One shot learning gesture recognition from RGBD images

Di Wu, Fan Zhu, Ling Shao

Research output: Contribution to conferencePaper

100 Citations (Scopus)

Abstract

We present a system to classify the gesture from only one learning example. The inputs are duo-modality, i.e. RGB and depth sensor from Kinect. Our system performs morphological denoising on depth images and automatically segments the temporal boundaries. Features are extracted based on Extended-Motion-History-Image (Extended-MHI) and the Multi-view Spectral Embedding (MSE) algorithm is used to fuse duo modalities in a physically meaningful manner. Our approach achieves less than 0.3 in Levenshtein distance in CHALEARN Gesture Challenge validation batches.
Original languageEnglish
DOIs
Publication statusPublished - Jun 2012
EventCVPRW 2012 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops - Providence, USA
Duration: 1 Jun 2012 → …

Conference

ConferenceCVPRW 2012 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Period1/06/12 → …

Fingerprint Dive into the research topics of 'One shot learning gesture recognition from RGBD images'. Together they form a unique fingerprint.

Cite this