Bibliographic Details
| Title: |
RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark |
| Authors: |
Ho, Yuan-Hao, Cheng, Jen-Hao, Kuan, Sheng Yao, Jiang, Zhongyu, Chai, Wenhao, Huang, Hsiang-Wei, Lin, Chih-Lung, Hwang, Jenq-Neng |
| Publication Year: |
2024 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Signal Processing |
| More Details: |
Traditional methods for human localization and pose estimation (HPE), which mainly rely on RGB images as an input modality, confront substantial limitations in real-world applications due to privacy concerns. In contrast, radar-based HPE methods emerge as a promising alternative, characterized by distinctive attributes such as through-wall recognition and privacy-preserving, rendering the method more conducive to practical deployments. This paper presents a Radar Tensor-based human pose (RT-Pose) dataset and an open-source benchmarking framework. The RT-Pose dataset comprises 4D radar tensors, LiDAR point clouds, and RGB images, and is collected for a total of 72k frames across 240 sequences with six different complexity-level actions. The 4D radar tensor provides raw spatio-temporal information, differentiating it from other radar point cloud-based datasets. We develop an annotation process using RGB images and LiDAR point clouds to accurately label 3D human skeletons. In addition, we propose HRRadarPose, the first single-stage architecture that extracts the high-resolution representation of 4D radar tensors in 3D space to aid human keypoint estimation. HRRadarPose outperforms previous radar-based HPE work on the RT-Pose benchmark. The overall HRRadarPose performance on the RT-Pose dataset, as reflected in a mean per joint position error (MPJPE) of 9.91cm, indicates the persistent challenges in achieving accurate HPE in complex real-world scenarios. RT-Pose is available at https://huggingface.co/datasets/uwipl/RT-Pose.
Comment: ECCV 2024 |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2407.13930 |
| Accession Number: |
edsarx.2407.13930 |
| Database: |
arXiv |
