Egocentric Pose Recognition in Four Lines of Code
Preprint
Abstract
We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during everyday interactions with objects. Past work shows that strong pose+viewpoint priors and depth-based features are crucial for robust performance. In egocentric views, hands and arms are observable within a well defined volume in front of the camera. We call this volume an egocentric workspace. A notable property is that hand appearance correlates with workspace location. To exploit this correlation, we classify arm+hand configurations in a global egocentric coordinate frame, rather than a local scanning window. This greatly simplify the architecture and improves performance. We propose an efficient pipeline which 1) generates synthetic workspace exemplars for training using a virtual chest-mounted camera whose intrinsic parameters match our physical camera, 2) computes perspective-aware depth features on this entire volume and 3) recognizes discrete arm+hand pose classes through a sparse multi-class SVM. Our method provides state-of-the-art hand pose recognition performance from egocentric RGB-D images in real-time.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Story-Driven Summarization for Egocentric Video2013
- Pixel-Level Hand Detection in Ego-centric Videos2013
- Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor2013
- Tracking the articulated motion of two strongly interacting hands2012
- Detecting activities of daily living in first-person camera views2012
- Social interactions: A first-person perspective2012
- An Appearance-Based Prior for Hand Tracking2010
- Hand Tracking with Flocks of Features2005
- Estimating 3D hand pose from a cluttered image2003
- Does stereopsis matter in humans?Eye, 1996