Please wait a minute...
Submit  |   Chinese  | 
 
Advanced Search
   Home  |  Online Now  |  Current Issue  |  Focus  |  Archive  |  For Authors  |  Journal Information   Open Access  
Submit  |   Chinese  | 
Engineering    2018, Vol. 4 Issue (4) : 479 -490     https://doi.org/10.1016/j.eng.2018.07.010
Research |
A Co-Point Mapping-Based Approach to Drivable Area Detection for Self-Driving Cars
Ziyi Liu1,2,Siyu Yu1,2,Nanning Zheng1,2()
1. Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China
2. National Engineering Laboratory for Visual Information Processing and Applications, Xi’an Jiaotong University, Xi’an 710049, China
Abstract
Abstract  

The randomness and complexity of urban traffic scenes make it a difficult task for self-driving cars to detect drivable areas. Inspired by human driving behaviors, we propose a novel method of drivable area detection for self-driving cars based on fusing pixel information from a monocular camera with spatial information from a light detection and ranging (LIDAR) scanner. Similar to the bijection of collineation, a new concept called co-point mapping, which is a bijection that maps points from the LIDAR scanner to points on the edge of the image segmentation, is introduced in the proposed method. Our method positions candidate drivable areas through self-learning models based on the initial drivable areas that are obtained by fusing obstacle information with superpixels. In addition, a fusion of four features is applied in order to achieve a more robust performance. In particular, a feature called drivable degree (DD) is proposed to characterize the drivable degree of the LIDAR points. After the initial drivable area is characterized by the features obtained through self-learning, a Bayesian framework is utilized to calculate the final probability map of the drivable area. Our approach introduces no common hypothesis and requires no training steps; yet it yields a state-of-art performance when tested on the ROAD-KITTI benchmark. Experimental results demonstrate that the proposed method is a general and efficient approach for detecting drivable area.

Keywords Drivable area      Self-driving      Data fusion      Co-point mapping     
Fund: 
Corresponding Authors: Nanning Zheng   
Issue Date: 11 September 2018
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Ziyi Liu
Siyu Yu
Nanning Zheng
Cite this article:   
Ziyi Liu,Siyu Yu,Nanning Zheng. A Co-Point Mapping-Based Approach to Drivable Area Detection for Self-Driving Cars[J]. Engineering, 2018, 4(4): 479 -490 .
URL:  
http://engineering.org.cn/EN/10.1016/j.eng.2018.07.010     OR     http://engineering.org.cn/EN/Y2018/V4/I4/479
References
Related
No related articles found!
Copyright © 2015 Higher Education Press & Engineering Sciences Press, All Rights Reserved.
京ICP备11030251号-2

 Engineering