Lightweight mobile network for real-time violence recognition

Abstract

Most existing violence recognition methods have complex network structures and high cost of computation and cannot meet the requirements of large-scale deployment. The purpose of this paper is to reduce the complexity of the model to realize the application of violence recognition on mobile intelligent terminals. To solve this problem, we propose MobileNet-TSM, a lightweight network, which uses MobileNet-V2 as main structure. By incorporating temporal shift modules (TSM), which can exchange information between frames, the capability of extracting dynamic characteristics between consecutive frames is strengthened. Extensive experiments are conducted to prove the validity of this method. Our proposed model has only 8.49MB parameters and 175.86MB estimated total size. Compared with the existing methods, this method greatly reduced the model size, at the cost of an accuracy gap of about 3%. The proposed model has achieved accuracy of 97.959%, 97.5% and 87.75% on three public datasets (Crowd Violence, Hockey Fights, and RWF-2000), respectively. Based on this, we also build a real-time violence recognition application on the Android terminal. The source code and trained models are available on https://github.com/1840210289/MobileNet-TSM.git.

VD-Net: An Edge Vision-Based Surveillance System for Violence Detection

“…6 to display the suggested model performance on surveillance and nonsurveillance datasets, respectively. It is common for VD techniques to define any progressing activity as violent in sports, where athletes collide or hit one another, e.g., in a [43] 90.70 90.00 92.93 82.50 MiNet-3D [44] 94.71 100.00 91.41 -ViF [45] 82.90 -85.00 -OViF [36] 87.50 -88.00 -ViF + OViF [36] 86.30 ---MoWLD-BoW [37] 90.90 89.50 --3D-CNNs [46] 96.00 90.20 98.00 -Two-casecade TSM [47] 98.05 -96.93 -SSHA [48] 97.05 -97.90 -FightCNN-based Attention [49] 95.00 --71.00 ViT Large-16 [50] 98.00 99.50 97.00 84.60 RCNN-based Darknet [32] 98 hockey fight. As a result, one method of detecting aggression is to watch how players approach one another.…”