Abstract
AbstractAs autonomous driving technology is developing rapidly, demands for pedestrian safety, intelligence, and stability are increasing. In this situation, there is a need to discern pedestrian location and action, such as crossing or standing, in dynamic and uncertain contexts. The success of autonomous driving for pedestrian zones depends heavily on its capacity to distinguish between safe and unsafe pedestrians. The vehicles must first recognize the pedestrian, then their body movements, and understand the meaning of their actions before responding appropriately. This article presents a detailed explanation of the architecture for 3D pedestrian activity recognition using recurrent neural networks (RNN). A custom dataset was created for behaviors such as parallel and perpendicular crossing while texting or calling encountered around autonomous vehicles. A model similar to Long-Short Term Memory (LSMT) has been used for different experiments. As a result, it is revealed that the models trained independently on upper and lower body data produced better classification than the one trained on whole body skeleton data. An accuracy of 97% has been achieved for lower body and 88–90% on upper body test data, respectively.
Funder
Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
Publisher
Springer Science and Business Media LLC
Subject
Computer Science Applications,Computer Networks and Communications,Computer Graphics and Computer-Aided Design,Computational Theory and Mathematics,Artificial Intelligence,General Computer Science
Reference44 articles.
1. Jan QH, Kleen JMA, Berns K. Self-aware pedestrians modeling for testing autonomous vehicles in simulation. In: VEHITS, 2020; 577–584.
2. Prédhumeau M. Simulating realistic pedestrian behaviors in the context of autonomous vehicles in shared spaces. In: 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021). 2021.
3. Tran TTM, Parker C, Tomitsch M. A review of virtual reality studies on autonomous vehicle–pedestrian interaction. IEEE Transactions on Human-Machine Systems. 2021.
4. Jan QH, Wolf P, Berns K, Reich J, Wellstein M. Integration of human skeleton posture models into reaction for realizing dynamic risk management
5. Jan QH, Berns K. Safety-configuration of autonomous bus in pedestrian zone. In: VEHITS, 2021; 698–705.