Semantic object detection for human activity monitoring system
Semantic object detection is significant for activity monitoring system. Any abnormalities occurred in a monitored area can be detected by applying semantic object detection that determines any displaced objects in the monitored area. Many approaches are being made nowadays towards better semantic o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Electronic and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka (UTeM)
2018
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/2876/ http://eprints.uthm.edu.my/2876/1/AJ%202019%20%2853%29.pdf |
| _version_ | 1848887865500499968 |
|---|---|
| author | Suriani, Nor Surayahani Nor Rashid, Fadilla ‘Atyka Badrul, Mohd Hafizrul |
| author_facet | Suriani, Nor Surayahani Nor Rashid, Fadilla ‘Atyka Badrul, Mohd Hafizrul |
| author_sort | Suriani, Nor Surayahani |
| building | UTHM Institutional Repository |
| collection | Online Access |
| description | Semantic object detection is significant for activity monitoring system. Any abnormalities occurred in a monitored area can be detected by applying semantic object detection that determines any displaced objects in the monitored area. Many approaches are being made nowadays towards better semantic object detection methods, but the approaches are either resource consuming such as using sensors that are costly or restricted to certain scenarios and background only. We assume that the scale structures and velocity can be estimated to define a different state of activity. This project proposes Histogram of Oriented Gradient (HOG) technique to extract feature points of semantic objects in the monitored area while Histogram of Oriented Optical Flow (HOOF) technique is used to annotate the current state of the semantic object that having human-and-object interaction. Both passive and active objects are extracted using HOG, and HOOF descriptor indicate the time series status of the spatial and orientation of the semantic object. Support Vector Machine technique uses the predictors to train and test the input video and classify the processed dataset to its respective activity class. We evaluate our approach to recognise human actions in several scenarios and achieve 89% accuracy with 11.3% error rate. |
| first_indexed | 2025-11-15T20:01:11Z |
| format | Article |
| id | uthm-2876 |
| institution | Universiti Tun Hussein Onn Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:01:11Z |
| publishDate | 2018 |
| publisher | Faculty of Electronic and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka (UTeM) |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uthm-28762021-11-16T03:48:28Z http://eprints.uthm.edu.my/2876/ Semantic object detection for human activity monitoring system Suriani, Nor Surayahani Nor Rashid, Fadilla ‘Atyka Badrul, Mohd Hafizrul TA168 Systems engineering Semantic object detection is significant for activity monitoring system. Any abnormalities occurred in a monitored area can be detected by applying semantic object detection that determines any displaced objects in the monitored area. Many approaches are being made nowadays towards better semantic object detection methods, but the approaches are either resource consuming such as using sensors that are costly or restricted to certain scenarios and background only. We assume that the scale structures and velocity can be estimated to define a different state of activity. This project proposes Histogram of Oriented Gradient (HOG) technique to extract feature points of semantic objects in the monitored area while Histogram of Oriented Optical Flow (HOOF) technique is used to annotate the current state of the semantic object that having human-and-object interaction. Both passive and active objects are extracted using HOG, and HOOF descriptor indicate the time series status of the spatial and orientation of the semantic object. Support Vector Machine technique uses the predictors to train and test the input video and classify the processed dataset to its respective activity class. We evaluate our approach to recognise human actions in several scenarios and achieve 89% accuracy with 11.3% error rate. Faculty of Electronic and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka (UTeM) 2018 Article PeerReviewed text en http://eprints.uthm.edu.my/2876/1/AJ%202019%20%2853%29.pdf Suriani, Nor Surayahani and Nor Rashid, Fadilla ‘Atyka and Badrul, Mohd Hafizrul (2018) Semantic object detection for human activity monitoring system. Journal of Telecommunication, Electronic and Computer Engineering, 10 (2-5). pp. 115-118. ISSN 2289-8131 https://jtec.utem.edu.my/jtec/article/view/4395 |
| spellingShingle | TA168 Systems engineering Suriani, Nor Surayahani Nor Rashid, Fadilla ‘Atyka Badrul, Mohd Hafizrul Semantic object detection for human activity monitoring system |
| title | Semantic object detection for human activity monitoring system |
| title_full | Semantic object detection for human activity monitoring system |
| title_fullStr | Semantic object detection for human activity monitoring system |
| title_full_unstemmed | Semantic object detection for human activity monitoring system |
| title_short | Semantic object detection for human activity monitoring system |
| title_sort | semantic object detection for human activity monitoring system |
| topic | TA168 Systems engineering |
| url | http://eprints.uthm.edu.my/2876/ http://eprints.uthm.edu.my/2876/ http://eprints.uthm.edu.my/2876/1/AJ%202019%20%2853%29.pdf |