Abstract
In this paper, a novel and robust method of lane detection has been proposed using images taken by a camera mounted on the hood of a vehicle. Detection of lane is an important and crucial element for an intelligent vehicle system. An important aspect of automatic driver assistance system (ADAS) is lane detection and it relies on accurate detection of lanes. In our method, we create a tentative model of the background and lane is detected as foreground. We develop a background model of the road surfaces without lane marking by considering the spatial neighbourhood of each pixel. It then compares each pixel of the testing frame to the modelled background to detect the lane. Morphological operations are applied over the detected regions of rain in order to give a proper shape and boundary to the detected lane markings. Our algorithm is capable of perfectly detecting straight and curved lanes, continuous and discontinuous lanes and also it has no issues in detecting number of lanes in the video frame. Our algorithm performs accurately in challenging and different scenarios as shown in experimental results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhou S, Lagnemma K (2010) Self-supervised learning method for unstructured road detection using fuzzy support vector machine. In: IEEE international conference on Intelligent robots and systems (IROS)
Zhou S, Gong J, Xiong G, Lagnemma L (2010) Road detection using support vector machine based on online learning and evaluation. In: Intelligent vehicle symposium (IV)
Wu C, Lin C, Lee C (2012) Applying a functional neuro fuzzy network to realtime lane detection and front vehicle distance measurement. IEEE Trans Syst Man Cybern 42(4)
Kuhnl T, Kummert F, Fritsch J (2012) Spatial ray features for real time ego-lane extraction’. IEEE Trans Intell Transp Syst USA, 16–19 Sept 16–19
Wang J, Lin C, Chen S (2010) Applying fuzzy method to vision based lane detection and departure warning system. Expert Syst. Appl. 37(2010):113126
Gupta A, Choudhary A (2017) Real-time lane detection using spatio-temporal incremental clustering. In: Proceedings of IEEE 20th international conference on intelligent transportation system, pp 1–6
Wang Y, Teoh EK, Shen D (2004) Lane detection and tracking using b-snake. Image Vis Comput 22(4):269–280
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Prusty, P., Mohanty, B. (2020). A Framework for Real-Time Lane Detection Using Spatial Modelling of Road Surfaces. In: Mohanty, M., Das, S. (eds) Advances in Intelligent Computing and Communication. Lecture Notes in Networks and Systems, vol 109. Springer, Singapore. https://doi.org/10.1007/978-981-15-2774-6_17
Download citation
DOI: https://doi.org/10.1007/978-981-15-2774-6_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-2773-9
Online ISBN: 978-981-15-2774-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)