Title :
Road Detection Method Corresponded to Multi Road Types with Flood Fill and Vehicle Control
Author :
Fukukawa, Tomoya ; Yu Maeda ; Sekiyama, Kosuke ; Fukuda, Toshio
Author_Institution :
Dept. of Mech. Sci. & Eng., Nagoya Univ., Nagoya, Japan
Abstract :
This paper proposes the road detection method corresponded to multi road types with Flood Fill. Flood Fill is one of the image processing methods to partition the region of input image based on RGB color model. Road detection is useful for automatic robots because the robots work on various road surface in outdoor environment. The proposed method has two features. Firstly, the method can cancel the influence of shadow on road by using HSV color model. Secondly, the method can recognize multi road types by k-nearest neighbor algorithm. By using the proposed method, the robot can select the suitable controller for road surface or the safety route. We implement the proposed method in vehicle navigation and the availability is verified by the experimental results.
Keywords :
image colour analysis; object detection; path planning; road safety; road traffic control; road vehicles; HSV color model; RGB color model; automatic robots; flood fill; image processing methods; k-nearest neighbor algorithm; multiroad type recognition; outdoor environment; region partition; road detection method; road shadow; road surface; safety route; vehicle control; vehicle navigation; Floods; Image color analysis; Mathematical model; Mobile robots; Roads; Robot kinematics; Flood Fill; Image Processing; Road Detection;
Conference_Titel :
Robot, Vision and Signal Processing (RVSP), 2013 Second International Conference on
Conference_Location :
Kitakyushu
Print_ISBN :
978-1-4799-3183-5
DOI :
10.1109/RVSP.2013.68
