DeepLanes: End-To-End Lane Position Estimation using Deep Neural Networks
Wednesday, October 24, 2018
Wegmans Hall Room 1400
Camera-based lane detection algorithms are one of the key enablers for many semi-autonomous and fully autonomous systems, ranging from lane keep assist to level-5 automated vehicles. Positioning a vehicle between lane boundaries is the core navigational aspect of a self-driving car. Even though this should be trivial, given the clarity of lane markings on most standard roadway systems, the process is typically mired with tedious pre-processing and computational effort. We present an approach to estimate lane positions directly using a deep neural network that operates on images from laterally-mounted down-facing cameras. To create a diverse training set, we present a method to generate semi-artificial images. Besides the ability to distinguish whether there is a lane-marker present or not, the network is able to estimate the position of a lane marker with sub-centimeter accuracy at an average of 100 frames/s on an embedded automotive platform, requiring no pre- or post-processing. This system can be used not only to estimate lane position for navigation, but also provide an efficient way to validate the robustness of driver-assist features which depend on lane information.
Surjya Ray is a research scientist at the Autonomous Vehicles Department of Ford Greenfield Labs at Palo Alto. Dr. Ray received a B.E. degree in Electronics and Telecommunications Engineering from Jadavpur University, Calcutta, India in 2006 and M.S. and PhD degrees in Electrical Engineering from University of Rochester, NY, in 2009 and 2013, respectively. His current research interests include applications of machine learning and computer vision in autonomous driving and advanced driver-assistance systems (ADAS). His other research interests lie in the areas of connected vehicles, wireless communications and networking, and the optimization of communication networks.
Refreshments will be provided