Physical Violence Detection Based on Distributed Surveillance Cameras.
Saved in:
| Title: | Physical Violence Detection Based on Distributed Surveillance Cameras. |
|---|---|
| Authors: | Ye, Liang1,2 (AUTHOR) yeliang@hit.edu.cn, Yan, Susu1 (AUTHOR), Zhen, Jialing1 (AUTHOR), Han, Tian2,3 (AUTHOR), Ferdinando, Hany2,4 (AUTHOR), Seppänen, Tapio5 (AUTHOR), Alasaarela, Esko2 (AUTHOR) |
| Source: | Mobile Networks & Applications. Aug2022, Vol. 27 Issue 4, p1688-1699. 12p. |
| Subjects: | Human activity recognition, Surveillance detection, Television in security systems, Video surveillance, Support vector machines, Violence, Human behavior |
| Abstract: | In recent years, physical violence detection has become a research hotspot in the area of human activity recognition. With the improvement and full coverage of surveillance systems, automatic physical violence detection becomes possible, which can continuously analyze human behavior in the scene, and greatly liberate human resources. This paper proposes a physical violence detecting method based on distributed surveillance cameras. The cameras capture images, and extract human bone models with an improved OpenPose model. All the surveillance cameras form an Ad hoc network, and transfer the extracted bone models to the monitoring center. Aiming at the problem of missing bone points caused by occlusion, this paper proposes a key point filling algorithm to improve the bone models. Then the monitoring center extracts morphological features and dynamic features from the improved bone models, and filters them with an improved Relief-F algorithm. SVM (Support Vector Machine) performs classification, and gets an average recognition accuracy of 94.2%. [ABSTRACT FROM AUTHOR] |
| Copyright of Mobile Networks & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | In recent years, physical violence detection has become a research hotspot in the area of human activity recognition. With the improvement and full coverage of surveillance systems, automatic physical violence detection becomes possible, which can continuously analyze human behavior in the scene, and greatly liberate human resources. This paper proposes a physical violence detecting method based on distributed surveillance cameras. The cameras capture images, and extract human bone models with an improved OpenPose model. All the surveillance cameras form an Ad hoc network, and transfer the extracted bone models to the monitoring center. Aiming at the problem of missing bone points caused by occlusion, this paper proposes a key point filling algorithm to improve the bone models. Then the monitoring center extracts morphological features and dynamic features from the improved bone models, and filters them with an improved Relief-F algorithm. SVM (Support Vector Machine) performs classification, and gets an average recognition accuracy of 94.2%. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 1383469X |
| DOI: | 10.1007/s11036-021-01865-8 |
