Citation

Yeo, Boon Chin and Lim, Way Soong and Lim, Heng Siong (2016) Lane detection in the absence of lane markings for roadway surveillance with thermal vision. International Journal of Innovative Computing, Information and Control (IJICIC), 12 (3). pp. 677-688. ISSN 1349-418X

Text 131.pdf Restricted to Repository staff only Download (712kB)

Abstract

Roadway surveillance is popular with the use of normal camera for at least two decades. Recently, thermal vision provides an alternative of machine vision for the roadway surveillance system since it demonstrates good vehicle detection accuracy, especially under night condition. Conventional lane detection method generally requires the presence of lane markings on the road. This also poses a challenge for thermal vision, in which the markings may be vague or even absent from the recorded video frames. In this paper, a Gaussian-shaped road model is proposed for lane detection in the absence of lane markings. The lane is detected based on least square method. Thus, the detected lane is considered to be the best-fit lane on the image plane. The proposed model is able to detect the center of the lane and also the width of the lane. In addition, the model also allows the determination of the shape of the lane, of whether the lane is linear or a polynomial of a certain degree.

Item Type:	Article
Uncontrolled Keywords:	Image processing
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	27 Jul 2018 15:53
Last Modified:	29 Dec 2020 16:57
URII:	http://shdl.mmu.edu.my/id/eprint/6711

Downloads

Edit (login required)