文献类型：期刊文献

英文题名：Violence detection and face recognition based on deep learning

作者：Wang, Pin[1];Wang, Peng[2];Fan, En[3]

机构：[1]Shenzhen Polytech, Sch Mech & Elect Engn, Shenzhen 518055, Guangdong, Peoples R China;[2]Chinese Acad Sci, South China Bot Garden, Garden Ctr, Guangzhou 510650, Guangdong, Peoples R China;[3]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Zhejiang, Peoples R China

年份：2021

卷号：142

起止页码：20

外文期刊名：PATTERN RECOGNITION LETTERS

收录：SCI-EXPANDED(收录号：WOS:000613175200004)、、EI(收录号：20205209694587)、Scopus(收录号：2-s2.0-85098180549)、WOS

基金：This work was supported by National Natural Science Foundation of China under Grant 61703280.

语种：英文

外文关键词：Deep learning; Brute force detection; Face recognition; Convolutional neural network; Video surveillance

外文摘要：With the emergence of the concept of "safe city", security construction has gradually been valued by various cities, and video surveillance technology has also been continuously developed and applied. However, as the functional requirements of actual applications become more and more diverse, video surveillance systems also need to be more intelligent. The purpose of this article is to study methods of brute force detection and face recognition based on deep learning. Aiming at the problem of abnormal behavior detection, especially the low efficiency and low accuracy of brute force detection, a brute force detection method based on the combination of convolutional neural network and trajectory is proposed. This method uses artificial features and depth features to extract the spatiotemporal features of the video through a convolutional neural network and combines them with the trajectory features. In view of the problem that face images in surveillance video cannot be accurately recognized due to low resolution, two models are proposed: the multi-foot input CNN model and the SPP-based CNN model. By testing the performance of the brute force detection method proposed in this paper, the accuracy of the method on the Crow and Hockey datasets is as high as 92% and 97.6%, respectively. Experimental results show that the violence detection method proposed in this paper improves the accuracy of violence detection in video. (c) 2020 Elsevier B.V. All rights reserved.