Lane detection is the task of detecting lanes on a road from a camera.
( Image credit: End-to-end Lane Detection )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations.
SOTA for Lane Detection on TuSimple
Lane detection is extremely important for autonomous vehicles.
In this paper, we use lane detection to study modeling and training techniques that yield better performance on real world test drives.
Traditional algorithms usually estimate only the position of the lanes on the road, but an autonomous control system may also need to know if a lane marking can be crossed or not, and what portion of space inside the lane is free from obstacles, to make safer control decisions.
Specifically, information of each frame is abstracted by a CNN block, and the CNN features of multiple continuous frames, holding the property of time-series, are then fed into the RNN block for feature learning and lane prediction.
The problem with such a two-step approach is that the parameters of the network are not optimized for the true task of interest (estimating the lane curvature parameters) but for a proxy task (segmenting the lane markings), resulting in sub-optimal performance.
Lane detection is to detect lanes on the road and provide the accurate location and shape of each lane.
We utilize the most fundamental property of instance labeling -- the pairwise relationship between pixels -- as the supervision to formulate the learning objective, then apply it to train a fully convolutional network (FCN) for learning to perform pixel-wise clustering.
#3 best model for Lane Detection on TuSimple
By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation.
#4 best model for Lane Detection on TuSimple