10 April 2018 A fusion network for semantic segmentation using RGB-D data
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061523 (2018) https://doi.org/10.1117/12.2304501
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
Semantic scene parsing is considerable in many intelligent field, including perceptual robotics. For the past few years, pixel-wise prediction tasks like semantic segmentation with RGB images has been extensively studied and has reached very remarkable parsing levels, thanks to convolutional neural networks (CNNs) and large scene datasets. With the development of stereo cameras and RGBD sensors, it is expected that additional depth information will help improving accuracy. In this paper, we propose a semantic segmentation framework incorporating RGB and complementary depth information. Motivated by the success of fully convolutional networks (FCN) in semantic segmentation field, we design a fully convolutional networks consists of two branches which extract features from both RGB and depth data simultaneously and fuse them as the network goes deeper. Instead of aggregating multiple model, our goal is to utilize RGB data and depth data more effectively in a single model. We evaluate our approach on the NYU-Depth V2 dataset, which consists of 1449 cluttered indoor scenes, and achieve competitive results with the state-of-the-art methods.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jiahui Yuan, Jiahui Yuan, Kun Zhang, Kun Zhang, Yifan Xia, Yifan Xia, Lin Qi, Lin Qi, Junyu Dong, Junyu Dong, } "A fusion network for semantic segmentation using RGB-D data", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061523 (10 April 2018); doi: 10.1117/12.2304501; https://doi.org/10.1117/12.2304501
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT


Back to Top