Real-Time Lane Detection via Efficient Feature Alignment and Covariance Optimization for Low-Power Embedded Systems
This work addresses the challenge of efficient lane detection for embedded systems, offering an incremental optimization that enhances performance and power efficiency.
The paper tackled the problem of real-time lane detection in low-power embedded systems by proposing a Covariance Distribution Optimization (CDO) module, which improved detection accuracy by 0.01% to 1.5% across six models on three datasets without increasing computational complexity.
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.