Advertisement

A Framework for Real-Time Lane Detection Using Spatial Modelling of Road Surfaces

  • Pankaj Prusty
  • Bibhuprasad MohantyEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 109)

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.

Keywords

ADAS Morphological operation Spatial modelling 

References

  1. 1.
    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)Google Scholar
  2. 2.
    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)Google Scholar
  3. 3.
    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)Google Scholar
  4. 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 16–19Google Scholar
  5. 5.
    Wang J, Lin C, Chen S (2010) Applying fuzzy method to vision based lane detection and departure warning system. Expert Syst. Appl. 37(2010):113126CrossRefGoogle Scholar
  6. 6.
    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 1–6Google Scholar
  7. 7.
    Wang Y, Teoh EK, Shen D (2004) Lane detection and tracking using b-snake. Image Vis Comput 22(4):269–280CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Electronics and Communication Engineering, Faculty of EngineeringITER, Siksha ‘O’ Anusandhan (Deemed to be University)BhubaneswarIndia

Personalised recommendations