VRU Pose-SSD: Multiperson Pose Estimation For Automated Driving

Authors

  • Chandan Kumar Mercedes-Benz Research and Development India
  • Jayanth Ramesh Mercedes-Benz Research and Development India
  • Bodhisattwa Chakraborty Mercedes-Benz Research and Development India
  • Renjith Raman Mercedes-Benz Research and Development India
  • Christoph Weinrich Robert Bosch GmbH, Germany
  • Anurag Mundhada Axogyan AI, Bangalore
  • Arjun Jain Indian Institute of Science,Bangalore, India Axogyan AI, India
  • Fabian B. Flohr Mercedes-Benz AG, Stuttgart, Germany.

DOI:

https://doi.org/10.1609/aaai.v35i17.17800

Keywords:

Autonomous Vehicles, Computer Vision, Pose Estimation

Abstract

We present a fast and efficient approach for joint person detection and pose estimation optimized for automated driving (AD) in urban scenarios. We use a multitask weight sharing architecture to jointly train detection and pose estimation. This modular architecture allows us to accommodate different downstream tasks in the future. By systematic large-scale experiments on the Tsinghua-Daimler Urban Pose Dataset (TDUP), we obtain multiple models with varying accuracy-speed trade-offs. We then quantize and optimize our network for deployment and present a detailed analysis of the efficacy of the algorithm. We introduce a two-stage evaluation strategy, which is more suitable for AD and achieve a significant performance improvement in comparison to state-of-the-art approaches. Our optimized model runs at 52~fps on full HD images and still reaches a competitive performance of 32.25~LAMR. We are confident that our work serves as an enabler to tackle higher-level tasks like VRU intention estimation and gesture recognition, which rely on stable pose estimates and will play a crucial role in future AD systems.

Downloads

Published

2021-05-18

How to Cite

Kumar, C., Ramesh, J., Chakraborty, B., Raman, R., Weinrich, C., Mundhada, A., Jain, A., & Flohr, F. B. (2021). VRU Pose-SSD: Multiperson Pose Estimation For Automated Driving. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15331-15338. https://doi.org/10.1609/aaai.v35i17.17800

Issue

Section

IAAI Technical Track on Emerging Applications of AI