Lane detection based on dual attention mechanism

doi:10.37188/CO.2022-0033

CIOMP OpenIR

	Lane detection based on dual attention mechanism
	F.-L. Ren, H.-B. Zhou, L. Yang and X. He
	2023
发表期刊	Chinese Optics
ISSN	20971842
卷号	16 期号:3 页码:645-653
摘要	In order to improve the performance of lane detection algorithms under complex scenes like obstacles, we proposed a multi-lane detection method based on dual attention mechanism. Firstly, we designed a lane segmentation network based on a spatial and channel attention mechanism. With this, we obtained a binary image which shows lane pixels and the background region. Then, we introduced HNet which can output a perspective transformation matrix and transform the image to a bird’s eye view. Next, we did curve fitting and transformed the result back to the original image. Finally, we defined the region between the two-lane lines near the middle of the image as the ego lane. Our algorithm achieves a 96.63% accuracy with real-time performance of 134 FPS on the Tusimple dataset. In addition, it obtains 77.32% of precision on the CULane dataset. The experiments show that our proposed lane detection algorithm can detect multi-lane lines under different scenarios including obstacles. Our proposed algorithm shows more excellent performance compared with the other traditional lane line detection algorithms. © 2023 Editorial Office of Chinese Optics. All rights reserved.
DOI	10.37188/CO.2022-0033
URL	查看原文
收录类别	ei
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/67812
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	F.-L. Ren, H.-B. Zhou, L. Yang and X. He. Lane detection based on dual attention mechanism[J]. Chinese Optics,2023,16(3):645-653.
APA	F.-L. Ren, H.-B. Zhou, L. Yang and X. He.(2023).Lane detection based on dual attention mechanism.Chinese Optics,16(3),645-653.
MLA	F.-L. Ren, H.-B. Zhou, L. Yang and X. He."Lane detection based on dual attention mechanism".Chinese Optics 16.3(2023):645-653.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Lane detection based（2491KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载