Izvorni znanstveni članak

https://doi.org/10.17559/TV-20230918000947

Enhanced Lane Recognition for Automated Warning Sign Placement Using Canny Edge Detection

Yuan-shuai Lan orcid.org/0009-0001-3289-8519 ; School of Electronic Information Engineering, Greely University of China, Chengdu, Sichuan, 123, Section 2, Chengjian Avenue, Eastern New Area, Jianyang City, Chengdu City, Sichuan Province *
Qian Wang ; School of Electronic Information Engineering, Greely University of China, Chengdu, Sichuan, 123, Section 2, Chengjian Avenue, Eastern New Area, Jianyang City, Chengdu City, Sichuan Province
Jing-gui Yang ; School of Electronic Information Engineering, Greely University of China, Chengdu, Sichuan, 123, Section 2, Chengjian Avenue, Eastern New Area, Jianyang City, Chengdu City, Sichuan Province
Xue-qin Meng ; School of Electronic Information Engineering, Greely University of China, Chengdu, Sichuan, 123, Section 2, Chengjian Avenue, Eastern New Area, Jianyang City, Chengdu City, Sichuan Province
Yao Yang ; School of Electronic Information Engineering, Greely University of China, Chengdu, Sichuan, 123, Section 2, Chengjian Avenue, Eastern New Area, Jianyang City, Chengdu City, Sichuan Province

* Dopisni autor.

Sažetak

Real-time lane recognition is critical for intelligent roadside warning sign vehicles that provide post-accident precautions. However, lane interference, uneven lighting, and night time dimness can impair automatic cruise control. This paper presents an enhanced lane recognition methodology using Canny edge detection to enable automated placement of roadside warning signs. Image preprocessing via multi-directional Sobel filtering improves edge detection across varied lighting. Experiments demonstrated up to 85% lane recognition accuracy using the proposed techniques, outperforming prior thresholding approaches. An optimized PID controller enabled precise vehicle control based on lane data. The system was implemented on a K210 controller, validating real-time embedded performance. By overcoming lane detection deficiencies, this research enables reliable automated warning sign deployment to enhance road safety.

Ključne riječi

canny filtering; dynamic lane recognition method; intelligent roadside warning sign vehicles; real-time lane recognition; Sobel edge detection

Hrčak ID:

332982

URI

https://hrcak.srce.hr/332982

Datum izdavanja:

29.6.2025.

Posjeta: 337 *