3D Human Pose Estimation Using Egocentric Depth Data

被引：0

作者：

Baek, Seongmin ^{[1
]}

Gil, Youn-Hee ^{[1
]}

Kim, Yejin ^{[2
]}

机构：

[1] Elect & Telecommun Res Inst, Daejeon, South Korea

[2] Hongik Univ, Sch Games, Sejong, South Korea

来源：

30TH ACM SYMPOSIUM ON VIRTUAL REALITY SOFTWARE AND TECHNOLOGY, VRST 2024 | 2024年

关键词：

Pose estimation; egocentric view; depth data; skeletal joints;

D O I：

10.1145/3641825.3689515

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we present a novel approach for 3D human pose estimation using depth data from egocentric viewpoints. Depth data has the advantage that it is less sensitive to color and lighting changes. We acquired depth data streamed from multiple depth cameras attached to a user's head and calibrated them into a depth map. For joint detection, a ResNet-based network was optimized with the skeletal joints of a Kinect camera. Unlike previous approaches, the proposed approach can track 3D human poses in an egocentric setup with a small dataset.

引用

页数：2

共 50 条

[41] 3D Human Pose Estimation=2D Pose Estimation plus Matching
Chen, Ching-Hang
Ramanan, Deva
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5759 - 5767
[42] AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
Ohkawa, Takehiko
He, Kun
Sener, Fadime
Hodan, Tomas
Tran, Luan
Keskin, Cem
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 12999 - 13008
[43] Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
Banik, Soubarna
Gschossmann, Patricia
Garcia, Alejandro Mendoza
Knoll, Alois
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
[44] Fast online human pose estimation via 3D voxel data
Sagawa, Yuichi
Shimosaka, Masamichi
Mori, Taketoshi
Sato, Tomomasa
2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, 2007, : 1040 - 1046
[45] Enhancement of human 3D pose estimation using a novel concept of depth prediction with pose alignment from a single 2D image?
Kushwaha, Mohit
Choudhary, Jaytrilok
Singh, Dhirendra Pratap
COMPUTERS & GRAPHICS-UK, 2022, 107 : 172 - 185
[46] Correspondence-free pose estimation for 3D objects from noisy depth data
Xenophon Zabulis
Manolis I. A. Lourakis
Panagiotis Koutlemanis
The Visual Computer, 2018, 34 : 193 - 211
[47] Correspondence-free pose estimation for 3D objects from noisy depth data
Zabulis, Xenophon
Lourakis, Manolis I. A.
Koutlemanis, Panagiotis
VISUAL COMPUTER, 2018, 34 (02): : 193 - 211
[48] Nonflat Observation Model and Adaptive Depth Order Estimation for 3D Human Pose Tracking
Cho, Nam-Gyu
Yuille, Alan
Lee, Seong-Whan
2011 FIRST ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR), 2011, : 382 - 386
[49] 3D human pose estimation from range images with depth difference and geodesic distance
Zhang, Wenhui
Kong, Dehui
Wang, Shaofan
Wang, Zhiyong
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2019, 59 : 272 - 282
[50] Multi-person Absolute 3D Human Pose Estimation with Weak Depth Supervision
Veges, Marton
Lorincz, Andras
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I, 2020, 12396 : 258 - 270

← 1 2 3 4 5 →