Publication Type : Conference Paper
Publisher : Springer International Publishing, Cham
Source : Intelligent Computing, Information and Control Systems, Springer International Publishing, Cham (2020)
ISBN : 9783030304652
Campus : Coimbatore
School : School of Engineering
Center : Computational Engineering and Networking
Department : Electronics and Communication
Year : 2020
Abstract : Autonomous vehicle technology, which is evolving at a faster pace than predicted is promising to deliver higher safety benefits. Detecting the obstacles accurately and reliably is important for safer navigation. Speed bumps are the obstacles installed on the roads in order to force the vehicle driver to reduce the speed of the vehicle in the critical road areas, such as hospitals and schools. Autonomous vehicles have to detect and slower the speed appropriately to drive safely over the speed bump. In this paper, we propose a novel method to detect the upcoming speed bump by using a deep learning algorithm called SegNet, which is a deep convolutional neural network architecture for semantic pixel-wise segmentation. The trained model will give segmented output from the monocular camera feed placed in front of the vehicle.
Cite this Research Publication : J. Arunpriyan, Variyar, V. V. Sajith, Dr. Soman K. P., and Adarsh, S., “Real-Time Speed Bump Detection Using Image Segmentation for Autonomous Vehicles”, in Intelligent Computing, Information and Control Systems, Cham, 2020.