Log In Sign Up

Keep your Eyes on the Lane: Attention-guided Lane Detection

by   Lucas Tabelini, et al.

Modern lane detection methods have achieved remarkable performances in complex real-world scenarios, but many have issues maintaining real-time efficiency, which is important for autonomous vehicles. In this work, we propose LaneATT: an anchor-based deep lane detection model, which, akin to other generic deep object detectors, uses the anchors for the feature pooling step. Since lanes follow a regular pattern and are highly correlated, we hypothesize that in some cases global information may be crucial to infer their positions, especially in conditions such as occlusion, missing lane markers, and others. Thus, we propose a novel anchor-based attention mechanism that aggregates global information. The model was evaluated extensively on two of the most widely used datasets in the literature. The results show that our method outperforms the current state-of-the-art methods showing both a higher efficacy and efficiency. Moreover, we perform an ablation study and discuss efficiency trade-off options that are useful in practice. To reproduce our findings, source code and pretrained models are available at


page 3

page 6


End-to-end Lane Shape Prediction with Transformers

Lane detection, the process of identifying lane markings as approximated...

PolyLaneNet: Lane Estimation via Deep Polynomial Regression

One of the main factors that contributed to the large advances in autono...

Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification

Modern methods mainly regard lane detection as a problem of pixel-wise s...

3D-LaneNet+: Anchor Free Lane Detection using a Semi-Local Representation

3D-LaneNet+ is a camera-based DNN method for anchor free 3D lane detecti...

Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes

A novel algorithm to detect road lanes in the eigenlane space is propose...

A Keypoint-based Global Association Network for Lane Detection

Lane detection is a challenging task that requires predicting complex to...

Repainting and Imitating Learning for Lane Detection

Current lane detection methods are struggling with the invisibility lane...