Efficient Sequential Neural Network with Spatial-Temporal Attention and Linear LSTM for Robust Lane Detection Using Multi-Frame Images

TL;DR

This paper presents a novel neural network model with spatial-temporal attention for robust, real-time lane detection in automated vehicles, outperforming existing methods especially under challenging conditions.

Contribution

Introduces a spatial-temporal attention mechanism within a sequential neural network for improved lane detection accuracy and efficiency in complex traffic scenarios.

Findings

Outperforms state-of-the-art lane detection methods

Reduces model parameters and computational costs

Demonstrates robustness in occlusion and lighting challenges

Abstract

Lane detection is a crucial perception task for all levels of automated vehicles (AVs) and Advanced Driver Assistance Systems, particularly in mixed-traffic environments where AVs must interact with human-driven vehicles (HDVs) and challenging traffic scenarios. Current methods lack versatility in delivering accurate, robust, and real-time compatible lane detection, especially vision-based methods often neglect critical regions of the image and their spatial-temporal (ST) salience, leading to poor performance in difficult circumstances such as serious occlusion and dazzle lighting. This study introduces a novel sequential neural network model with a spatial-temporal attention mechanism to focus on key features of lane lines and exploit salient ST correlations among continuous image frames. The proposed model, built on a standard encoder-decoder structure and common neural network backbones, is trained and evaluated on three large-scale open-source datasets. Extensive experiments demonstrate the strength and robustness of the proposed model, outperforming state-of-the-art methods in various testing scenarios. Furthermore, with the ST attention mechanism, the developed sequential neural network models exhibit fewer parameters and reduced Multiply-Accumulate Operations (MACs) compared to baseline sequential models, highlighting their computational efficiency. Relevant data, code, and models are released at https://doi.org/10.4121/4619cab6-ae4a-40d5-af77-582a77f3d821.