Sketch and Refine: Towards Fast and Accurate Lane Detection
Preprint
Abstract
Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of real-world scenarios. Existing approaches, whether proposal-based or keypoint-based, suffer from depicting lanes effectively and efficiently. Proposal-based methods detect lanes by distinguishing and regressing a collection of proposals in a streamlined top-down way, yet lack sufficient flexibility in lane representation. Keypoint-based methods, on the other hand, construct lanes flexibly from local descriptors, which typically entail complicated post-processing. In this paper, we present a "Sketch-and-Refine" paradigm that utilizes the merits of both keypoint-based and proposal-based methods. The motivation is that local directions of lanes are semantically simple and clear. At the "Sketch" stage, local directions of keypoints can be easily estimated by fast convolutional layers. Then we can build a set of lane proposals accordingly with moderate accuracy. At the "Refine" stage, we further optimize these proposals via a novel Lane Segment Association Module (LSAM), which allows adaptive lane segment adjustment. Last but not least, we propose multi-level feature integration to enrich lane feature representations more efficiently. Based on the proposed "Sketch and Refine" paradigm, we propose a fast yet effective lane detector dubbed "SRLane". Experiments show that our SRLane can run at a fast speed (i.e., 278 FPS) while yielding an F1 score of 78.9\%. The source code is available at: https://github.com/passerer/SRLane.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- RCLane: Relay Chain Prediction for Lane Detection2022
- CLRNet: Cross Layer Refinement Network for Lane Detection2022
- Rethinking Efficient Lane Detection via Curve Modeling2022
- Structure Guided Lane Detection2021
- LaneAF: Robust Multi-Lane Detection With Affinity FieldsIEEE Robotics and Automation Letters, 2021
- Key Points Estimation and Point Instance Segmentation Approach for Lane DetectionIEEE Transactions on Intelligent Transportation Systems, 2021
- Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection2021
- Line-CNN: End-to-End Traffic Line Detection With Line Proposal UnitIEEE Transactions on Intelligent Transportation Systems, 2019
- Lane-mark extraction for automobiles under complex conditionsPattern Recognition, 2014
- Road Lane Detection Using H-Maxima and Improved Hough Transform2012