Open AccessDetection of potholes in autonomous vehicle
Author(s) -
Bharadwaj Sundra Murthy Sachin,
Varaprasad Golla
Publication year - 2014
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/iet-its.2013.0138
Subject(s) - pothole (geology) , obstacle avoidance , computer vision , frame (networking) , computer science , obstacle , matlab , software , artificial intelligence , remotely operated underwater vehicle , path (computing) , real time computing , simulation , mobile robot , geology , robot , geography , petrology , telecommunications , archaeology , programming language , operating system
Pothole avoidance may be considered similar to other obstacle avoidance, except that the potholes are depressions rather than extrusions from a surface. This study discusses a solution for detection of potholes in the path of an autonomous vehicle operating in an unstructured environment. Here, a vision approach is used since the simulated potholes are significantly different from the background surface. Furthermore, using this approach, pothole can only be detected in case of uniform lighting conditions. The solution to the problem is developed in a systematic manner. Initially, a specific camera and frame grabber are chosen, then camera is mounted on top of the autonomous vehicle and the images will be acquired. Then, a software solution is designed using MATLAB. The method is tested under real‐time conditions and results demonstrate its reasonable efficiency.