Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation

04/27/2015
by   Xiaochuan Fan, et al.
0

We propose a new learning-based method for estimating 2D human pose from a single image, using Dual-Source Deep Convolutional Neural Networks (DS-CNN). Recently, many methods have been developed to estimate human pose by using pose priors that are estimated from physiologically inspired graphical models or learned from a holistic perspective. In this paper, we propose to integrate both the local (body) part appearance and the holistic view of each local part for more accurate human pose estimation. Specifically, the proposed DS-CNN takes a set of image patches (category-independent object proposals for training and multi-scale sliding windows for testing) as the input and then learns the appearance of each local part by considering their holistic views in the full body. Using DS-CNN, we achieve both joint detection, which determines whether an image patch contains a body joint, and joint localization, which finds the exact location of the joint in the image patch. Finally, we develop an algorithm to combine these joint detection/localization results from all the image patches for estimating the human pose. The experimental results show the effectiveness of the proposed method by comparing to the state-of-the-art human-pose estimation methods based on pose priors that are estimated from physiologically inspired graphical models or learned from a holistic perspective.

READ FULL TEXT

page 1

page 3

page 7

page 8

research
08/10/2016

3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information

While there has been a success in 2D human pose estimation with convolut...
research
05/20/2019

Patch-based 3D Human Pose Refinement

State-of-the-art 3D human pose estimation approaches typically estimate ...
research
07/12/2014

Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

We present a method for estimating articulated human pose from a single ...
research
06/15/2017

Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation

We propose a novel approach to 3D human pose estimation from a single de...
research
08/18/2023

Improving 3D Pose Estimation for Sign Language

This work addresses 3D human pose reconstruction in single images. We pr...
research
11/16/2014

Efficient Object Localization Using Convolutional Networks

Recent state-of-the-art performance on human-body pose estimation has be...
research
10/26/2020

Handgun detection using combined human pose and weapon appearance

CCTV surveillance systems are essential nowadays to prevent and mitigate...

Please sign up or login with your details

Forgot password? Click here to reset