Abstract
Automatic violence detection in video surveillance is essential for social and personal security. Monitoring the large number of surveillance cameras used in public and private areas is challenging for human operators. The manual nature of this task significantly increases the possibility of ignoring important events due to human limitations when paying attention to multiple targets at a time. Researchers have proposed several methods to detect violent events automatically to overcome this problem. So far, most previous studies have focused only on classifying short clips without performing spatial localization. In this work, we tackle this problem by proposing a weakly supervised method to detect spatially and temporarily violent actions in surveillance videos using only video-level labels. The proposed method follows a Fast-RCNN style architecture, that has been temporally extended. First, we generate spatiotemporal proposals (action tubes) leveraging pre-trained person detectors, motion appearance (dynamic images), and tracking algorithms. Then, given an input video and the action proposals, we extract spatiotemporal features using deep neural networks. Finally, a classifier based on multiple-instance learning is trained to label each action tube as violent or non-violent. We obtain similar results to the state of the art in three public databases Hockey Fight, RLVSD, and RWF-2000, achieving an accuracy of 97.3%, 92.88%, 88.7%, respectively.
Funder
Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference92 articles.
1. Action recognition and localization with spatial and temporal contexts;Wanru;Neurocomputing,2019
2. Holistic object detection and image understanding
3. Real-World Anomaly Detection in Surveillance Videos;Sultani;Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR),2018
4. The MediaEval 2013 Affect Task: Violent Scenes Detection;Demarty;Proceedings of the MediaEval 2013 Workshop,2013
5. Temporal Robust Features for Violence Detection;Moreira;Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV),2017
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献