A dense convolutional network lane detection based on attention mechanism

Xiangzhi Kong; Hao Sheng; Tong Zhang; Qingguo Sun; Honglin Wan

doi:10.1117/12.3011455

7 December 2023 A dense convolutional network lane detection based on attention mechanism

Xiangzhi Kong, Hao Sheng, Tong Zhang, Qingguo Sun, Honglin Wan

Proceedings Volume 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023); 1294156 (2023) https://doi.org/10.1117/12.3011455
Event: Third International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 203), 2023, Yinchuan, China

Abstract

Lane detection is a fundamental component of Advanced Driver Assistance Systems (ADAS). In this paper, we propose a dense convolutional network lane detection based on attention mechanism. The algorithm adopts DenseNet (Dense Convolutional Network) as the backbone network to capture global features and improve detection accuracy. In addition, CBAM is utilized to enhance the perception of lane details. Moreover, an auxiliary training network is designed where Spatial Pyramid Pooling (SPP) is employed to obtain multi-scale feature representations for handling lanes in various sizes and shapes. Our algorithm effectively addresses the issues of efficiency and challenging scenarios like no-visual cues. Experiments on public data sets show that the detection accuracy of our proposed algorithm improves to 96.9% compared with other state-of-the-art algorithms, especially under complex lighting conditions.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiangzhi Kong, Hao Sheng, Tong Zhang, Qingguo Sun, and Honglin Wan "A dense convolutional network lane detection based on attention mechanism", Proc. SPIE 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), 1294156 (7 December 2023); https://doi.org/10.1117/12.3011455

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available