10 April 2018 Multi-channel feature dictionaries for RGB-D object recognition
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061515 (2018) https://doi.org/10.1117/12.2303479
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
Hierarchical matching pursuit (HMP) is a popular feature learning method for RGB-D object recognition. However, the feature representation with only one dictionary for RGB channels in HMP does not capture sufficient visual information. In this paper, we propose multi-channel feature dictionaries based feature learning method for RGB-D object recognition. The process of feature extraction in the proposed method consists of two layers. The K-SVD algorithm is used to learn dictionaries in sparse coding of these two layers. In the first-layer, we obtain features by performing max pooling on sparse codes of pixels in a cell. And the obtained features of cells in a patch are concatenated to generate patch jointly features. Then, patch jointly features in the first-layer are used to learn the dictionary and sparse codes in the second-layer. Finally, spatial pyramid pooling can be applied to the patch jointly features of any layer to generate the final object features in our method. Experimental results show that our method with first or second-layer features can obtain a comparable or better performance than some published state-of-the-art methods.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaodong Lan, Xiaodong Lan, Qiming Li, Qiming Li, Mina Chong, Mina Chong, Jian Song, Jian Song, Jun Li, Jun Li, } "Multi-channel feature dictionaries for RGB-D object recognition", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061515 (10 April 2018); doi: 10.1117/12.2303479; https://doi.org/10.1117/12.2303479
PROCEEDINGS
7 PAGES


SHARE
Back to Top