Distributed Intelligent Video Surveillance for Early Armed Robbery Detection based on Deep Learning

被引:0
|
作者
Fernandez-Testa, Sergio [1 ]
Salcedo, Edwin [1 ]
机构
[1] Univ Catolica Boliviana San Pablo, Ctr Invest Desarrollo & Innovac Ingn Mecatron, La Paz, Bolivia
关键词
D O I
10.1109/SIBGRAPI62404.2024.10716299
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Low employment rates in Latin America have contributed to a substantial rise in crime, prompting the emergence of new criminal tactics. For instance, "express robbery" has become a common crime committed by armed thieves, in which they drive motorcycles and assault people in public in a matter of seconds. Recent research has approached the problem by embedding weapon detectors in surveillance cameras; however, these systems are prone to false positives if no counterpart confirms the event. In light of this, we present a distributed IoT system that integrates a computer vision pipeline and object detection capabilities into multiple end-devices, constantly monitoring for the presence of firearms and sharp weapons. Once a weapon is detected, the end-device sends a series of frames to a cloud server that implements a 3DCNN to classify the scene as either a robbery or a normal situation, thus minimizing false positives. The deep learning process to train and deploy weapon detection models uses a custom dataset with 16,799 images of firearms and sharp weapons. The best-performing model, YOLOv5s, optimized using TensorRT, achieved a final mAP of 0.87 running at 4.43 FPS. Additionally, the 3DCNN demonstrated 0.88 accuracy in detecting abnormal situations. Extensive experiments validate that the proposed system significantly reduces false positives while autonomously monitoring multiple locations in real-time.
引用
收藏
页码:103 / 108
页数:6
相关论文
共 50 条
  • [1] Intelligent monitoring of indoor surveillance video based on deep learning
    Liu, Yun-Xia
    Yang, Yang
    Shi, Aijun
    Peng Jigang
    Liu Haowei
    2019 21ST INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY (ICACT): ICT FOR 4TH INDUSTRIAL REVOLUTION, 2019, : 648 - 653
  • [2] DESIGN OF INTELLIGENT VIDEO SURVEILLANCE SYSTEM FOR INTELLIGENT ORCHARD BASED ON DEEP LEARNING NETWORK
    Liu, Yangyang
    Yin, NiuNiu
    Sun, Yan
    Chen, Leijing
    Meng, Fansheng
    Zhang, Pengyang
    Ren, Huimin
    Feng, Ruizhuo
    UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2023, 85 (01): : 181 - 196
  • [3] DESIGN OF INTELLIGENT VIDEO SURVEILLANCE SYSTEM FOR INTELLIGENT ORCHARD BASED ON DEEP LEARNING NETWORK
    Liu, Yangyang
    Yin, Niuniu
    Sun, Yan
    Chen, Leijing
    Meng, Fansheng
    Zhang, Pengyang
    Ren, Huimin
    Feng, Ruizhuo
    UPB Scientific Bulletin, Series C: Electrical Engineering and Computer Science, 2023, 85 (01): : 181 - 196
  • [4] Deep Learning based Moving Object Detection for Video Surveillance
    Huang, Han-Yi
    Lin, Chih-Yang
    Lin, Wei-Yang
    Lee, Chien-Cheng
    Chang, Chuan-Yu
    2019 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TW), 2019,
  • [5] Abnormal Event Detection Using Deep Contrastive Learning for Intelligent Video Surveillance System
    Huang, Chao
    Wu, Zhihao
    Wen, Jie
    Xu, Yong
    Jiang, Qiuping
    Wang, Yaowei
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (08) : 5171 - 5179
  • [6] Deep Reinforcement Learning-based Anomaly Detection for Video Surveillance
    Aberkane, Sabrina
    Elarbi-Boudihir, Mohamed
    INFORMATICA-AN INTERNATIONAL JOURNAL OF COMPUTING AND INFORMATICS, 2022, 46 (02): : 291 - 298
  • [7] Deep Learning-Based Anomaly Detection in Video Surveillance: A Survey
    Duong, Huu-Thanh
    Le, Viet-Tuan
    Hoang, Vinh Truong
    SENSORS, 2023, 23 (11)
  • [8] A Suvey on Edge Intelligent Video Surveillance with Deep Reinforcement Learning
    Li, Yan
    Journal of Network Intelligence, 2022, 7 (01): : 70 - 83
  • [9] A deep learning approach to building an intelligent video surveillance system
    Jie Xu
    Multimedia Tools and Applications, 2021, 80 : 5495 - 5515
  • [10] A deep learning approach to building an intelligent video surveillance system
    Xu, Jie
    MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (04) : 5495 - 5515