Obstacle detection in single images with deep neural networks. Issue 6 (September 2016)

• Record Type: Journal Article
• Authors: Jia, Baozhi; Feng, Weiguo; Zhu, Ming
• Is Part Of: Signal, image and video processing. Volume 10:Issue 6(2016)
• Page Start: 1033
• Page End: 1040
• Publication Date: 2016-09
• Subjects: Autonomous navigation -- Obstacle detection -- Single image -- Deep neural network and obstacle depth; Signal processing -- Digital techniques -- Periodicals; Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; 621.3822
• DOI: 10.1007/s11760-015-0855-4
• Languages: English
• ISSNs: 1863-1703

Abstract

Abstract Obstacle detection in single images is a challenging problem in autonomous navigation on low-cost condition. In this paper, we introduce an approach for obstacle detection in single images with deep neural networks. We propose the followings: (1) a deep model combined with other deep neural network for obstacle detection; (2) a method to segment obstacles and infer their depths. Among others, both local and global information are generated in our method for better classification and portability. Experiments are performed on the open datasets and images captured by our autonomous vehicle. The results show that our method is effective in both obstacle detection and depth inference.