Browse > Article
http://dx.doi.org/10.22680/kasa2022.14.3.071

Particle Filter Based Robust Multi-Human 3D Pose Estimation for Vehicle Safety Control  

Park, Joonsang (현대자동차)
Park, Hyungwook (현대자동차)
Publication Information
Journal of Auto-vehicle Safety Association / v.14, no.3, 2022 , pp. 71-76 More about this Journal
Abstract
In autonomous driving cars, 3D pose estimation can be one of the effective methods to enhance safety control for OOP (Out of Position) passengers. There have been many studies on human pose estimation using a camera. Previous methods, however, have limitations in automotive applications. Due to unexplainable failures, CNN methods are unreliable, and other methods perform poorly. This paper proposes robust real-time multi-human 3D pose estimation architecture in vehicle using monocular RGB camera. Using particle filter, our approach integrates CNN 2D/3D pose measurements with available information in vehicle. Computer simulations were performed to confirm the accuracy and robustness of the proposed algorithm.
Keywords
Human Pose Estimation; Sensor Fusion; Convolutional Neural Network; Driver Monitoring System;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M. Veges and A. Lorincz, 2019, "Absolute Human Pose Estimation with Depth Prediction Network," International Joint Conference on Neural Networks (IJCNN), pp. 1-7.
2 D. Mehta et al., 2018, "Single-Shot Multi-person 3D Pose Estimation from Monocular RGB," International Conference on 3D Vision (3DV), pp. 120-130.
3 Y. Xu, X. Yang, L. Gong, H. Lin, T. Wu, Y. Li and N. Vasconcelos, 2020, "Explainable Object-Induced Action Decision for Autonomous Vehicles," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9523-9532.
4 J. Lin, G. H. Lee, 2020, "HDNet: Human Depth Estimation for Multi-person Camera-Space Localization," European Conference on Computer Vision (ECCV), pp. 633-648.
5 J. Kim, S. Moon, A. Rohrbach, T. Darrell and J. Canny, 2020, "Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9661-9670.
6 D. Osokin, 2018, "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose," arXiv:1811.12004.
7 D. Osokin, 2020, Real-time 3D Multi-person Pose Estimation Demo [Source code]. https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch.
8 A. Bewley, Z. Ge, L. Ott, F. Ramos and B. Upcroft, 2016, "Simple online and realtime tracking," IEEE International Conference on Image Processing (ICIP), pp. 3464-3468.
9 M. S. Arulampalam, S. Maskell, N. Gordon and T. Clapp, 2002, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Transactions on Signal Processing, Vol. 50, No. 2, pp. 174-188.   DOI
10 X. Ji, Q. Fang, J. Dong, Q. Shuai, W. Jiang and X. Zhou, 2020, "A survey on monocular 3D human pose estimation," Virtual Reality & Intelligent Hardware, Vol. 2, No. 6, pp. 471-500.   DOI
11 K. Sun, B. Xiao, D. Liu and J. Wang, 2019, "Deep High-Resolution Representation Learning for Human Pose Estimation," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5686-5696.
12 H. Fang, S. Xie, Y. Tai and C. Lu, 2017, "RMPE: Regional Multi-Person Pose Estimation," IEEE International Conference on Computer Vision (ICCV), pp. 2334-2343.
13 Z. Cao, T. Simon, S. Wei and Y. Sheikh, 2017, "Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1302-1310.
14 K. Gong, J. Zhang and J. Feng, 2021, "PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8571-8580.
15 L. Zhao, X. Peng, Y. Tian, M. Kapadia and D. N. Metaxas, 2019, "Semantic Graph Convolutional Networks for 3D Human Pose Regression," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3420-3430.
16 M. Kocabas, S. Karagoz, and E. Akbas, 2018, "Multiposenet: Fast multi-person pose estimation using pose residual network," European Conference on Computer Vision (ECCV), pp. 437-453.