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

[21] 3D Human Body Shape and Pose Estimation from Depth Image
Liu, Lei
Wang, Kangkan
Yang, Jian
PATTERN RECOGNITION AND COMPUTER VISION, PT I, PRCV 2020, 2020, 12305 : 410 - 421
[22] 3D Human Pose Estimation via Explicit Compositional Depth Maps
Wu, Haiping
Xiao, Bin
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 12378 - 12385
[23] Hand Shape and 3D Pose Estimation Using Depth Data from a Single Cluttered Frame
Doliotis, Paul
Athitsos, Vassilis
Kosmopoulos, Dimitrios
Perantonis, Stavros
ADVANCES IN VISUAL COMPUTING, ISVC 2012, PT I, 2012, 7431 : 148 - 158
[24] Estimation of 3D human pose using prior knowledge
Zhang, Lei
Chen, Shu
Zou, Beiji
JOURNAL OF ELECTRONIC IMAGING, 2021, 30 (04)
[25] GoPose: 3D Human Pose Estimation Using WiFi
Ren, Yili
Wang, Zi
Wang, Yichao
Tan, Sheng
Chen, Yingying
Yang, Jie
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT, 2022, 6 (02):
[26] Automatic Calibration of the Fisheye Camera for Egocentric 3D Human Pose Estimation from a Single Image
Zhang, Yahui
You, Shaodi
Gevers, Theo
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 1771 - 1780
[27] SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera
Tome, Denis
Alldieck, Thiemo
Peluse, Patrick
Pons-Moll, Gerard
Agapito, Lourdes
Badino, Hernan
de la Torre, Fernando
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (06) : 6794 - 6806
[28] Sparse Depth Odometry: 3D Keypoint based Pose Estimation from Dense Depth Data
Manoj, Prakhya Sai
Liu Bingbing
Lin Weisi
Qayyum, Usman
2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2015, : 4216 - 4223
[29] How to Refine 3D Hand Pose Estimation from Unlabelled Depth Data ?
Dibra, Endri
Wolf, Thomas
Oeztireli, Cengiz
Gross, Markus
PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2017, : 135 - 144
[30] On the Robustness of 3D Human Pose Estimation
Chen, Zerui
Huang, Yan
Wang, Liang
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 5326 - 5332

← 1 2 3 4 5 →