AI based monitoring violent action detection data for in-vehicle scenarios

Nelson R P Rodrigues; Nuno M C da Costa; Rita Novais; Jaime Fonseca; Paulo Cardoso; João Borges

doi:10.1016/j.dib.2022.108564

AI based monitoring violent action detection data for in-vehicle scenarios

Data Brief. 2022 Aug 31:45:108564. doi: 10.1016/j.dib.2022.108564. eCollection 2022 Dec.

Authors

Nelson R P Rodrigues¹, Nuno M C da Costa¹, Rita Novais¹, Jaime Fonseca¹, Paulo Cardoso¹, João Borges²

Affiliations

¹ Algoritmi Center, University of Minho, Guimarães, Portugal.
² Polytechnic Institute of Cavado and Ave, Barcelos, Portugal.

Abstract

With the evolution of technology associated with mobility and autonomy, Shared Autonomous Vehicles will be a reality. To ensure passenger safety, there is a need to create a monitoring system inside the vehicle capable of recognizing human actions. We introduce two datasets to train human action recognition inside the vehicle, focusing on violence detection. The InCar dataset tackles violent actions for in-car background which give us more realistic data. The InVicon dataset although doesn't have the realistic background as the InCar dataset can provide skeleton (3D body joints) data. This datasets were recorded with RGB, Depth, Thermal, Event-based, and Skeleton data. The resulting dataset contains 6 400 video samples and more than 3 million frames, collected from sixteen distinct subjects. The dataset contains 58 action classes, including violent and neutral (i.e., non-violent) activities.

Keywords: Action recognition; Autonomous vehicles; Dataset; Deep learning; Violent action.