딥러닝 기반의 폭력행위 감지 시스템 개발
Deep Learning based violent protest detection system
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.
Abstract
In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.
참고문헌 (21)
- "AWS(AmazonWebService)"[URL]
- "Naver about protest"[URL]
- "ChosunIlbo, ratio of demonstration"[URL]
- "Navernews research about drone"[URL]
- "CatChaser(2016)ByRobertBond Nvidia"[URL]
- SINGH, Amarjot, "Eye in the Sky: Real-time Drone Surveillance System (DSS)for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.1629~1637 (2018)
- "How To Do Real Time Object Detection OnDroneVideo Streams"[URL]
- REDMON, Joseph, "Yolov3: An incremental improvement", arXiv preprint arXiv:1804.02767, ~ (2018)
- "AWS Amazon Simple Storage Service"[URL]
- ZHANG, Jianming, "A real-time chinese traffic sign detection algorithm based on modified YOLOv2", Algorithms, 10(4), pp.127~ (2017)
- "GoogleAPI"[URL]
- "Google crawling using selenium"[URL]
- "Image capture FFmpeg"[URL]
- "Thumos Challenge2015"[URL]
- "Large Scale Visual Recognition Challenge 2014"[URL]
- SZEGEDY, Christian, "Going deeper with convolutio ns", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1~9 (2015), CVPR
- "Labeling Yolo_mark"[URL]
- REDMON, Joseph, "YOLO9000: better, faster, stronger", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.7263~7271 (2017), CVPR
- Lin, Tsung-Yi, "Feature pyramid networks for object detection", CVPR, 1(2) (2017)
- "Tistory Blog yeonsu"[URL]
- "Live streaming RTMPServer"[URL]