An improved efficient model for structure-aware lane detection of unmanned vehicles
Authors:
- 20 February 2021
- journal article
- research article
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
- Vol. 235 (9) , 2496-2508
Abstract
Lane detection algorithms require extremely low computational costs as an important part of autonomous driving. Due to heavy backbone networks, algorithms based on pixel-wise segmentation is struggling to handle the problem of runtime consumption in the recognition of lanes. In this paper, a novel and practical methodology based on lightweight Segmentation Network is proposed, which aims to achieve accurate and efficient lane detection. Different with traditional convolutional layers, the proposed Shadow module can reduce the computational cost of the backbone network by performing linear transformations on intrinsic feature maps. Thus a lightweight backbone network Shadow-VGG-16 is built. After that, a tailored pyramid parsing module is introduced to collect different sub-domain features, which is composed of both a strip pool module based on Pyramid Scene Parsing Network (PSPNet) and a convolution attention module. Finally, a lane structural loss is proposed to explicitly model the lane structure and reduce the influence of noise, so that the pixels can fit the lane better. Extensive experimental results demonstrate that the performance of our method is significantly better than the state-of-the-art (SOTA) algorithms such as Pointlanenet and Line-CNN et al. 95.28% and 90.06% accuracy and 62.5 frames per second (fps) inference speed can be achieved on the CULane and Tusimple test dataset. Compared with the latest ERFNet, Line-CNN, SAD, F1 scores have respectively increased by 3.51%, 2.84%, and 3.82%. Meanwhile, the result from our dataset exceeds the top performances of the other by 8.6% with an 87.09 F1 score, which demonstrates the superiority of our method.Keywords
This publication has 16 references indexed in Scilit:
- Robust Lane Detection using Two-stage Feature Extraction with Curve FittingPattern Recognition, 2016
- Multiple Lane Detection Algorithm Based on Novel Dense Vanishing Point EstimationIEEE Transactions on Intelligent Transportation Systems, 2016
- Deep Residual Learning for Image Recognition2016
- Deep Neural Network for Structural Prediction and Lane Detection in Traffic SceneIEEE Transactions on Neural Networks and Learning Systems, 2016
- Efficient Lane Detection Based on Spatiotemporal ImagesIEEE Transactions on Intelligent Transportation Systems, 2015
- Automatic Detection and Classification of Road Lane Markings Using Onboard Vehicular CamerasIEEE Transactions on Intelligent Transportation Systems, 2015
- Real-time illumination invariant lane detection for lane departure warning systemExpert Systems with Applications, 2015
- Lane Detection and Tracking Using a Parallel-snake ApproachJournal of Intelligent & Robotic Systems, 2014
- A Sensor-Fusion Drivable-Region and Lane-Detection System for Autonomous Vehicle Navigation in Challenging Road ScenariosIEEE Transactions on Vehicular Technology, 2013
- Recent progress in road and lane detection: a surveyMachine Vision and Applications, 2012