Study on Obstacle Detection and Recognition Method Based on Stereo Vision and Convolutional Neural Network

• Main Authors: Lian, Jing, Kong, Ling-chao, Li, Lin-hui, Zheng, Wei-na, Zhou, Ya-fu, Fang, Si-yu, Qian, Bo
• Format: Conference Proceeding
• Language: English
• Subjects: Convolution; convolutional neural network; Convolutional neural networks; Feature extraction; Kernel; obstacle detection and recognition; Stereo vision; Stixel; Training
• ISSN: 2161-2927
• DOI: 10.23919/ChiCC.2019.8866348

In order to solve the problems of long time for selecting candidate areas of obstacles and low accuracy of obstacle recognition. In this paper, we proposed an obstacle detection and recognition method based on stereo vision and convolution neural network. First, we use semi-global stereo matching to calculate disparity between left and right images. A method for Stixel computation is used to obtain the candidate regions of obstacles. Then, we use U-disparity map to extract the target obstacles from the candidate regions of obstacles. Then, we propose a new convolutional neural network to recognize the target obstacles. In order to verify the recognition performance of the new convolutional neural network, we compare the results with other convolutional neural networks on CIFAR-10 datasets. The experimental results show that our proposed convolutional neural network improves the real-time performance by 69% when the recognition accuracy is reduced by 4.9%.