Lane detection in complex scenes based on end-to-end neural network
This work addresses lane detection for unmanned driving, which is crucial for vehicle decision-making, but it appears incremental as it builds on existing methods like spatial convolution and ERFNet.
The paper tackles lane detection in complex driving scenes by proposing an end-to-end neural network that combines spatial convolution and ERFNet for semantic segmentation, achieving an F1-measure of 71.9% on the CULane database with an IOU threshold of 0.5.
The lane detection is a key problem to solve the division of derivable areas in unmanned driving, and the detection accuracy of lane lines plays an important role in the decision-making of vehicle driving. Scenes faced by vehicles in daily driving are relatively complex. Bright light, insufficient light, and crowded vehicles will bring varying degrees of difficulty to lane detection. So we combine the advantages of spatial convolution in spatial information processing and the efficiency of ERFNet in semantic segmentation, propose an end-to-end network to lane detection in a variety of complex scenes. And we design the information exchange block by combining spatial convolution and dilated convolution, which plays a great role in understanding detailed information. Finally, our network was tested on the CULane database and its F1-measure with IOU threshold of 0.5 can reach 71.9%.