A Robust Lane Detection Model via Vertical Spatial Convolutions

Lane detection is still a problem to be solved due to the complex and dynamic autonomous driving environment. In this work, we propose a robust lane detection model via vertical spatial convolutions. In the encoder phase, a pair of convolutions is used to increase the number of channels of feature maps, and reduce the network parameters. Then, a combination module is utilized to further compress the redundant spatial information into a valid and compact representation. Finally, a group of vertical spatial convolution blocks and efficient residual modules is employed to help the proposed model obtain more effective global context information of lane lines, which are used by the subsequent network layers to detect lane lines more accurately in some challenging scenarios. Furthermore, we verify the performance and robustness of the proposed model on two popular and diverse lane detection benchmarks: TuSimple and CULane. A large number of experimental results show that our model outperforms the state-of-the-art algorithms.