3D Hand Pose Detection in Egocentric RGB-D Images

Abstract

We focus on the task of everyday hand pose estimation from egocentric viewpoints. For this task, we show that depth sensors are particularly informative for extracting near-field interactions of the camera wearer with his/her environment. Despite the recent advances in full-body pose estimation using Kinect-like sensors, reliable monocular hand pose estimation in RGB-D images is still an unsolved problem. The problem is considerably exacerbated when analyzing hands performing daily activities from a first-person viewpoint, due to severe occlusions arising from object manipulations and a limited field-of-view. Our system addresses these difficulties by exploiting strong priors over viewpoint and pose in a discriminative tracking-by-detection framework. Our priors are operationalized through a photorealistic synthetic model of egocentric scenes, which is used to generate training data for learning depth-based pose classifiers. We evaluate our approach on an annotated dataset of real egocentric object manipulation scenes and compare to both commercial and academic approaches. Our method provides state-of-the-art performance for both hand detection and pose estimation in egocentric RGB-D images.

14 pages, 15 figures, extended version of the corresponding ECCV workshop paper, submitted to International Journal of Computer Vision

Cited by in corpus (6)

• The Evolution of First Person Vision Methods: A Survey
• Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera
• RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video
• EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras
• A Learning-based Variable Size Part Extraction Architecture for 6D Object Pose Recovery in Depth
• Enhanced Touchable Projector-depth System with Deep Hand Pose Estimation