[论文解读] Real-Time Lane Detection via Efficient Feature Alignment and Covariance Optimization for Low-Power Embedded Systems

Yian Liu, Xiong Jun Wang+4 more|arXiv (Cornell University)|Jan 5, 2026

Autonomous Vehicle Technology and Safety被引用 0

一句话总结

本文提出 Covariance Distribution Optimization (CDO) 模块，通过将特征分布与真实标签对齐，在不增加额外计算负担且易于集成的前提下提升低功耗嵌入式系统上实时道路线检测的性能。

ABSTRACT

Real-time lane detection in embedded systems encounters significant challenges due to subtle and sparse visual signals in RGB images, often constrained by limited computational resources and power consumption. Although deep learning models for lane detection categorized into segmentation-based, anchor-based, and curve-based methods there remains a scarcity of universally applicable optimization techniques tailored for low-power embedded environments. To overcome this, we propose an innovative Covariance Distribution Optimization (CDO) module specifically designed for efficient, real-time applications. The CDO module aligns lane feature distributions closely with ground-truth labels, significantly enhancing detection accuracy without increasing computational complexity. Evaluations were conducted on six diverse models across all three method categories, including two optimized for real-time applications and four state-of-the-art (SOTA) models, tested comprehensively on three major datasets: CULane, TuSimple, and LLAMAS. Experimental results demonstrate accuracy improvements ranging from 0.01% to 1.5%. The proposed CDO module is characterized by ease of integration into existing systems without structural modifications and utilizes existing model parameters to facilitate ongoing training, thus offering substantial benefits in performance, power efficiency, and operational flexibility in embedded systems.

研究动机与目标

• 在嵌入式系统的有限计算与功耗约束下解决实时道路线检测问题。
• 开发一个轻量级优化模块，在不增加复杂度的前提下提升检测精度。
• 证明 CDO 模块在基于分割、基于锚框、基于曲线的道路线检测方法中的可移植性。
• 在多个数据集和实时优化模型上评估该方法，以展示泛化性和实际收益。

提出的方法

• 引入 Covariance Distribution Optimization (CDO) 以使特征分布与真实标签对齐。
• 将 CDO 实现为一个可集成的插件模块，与现有模型在结构上无改动地结合。
• 利用现有模型参数实现持续训练并在嵌入式系统中部署。
• 在三种道路线检测范式（分割基、锚框基、曲线基）和六个模型上验证有效性。

实验结果

研究问题

• RQ1 CDO 是否能够在低功耗、实时嵌入式场景下在不增加计算负担的前提下提升道路线检测精度？
• RQ2 CDO 是否广泛兼容多种道路线检测架构（分割、锚框、曲线）和数据集？
• RQ3 在标准道路线检测基准上将 CDO 应用于实时优化和 SOTA 模型时观测到的准确率提升是多少？

主要发现

• CDO 在六个模型中带来 0.01% 到 1.5% 的准确率提升。
• 提升在不增加计算复杂度的情况下实现。
• CDO 易于集成到现有系统中，并利用当前模型参数实现持续训练。
• 在三个数据集：CULane、TuSimple 和 LLAMAS 上证明了有效性。