Open AccessBlind sidewalk segmentation based on the lightweight semantic segmentation network
Author(s) -
Xingjian Liu,
Xin Zhao,
Sizhan Wang
Publication year - 2021
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 - 10.1088/1742-6596/1976/1/012004
Subject(s) - segmentation , computer science , convolution (computer science) , residual , artificial intelligence , inference , block (permutation group theory) , encode , basis (linear algebra) , separable space , pattern recognition (psychology) , feature (linguistics) , computer vision , algorithm , mathematics , artificial neural network , linguistics , geometry , philosophy , gene , mathematical analysis , biochemistry , chemistry
A lightweight semantic segmentation network is proposed to solve the problem of real-time segmentation of blind sidewalk. On the basis of U-Net’s encode-decoding structure, the inverse residual block composed of deep separable convolution is used to replace the ordinary convolution for feature extraction, and the number of convolution layer channels is compressed. Experiments show that the blind segmentation method used can effectively overcome the disadvantages of traditional methods that are affected by the environment easily. Compared with U-Net, the parameter amount is reduced by 25.2 times, and the reasoning speed is increased by 3.6 times, while the loss of precision is just less than 2%, which basically meet the requirement of real-time inference.