期刊
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
卷 33, 期 4, 页码 581-599出版社
SAGE PUBLICATIONS LTD
DOI: 10.1177/0278364913514283
关键词
Object recognition; feature learning; sparse coding; hierarchical segmentation; RGB-D cameras
类别
资金
- Intel Science and Technology Center for Pervasive Computing
- ONR MURI [N00014-07-1-0749]
Recently introduced RGB-D cameras are capable of providing high quality synchronized videos of both color and depth. With its advanced sensing capabilities, this technology represents an opportunity to significantly increase the capabilities of object recognition. It also raises the problem of developing expressive features for the color and depth channels of these sensors. In this paper we introduce hierarchical matching pursuit (HMP) for RGB-D data. As a multi-layer sparse coding network, HMP builds feature hierarchies layer by layer with an increasing receptive field size to capture abstract representations from raw RGB-D data. HMP uses sparse coding to learn codebooks at each layer in an unsupervised way and builds hierarchical feature representations from the learned codebooks in conjunction with orthogonal matching pursuit, spatial pooling and contrast normalization. Extensive experiments on various datasets indicate that the features learned with our approach enable superior object recognition results using linear support vector machines.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据