Towards Scalable Abnormal Behavior Detection in Automated Surveillance
| Autor: | Herman G.J. Groot, Tunc Alkanat, Egor Bondarev, Matthijs H. Zwemer, Peter H.N. de |
|---|---|
| Přispěvatelé: | Video Coding & Architectures, EAISI Health, EAISI High Tech Systems |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Focus (computing)
rechtvaardigheid en sterke instellingen Surveillance SDG 16 - Peace Situation awareness Computer science business.industry SDG 16 – Vrede Deep learning Video surveillance Feature extraction SDG 16 - Peace Justice and Strong Institutions Object (computer science) Re-ID Abnormal behavior analysis Justice and Strong Institutions Human–computer interaction Scalability Investment cost Artificial intelligence Abnormality business Real-time systems |
| Zdroj: | Proceedings-2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021, 21-24 STARTPAGE=21;ENDPAGE=24;TITLE=Proceedings-2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021 AI4I |
| Popis: | This study presents a scalable automated video surveillance framework that (1) automatically detects the occurrences of abnormal behavior patterns by both pedestrians and vehicles, and (2) directs the focus of the security personnel to the relevant camera view, thereby providing global situational awareness. Powered by deep learning, our methodology can detect both vision and location-based abnormalities, including the events of vandalism, violence, loitering, scouting, and speeding. The proposed framework requires a low initial investment cost and features both real-time detection of various abnormal behaviors and post-crime analysis in scalable form, by enabling wide-area multi-camera networks with person/object re-identification. By combining multiple functionalities in an efficient framework, the proposed system opens up new possibilities for surveillance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|