Open AccessIndoor Scene Semantic Segmentation Based on RGB-D Image and Convolution Neural Network
Author(s) -
Guitang Wang,
Ziyu Wang,
Yongbin Chen,
Wang Guo-zhen,
Jianqiang Chen
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1637/1/012138
Subject(s) - computer science , artificial intelligence , segmentation , rgb color model , convolutional neural network , residual , image segmentation , scale space segmentation , computer vision , pattern recognition (psychology) , segmentation based object categorization , convolution (computer science) , decoding methods , artificial neural network , algorithm
In recent years, convolutional neural network has been widely used in image semantic segmentation and achieved great success. In this paper, a semantic segmentation network of indoor scene based on rgb-d image is proposed: SRNET (Strong supervision Residual Net). In this network model, the original data is processed by separate training and gradual fusion, and the mandatory supervision module is added in the decoding stage, which effectively improves the accuracy of semantic segmentation. At the same time, anti residual decoding method and jump structure are introduced to reduce information loss. Experimental results show that the segmentation accuracy of this model is better than most of the current segmentation algorithms.