Neural network-based semantic segmentation model for robot perception of driverless vision

IET Cyber-systems and Robotics

Lu Ye¹  Jiayi Zhu²  Ting Duan² 

[1] School of Information and Electronic Engineering, Zhejiang University of Science & Technology;School of Mechanical and Energy Engineering, Zhejiang University of Science & Technology;

关键词: video signal processing;    unsupervised learning;    feature extraction;    image segmentation;    neural nets;    object recognition;    neural network-based semantic segmentation model;    robot perception;    driverless vision;    driverless vehicles;    surrounding objects;   

DOI  :  10.1049/iet-csr.2020.0040

来源: DOAJ

【 摘 要 】

Driverless vision is one of the important applications of robot perception. With the development of driverless vehicles, the perception and understanding of the surrounding environment are becoming more and more important. When the types of surrounding objects are too complex, the ability of the computer to recognise the environment is poor. To improve the recognition accuracy of the computer and enhance the ability of segmentation, in this study, depth estimation is used to predict depth information to assist semantic segmentation, and then edge features of objects are introduced to enhance the contour of objects. A neural network-based semantic segmentation model is proposed. Finally, the intrinsic mechanism of attention is used to increase the correlation between channels. The experimental results on the CamVid data set show that this model can obtain better evaluation results and improve the segmentation accuracy of images compared with other models.

【 授权许可】

Unknown