Curb Detection
Curb detection, the automated identification of road curbs using sensors like cameras and LiDAR, is crucial for autonomous vehicle navigation and assistive technologies for the visually impaired. Current research focuses on improving the accuracy and efficiency of curb detection algorithms, often employing deep learning architectures tailored to handle the challenges of noisy data and varying environmental conditions, including the development of large-scale annotated datasets. These advancements aim to overcome limitations of existing methods, such as sensitivity to lighting changes and high computational costs, leading to more robust and reliable curb detection in real-world scenarios. The resulting improvements have significant implications for safer autonomous driving and enhanced navigation aids for people with visual impairments.
Papers
WATonoBus: An All Weather Autonomous Shuttle
Neel P. Bhatt, Ruihe Zhang, Minghao Ning, Ahmad Reza Alghooneh, Joseph Sun, Pouya Panahandeh, Ehsan Mohammadbagher, Ted Ecclestone, Ben MacCallum, Ehsan Hashemi, Amir Khajepour
LiDAR-based curb detection for ground truth annotation in automated driving validation
Jose Luis Apellániz, Mikel García, Nerea Aranjuelo, Javier Barandiarán, Marcos Nieto