Dynamic integration and online evaluation of vision-based lane detection algorithms

Lane detection techniques have been widely studied in the last two decades and applied in many advance driver assistance systems. However, the development of a robust lane detection system, which can deal with various road conditions and efficiently evaluate its detection results in real time, is st...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IET intelligent transport systems Ročník 13; číslo 1; s. 55 - 62
Hlavní autoři:	Xing, Yang, Lv, Chen, Wang, Huaji, Cao, Dongpu, Velenis, Efstathios
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	The Institution of Engineering and Technology 01.01.2019
Témata:	advance driver assistance systems cameras computer vision dynamic integration edge detection ego lanes false detections feature extraction Gaussian mixture model Gaussian processes Hough transform algorithm Hough transforms image segmentation integration system lane geometry knowledge lane missing scenarios lane sampling low detection confidence object detection online evaluation primary lane detection module real time road vehicles robust lane detection system Special Issue: Recent Advancements on Electrified, Low Emission and Intelligent Vehicle-Systems steerable filter SVT system traffic engineering computing vision‐based lane detection algorithms voting technique Hough transform algorithm dynamic integration advance driver assistance systems steerable filter false detections integration system object detection vision-based lane detection algorithms SVT system Gaussian mixture model cameras robust lane detection system ego lanes lane missing scenarios road vehicles feature extraction image segmentation edge detection real time low detection confidence traffic engineering computing voting technique online evaluation Hough transforms computer vision Gaussian processes lane sampling lane geometry knowledge primary lane detection module
ISSN:	1751-956X, 1751-9578
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Lane detection techniques have been widely studied in the last two decades and applied in many advance driver assistance systems. However, the development of a robust lane detection system, which can deal with various road conditions and efficiently evaluate its detection results in real time, is still of great challenge. In this study, a vision-based lane detection system with dynamic integration and online evaluation is proposed. To increase the robustness of the lane detection system, the integration system dynamically processes two lane detection modules. First, a primary lane detection module is designed based on the steerable filter and Hough transform algorithm. Then, a secondary algorithm, which combines the Gaussian mixture model for image segmentation and random sample consensus for lane model fitting, will be activated when the primary algorithm encounters a low detection confidence. To detect the colour and line style of the ego lanes and evaluate the lane detection system in real time, a lane sampling and voting technique is proposed. By combining the sampling and voting system system with prior lane geometry knowledge, the evaluation system can efficiently recognise the false detections. The system works robustly in various complex situations (e.g. shadows, night, and lane missing scenarios) with a monocular camera.
ISSN:	1751-956X 1751-9578
DOI:	10.1049/iet-its.2018.5256