Use of Computer Vision for White Line Detection for Robotic Applications

Abstract

Image processing and its use for object detection that allows to alter decisions based on what is being observed remains a challenge today. As participants in the Intelligent Ground Vehicle Competition (IGVC) 2018 and 2019, we were tasked to build an autonomous vehicle that is capable of maneuvering and traversing through a grassy course delineated with white lines and laid out with scattered obstacles. In order to remain within the white line boundaries, computer vision was used with the implementation of OpenCV and Python for image processing and white line detection. To accomplish the white line detection task, various image processing techniques such as change of color space, image filtering, blurring, histogram equalizing, and edge detection are utilized. Testing of the image processing techniques was performed using prerecorded videos from previous competitions as well as videos taken using the autonomous vehicle's ZED camera. In both test cases there were challenges due to differences in lighting conditions, image clarity between cameras used for both video types, and the angle of the camera.