Lane detection using lane boundary marker network with road geometry constraints
Authors:
- 1 March 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1823-1832
Abstract
Lane detection is of critical importance to both the self-driving cars as well as advanced driver assistance systems. While current methods use a range of features from low-level to deep features extracted from convolutional neural networks, they all suffer from the problem of occlusion and struggle to detect lanes with low or no evidence on the road. In this paper, we use a lane boundary marker network to detect keypoints along the lane boundaries. An inverse perspective mapping is estimated using road geometry which is then applied to the detected markers and lines/curves are fitted jointly on the rectified points. Finally, missing lane boundaries are predicted using lane geometry constraints i.e., equidistant and parallelism. Reciprocal weighted averaging ensures lane boundaries with strong evidence dominate their predicted alternatives. The results show a significant improvement of +7.8%, +6.8% and +1.2% of F1 scores over the state-of-the-art on CU-Lane, Caltech and TuSimple datasets, respectively. This proves our algorithm’s robustness against both occluded and missing lanes cases. Furthermore, we also show that our algorithm can be combined with other lane detectors to improve their lane retrieval potential.Keywords
This publication has 25 references indexed in Scilit:
- DeepLanes: End-To-End Lane Position Estimation Using Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- A Vision Based Top-View Transformation Model for a Vehicle Parking AssistantSensors, 2012
- A real-time lane departure warning system based on FPGA2011
- Applying fuzzy method to vision-based lane detection and departure warning systemExpert Systems with Applications, 2010
- Lane following and lane departure using a linear-parabolic modelImage and Vision Computing, 2005
- Multitype lane markers recognition using local edge direction2003
- Real-time lane and obstacle detection on the GOLD system2002
- Random sample consensusCommunications of the ACM, 1981