Open Access System for Information Sharing

Login Library

 

Article
Cited 20 time in webofscience Cited 27 time in scopus
Metadata Downloads

A CNN-based 3D human pose estimation based on projection of depth and ridge data SCIE SCOPUS

Title
A CNN-based 3D human pose estimation based on projection of depth and ridge data
Authors
Kim, YeonhoKim, Daijin
Date Issued
2020-10
Publisher
ELSEVIER SCI LTD
Abstract
We propose a method that use a convolutional neural network (CNN) to estimate human pose by analyzing the projection of the depth and ridge data, which represent local maxima in a distance transform map. To fully utilize the 3D information of depth points, we propose a method to project the depth and ridge data on various directions. The proposed projection method can reduce the 3D information loss, the ridge data can avoid joint drift, and the CNN increases localization accuracy. The proposed method proceeds as follows. (1) We use depth data to segment the human from the background and extract ridge data from human silhouettes. (2) We project the depth and ridge data onto XY, XZ, and ZY planes. (3) ResNet-101 accepts six projected images and use 1 x 1 convolution layers to generate 2D heatmaps and offsets. (4) We generate 2D keypoints per plane by using the soft-argmax operation. (5) We obtain 3D joint positions by using the fully-connected layers. In experiments on the SMMC-10, EVAL, and ITOP datasets, the proposed method achieved the state-of-the-art pose estimation accuracies. The proposed method can eliminate the 3D information loss and drift of joint positions that can occur during estimation of human pose. Keywords: 3D Human pose estimation 3D Point projection Ridge data (C) 2020 Elsevier Ltd. All rights reserved.
URI
https://oasis.postech.ac.kr/handle/2014.oak/107825
DOI
10.1016/j.patcog.2020.107462
ISSN
0031-3203
Article Type
Article
Citation
PATTERN RECOGNITION, vol. 106, 2020-10
Files in This Item:
There are no files associated with this item.

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

김대진KIM, DAI JIN
Dept of Computer Science & Enginrg
Read more

Views & Downloads

Browse