Road Boundary Detection Based on Random Forests and Particle Filter

Abstract:

Road detection is a primary problem for autonomous vehicle. There have been many approaches attempting to solve this problem. However, most of the approaches tend to be affected by shadow, occlusion and not always robust. In this paper, we propose a new approach to detect the road boundary, our approach has two parts: firstly, we detect the road boundary by random forests on the pixel level, then we track the road boundary by particle filter with the parameters of vanish point position and road boundary slope. The experiment shows our approach is an effective way to detect road boundary fast and robustly.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 3875-3879
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.3875
• Online since: November 2014
• Authors: Da Wei Zhao*, Tao Wu, Yu Qiang Fang, Jing Dai
• Keywords: Particle Filter, Random Forest (RF), Road Boundary Detection

References

[1] He Z, Wu T, Xiao Z, et al. Robust Road Detection From a Single Image Using Road Shape Prior[C]. International Conference on Image Processing (ICIP) (2013).

DOI: 10.1109/icip.2013.6738568

[2] Choi C, Trevor A J B, Christensen H I. RGB-D edge detection and edge-based registration[C]. Intelligent Robots and Systems (IROS) (2013).

DOI: 10.1109/iros.2013.6696558

[3] Dollar P, Zitnick C L. Structured Forests for Fast Edge Detection[C]. International Conference on Computer Vision (ICCV) (2013).

DOI: 10.1109/iccv.2013.231

[4] Kontschieder P, Bulo S R, Bischof H, et al. Structured class-labels in random forests for semantic image labelling[C].

DOI: 10.1109/iccv.2011.6126496

[5] Wang C, Hu Z, Maeda T, et al. Predictive Lane Detection for Simultaneous Road Geometry Estimation and Vehicle Localization[C]. IEEE International Conference on Robotics and Automation (ICRA) (2009).

[6] Zhou S, Jiang Y, Xi J, et al. A novel lane detection based on geometrical model and gabor filter[C]. Intelligent Vehicles Symposium (IV) (2010).

DOI: 10.1109/ivs.2010.5548087

[7] Aly M. Real time detection of lane markers in urban streets[C]. Intelligent Vehicles Symposium (IV) (2008).

DOI: 10.1109/ivs.2008.4621152

[8] Dollar P, Belongie S, Perona P. The Fastest Pedestrian Detector in the West[C]. British Machine Vision Conference (BMVC) (2010).

DOI: 10.5244/c.24.68

[9] Kong H, Audibert J Y, Ponce J. General road detection from a single image[J]. Image Processing 19(8): 2211-2220 (2010).

DOI: 10.1109/tip.2010.2045715

[10] Simandl M, Straka O. Sampling densities of particle filter: a survey and comparison[C]. American Control Conference (2007).

DOI: 10.1109/acc.2007.4282447