Identification of Antisocial Activities in Surveillance Monitoring Systems using Advanced-CNN based Techniques

DOI

10.2991/978-94-6239-618-0_7How to use a DOI?

Keywords

Deep Learning; Machine Learning; YOLOv11; DCNv3; Multi-Class Threat Detection; IOU; Object Detection; Smart Cities; Surveillance; Real-Time Systems

Abstract

This research introduces a deep learning system that helps detect emergencies and dangerous events in real time. The system can detect threats and activities such as violence, fires, accidents, and weapons like guns and knives, using live video feed from CCTV Cameras. The model uses the sophisticated YOLOv11 combined with Deformable Convolution Networks (DCNv3) for better detection in complex and crowded scenes. It works on transfer learning, where the model is trained on more than 18000 images which covers many public safety situations. It has been demonstrated that this approach is more precise, quicker, and more dependable than the previous versions of YOLO, particularly in strenuous circumstances. This system allows making cities safer and enables faster emergency response by minimizing the number of human monitors required and will allow the system to be easily expanded.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kunj Agarwal
AU  - Yagyansh Singh Deshwal
AU  - Sparsh Pandey
AU  - Vikas Srivastava
PY  - 2026
DA  - 2026/03/16
TI  - Identification of Antisocial Activities in Surveillance Monitoring Systems using Advanced-CNN based Techniques
BT  - Proceedings of 3rd International Conference on Library & Technology on “Artificial Intelligence and Humanities in Library and Education 4.0 (AIHLE 2025)
PB  - Atlantis Press
SP  - 89
EP  - 100
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-618-0_7
DO  - 10.2991/978-94-6239-618-0_7
ID  - Agarwal2026
ER  -