Agnostic Lane Detection

2 May 2019Yuenan Hou

Lane detection is an important yet challenging task in autonomous driving, which is affected by many factors, e.g., light conditions, occlusions caused by other vehicles, irrelevant markings on the road and the inherent long and thin property of lanes. Conventional methods typically treat lane detection as a semantic segmentation task, which assigns a class label to each pixel of the image... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Lane Detection CULane ENet-Label F1 score 68.8 # 2
Lane Detection TuSimple ENet-Label Accuracy 96.29% # 4