Robust Lane Detection via Expanded Self Attention

by   Minhyeok Lee, et al.

The image-based lane detection algorithm is one of the key technologies in autonomous vehicles. Modern deep learning methods achieve high performance in lane detection, but it is still difficult to accurately detect lanes in challenging situations such as congested roads and extreme lighting conditions. To be robust on these challenging situations, it is important to extract global contextual information even from limited visual cues. In this paper, we propose a simple but powerful self-attention mechanism optimized for lane detection called the Expanded Self Attention (ESA) module. Inspired by the simple geometric structure of lanes, the proposed method predicts the confidence of a lane along the vertical and horizontal directions in an image. The prediction of the confidence enables estimating occluded locations by extracting global contextual information. ESA module can be easily implemented and applied to any encoder-decoder-based model without increasing the inference time. The performance of our method is evaluated on three popular lane detection benchmarks (TuSimple, CULane and BDD100K). We achieve state-of-the-art performance in CULane and BDD100K and distinct improvement on TuSimple dataset. The experimental results show that our approach is robust to occlusion and extreme lighting conditions.


page 1

page 3

page 4

page 5

page 7


Learning Lightweight Lane Detection CNNs by Self Attention Distillation

Training deep models for lane detection is challenging due to the very s...

Laneformer: Object-aware Row-Column Transformers for Lane Detection

We present Laneformer, a conceptually simple yet powerful transformer-ba...

Ultra Fast Structure-aware Deep Lane Detection

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

LVLane: Deep Learning for Lane Detection and Classification in Challenging Conditions

Lane detection plays a pivotal role in the field of autonomous vehicles ...

Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification

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

Contrastive Learning for Lane Detection via cross-similarity

Detecting road lanes is challenging due to intricate markings vulnerable...

FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network

The search for predictive models that generalize to the long tail of sen...

Please sign up or login with your details

Forgot password? Click here to reset