title_fullStr | Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier |
| title_full_unstemmed | Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier |
| title_short | Advanced Human Pose Estimation and Event Classification Using Context-Aware Features and XGBoost Classifier |
| title_sort | advanced human pose estimation and event classification using context aware features and xgboost classifier |
| topic | Pose estimation event recognition remote sensing multi-level feature extraction Lucas-Kanade skeletonization |
| url | https://ieeexplore.ieee.org/document/10752949/ |
| work_keys_str_mv | AT wasimwahid advancedhumanposeestimationandeventclassificationusingcontextawarefeaturesandxgboostclassifier AT aishaahmedalarfaj advancedhumanposeestimationandeventclassificationusingcontextawarefeaturesandxgboostclassifier AT ebtisamabdullahalabdulqader advancedhumanposeestimationandeventclassificationusingcontextawarefeaturesandxgboostclassifier AT touseefsadiq advancedhumanposeestimationandeventclassificationusingcontextawarefeaturesandxgboostclassifier AT hameedurrahman advancedhumanposeestimationandeventclassificationusingcontextawarefeaturesandxgboostclassifier AT ahmadjalal advancedhumanposeestimationandeventclassificationusingcontextawarefeaturesandxgboostclassifier |