29 August 2016 Towards 3D object recognition with contractive autoencoders
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100330S (2016) https://doi.org/10.1117/12.2243988
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
Abstract
Nowadays, object recognition in 3D scenes has become an emerging challenge with various applications. However, an object can’t be represented well by artificial features derived only from 2D images or depth images separately, and supervised learning method usually requires lots of manually labeled data. To address those limitations, we propose a cross-modality deep learning framework based on contractive autoencoders for 3D scenes object recognition. In particular, we use contractive autoencoding to learn feature representations from 2D and depth images at the same time in an unsupervised way, it is possible to capture their joint information to reinforce detector training. Experiments on 3D image dataset demonstrate the effectiveness of the proposed method for 3D scene object recognition.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bo Liu, Lingcheng Kong, Jianghai Zhao, Jinghua Wu, Zhiying Tan, "Towards 3D object recognition with contractive autoencoders", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100330S (29 August 2016); doi: 10.1117/12.2243988; https://doi.org/10.1117/12.2243988
PROCEEDINGS
7 PAGES


SHARE
Back to Top