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
  • [41] Reconfigurable Pedestrian Detection System Using Deep Learning for Video Surveillance
    Jeevarajan, M. K.
    Kumar, P. Nirmal
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2023, E106D (09) : 1610 - 1614
  • [42] Federated learning based intelligent edge computing technique for video surveillance
    Zhao Y.
    Yang J.
    Liu M.
    Sun J.
    Gui G.
    1600, Editorial Board of Journal on Communications (41): : 109 - 115
  • [43] A real time crime scene intelligent video surveillance systems in violence detection framework using deep learning techniques
    Sahay, Kishan Bhushan
    Balachander, Bhuvaneswari
    Jagadeesh, B.
    Kumar, G. Anand
    Kumar, Ravi
    Parvathy, L. Rama
    COMPUTERS & ELECTRICAL ENGINEERING, 2022, 103
  • [44] Abnormal Motion Detection for Intelligent Video Surveillance
    Huan, Ruohong
    Tang, Xiaomei
    Wang, Zhehu
    Chen, Qingzhang
    INFORMATION TECHNOLOGY FOR MANUFACTURING SYSTEMS II, PTS 1-3, 2011, 58-60 : 2290 - 2295
  • [45] Intelligent Video Surveillance System Based on Moving Object Detection and Tracking
    Miao, Zhuang
    Zou, Shan
    Li, Yang
    Zhang, Xiancai
    Wang, Jiabao
    He, Ming
    2016 INTERNATIONAL CONFERENCE ON INFORMATION ENGINEERING AND COMMUNICATIONS TECHNOLOGY (IECT 2016), 2016, : 388 - 391
  • [46] Motion detection based multimedia supported intelligent video surveillance system
    Zeljkovic, V.
    Pokrajac, D.
    PROCEEDINGS ELMAR-2006, 2006, : 49 - +
  • [47] AN INTELLIGENT EVENT DETECTION AND ALARM BASED SURVEILLANCE ALGORITHM FOR VIDEO SUMMARIZATION
    Javed, Ali
    Noman, Sidra
    4TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER THEORY AND ENGINEERING ( ICACTE 2011), 2011, : 817 - 821
  • [48] Deep Learning Technique Based Surveillance Video Analysis for the Store
    Xu, Qingyang
    Zheng, Wanqiang
    Liu, Xiaoxiao
    Jing, Punan
    APPLIED ARTIFICIAL INTELLIGENCE, 2020, 34 (14) : 1055 - 1073
  • [49] Estimation of body occlusion using deep learning for advanced intelligent video surveillance system
    Nagayama I.
    Iwanaga T.
    Uehara W.
    Miyazato T.
    Nagayama, Itaru (nagayama@ie.uryukyu.ac.jp), 1600, Institute of Electrical Engineers of Japan (141): : 138 - 146
  • [50] Design of an intelligent video surveillance system for crime prevention: applying deep learning technology
    Sung, Chang-Soo
    Park, Joo Yeon
    MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (26-27) : 34297 - 34309