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

Abstract

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.

CVPR 2015

References in corpus (2)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• Learning Human Pose Estimation Features with Convolutional Networks

Cited by in corpus (24)

• Human pose estimation via Convolutional Part Heatmap Regression
• Stacked Hourglass Networks for Human Pose Estimation
• Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
• Recent Advances in Convolutional Neural Networks
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• Pose Invariant Embedding for Deep Person Re-identification
• Synthesizing Training Images for Boosting Human 3D Pose Estimation
• RMPE: Regional Multi-person Pose Estimation
• End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth Data
• Human Pose Estimation using Deep Consensus Voting
• Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
• Space-Time Representation of People Based on 3D Skeletal Data: A Review
• Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery
• ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
• Structured Feature Learning for Pose Estimation
• Attaining human-level performance with atlas location autocontext for anatomical landmark detection in 3D CT data
• Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation
• Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly
• Object Detection with Mask-based Feature Encoding
• 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
• Human Pose Estimation using Global and Local Normalization
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
• cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey