ICRA 2011 Paper Abstract

Close

Paper WeP204.1

Lai, Kevin (University of Washington), Bo, Liefeng (University of Washington), Ren, Xiaofeng (Intel Labs Seattle), Fox, Dieter (University of Washington)

Sparse Distance Learning for Object Recognition Combining RGB and Depth Information

Scheduled for presentation during the Regular Sessions "Recognition II" (WeP204), Wednesday, May 11, 2011, 15:25−15:40, Room 3E

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on December 8, 2019

Keywords Recognition, Computer Vision for Robotics and Automation

Abstract

In this work we address joint object category and instance recognition in the context of RGB-D (depth) cameras. Motivated by local distance learning, where a novel view of an object is compared to individual views of previously seen objects, we define a view-to-object distance where a novel view is compared simultaneously to all views of a previous object. This novel distance is based on a weighted combination of feature differences between views. We show, through jointly learning per-view weights, that this measure leads to superior classification performance on object category and instance recognition. More importantly, our distance allows us to find a sparse solution via Group-Lasso regularization, where a small subset of representative views of an object is identified and used, with the rest discarded. This significantly reduces computational cost without compromising recognition accuracy. We evaluate the proposed technique, Instance Distance Learning (IDL), on the RGB-D Object Dataset, which consists of 300 object instances in 51 everyday categories and about 250,000 views of objects with both RGB color and depth. We empirically compare IDL to several alternative state-of-the-art approaches and also validate the use of visual and shape cues and their combination.

 

 

Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2019 PaperCept, Inc.
Page generated 2019-12-08  02:02:56 PST  Terms of use