Google scholar arxiv informatics ads IJAIS publications are indexed with Google Scholar, NASA ADS, Informatics et. al.

Call for Paper


March Edition 2023

International Journal of Applied Information Systems solicits high quality original research papers for the March 2023 Edition of the journal. The last date of research paper submission is February 15, 2023.

Obstacle Extraction based on Region Extraction on a Monocular Video

Pramodh K.P., Prasad Bhagwat, Shashank P.S., Mamatha H.R.. Published in Image Processing

International Journal of Applied Information Systems
Year of Publication: 2015
Publisher: Foundation of Computer Science (FCS), NY, USA
Authors: Pramodh K.P., Prasad Bhagwat, Shashank P.S., Mamatha H.R.
Download full text
  1. Pramodh K.P., Prasad Bhagwat, Shashank P.S. and Mamatha H.R.. Article: Obstacle Extraction based on Region Extraction on a Monocular Video. International Journal of Applied Information Systems 10(1):1-5, November 2015. BibTeX

    	author = "Pramodh K.P. and Prasad Bhagwat and Shashank P.S. and Mamatha H.R.",
    	title = "Article: Obstacle Extraction based on Region Extraction on a Monocular Video",
    	journal = "International Journal of Applied Information Systems",
    	year = 2015,
    	volume = 10,
    	number = 1,
    	pages = "1-5",
    	month = "November",
    	note = "Published by Foundation of Computer Science (FCS), NY, USA"


Ever since the advent of computers, they has proven themselves extremely useful for automating routine parts of human life. With improvements in computer vision techniques, Unmanned Ground Vehicles (UGV) are a hot topic of research. In order to build such a system, one of the main objectives is to locate and identify things present in its surroundings. Obstacle Extraction is one such field which deals with detection of obstacles in front of it. In this project, an obstacle extraction system is built, by first extracting the region of interest, the road. This region of interest is then merged with the foreground obtained from the background modeling. Two different background modeling techniques are implemented, one based on GMM, and the other based on Bayesian color estimation. Further, a lane detection system has been implemented, which helps in detecting the current lane that the UGV is moving in. This is implemented based on two techniques, one based on Hough transform and the other based on Contours. The second method was also extended to determine the direction of the curve ahead of the vehicle.


  1. Christophe Braillon, Cedric Pradalier, Jim Crowley, Christian Laugier. Real-time Moving Obstacle Detection Using Optical Flow Models. Proc. of the IEEE Intelligent Vehicle Symp.,Jun 2006, Tokyo (JP), France. pp.466-471
  2. A. Broggi, M. Bertozzi, , Shape-based Pedestrian Detection, Proceedings of the IEEE Intelligent Vehicles Symposium 2000,Dearbon (MI), USA, pp. 1-6
  3. Shumin Liu,  Yingping Huang and Renjie Zhang, On-Road Vehicle Recognition Using the Symmetry Property and Snake Models, pp. 1-9
  4. Shaohua Quin et al., Road Region Estimation and Obstacle Extraction using Monocular camera, ICIC International 2013, Vol 9, No 9 September 2013, pp. 1- 12
  5. Razvan Itu, Radu Danescu, An Efficient Obstacle Awareness Application for Android Mobile Devices, ICCP IEEE 2014, pp. 1-7
  6. José M. Álvarez and Antonio M.Lopez, IEEE Transactions on Intelligent Transportation Systems, Vol. 12, No. 1, March 2011, pp. 1-10
  7. Arthur Miranda Neto, Alessandro Correa Victorino, Isabelle Fantoni, Janito Vaqueiro Ferreira. Real-Time Estimation of Drivable Image Area based on Monocular Vision. IEEE Intelligent Vehicles Symposium (IV), Jun 2013, Gold Coast, Australia. pp.63-68, 2013
  8. Stauffer, Chris, Adaptive background mixture models for real-time tracking, IEEE CVPR 99, Vol 2 pp. 1-7
  9. Duda, R. O. and P. E. Hart, "Use of the Hough Transformation to Detect Lines and Curves in Pictures," Comm. ACM, Vol. 15, pp. 11–15 (January, 1972)
  10. Canny, J., A Computational Approach to Edge Detection, IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.
  11. Video Dataset for lane detection and obstacle extraction


GMM, Otsu Thresholding, Canny Edge Detection, Contours, Mahalanobis Distance, Recursive Bayesian, Hough Transform.