By Topic

A simple method for calculating vehicle density in traffic images

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Royani, T. ; Electr. Eng. Fac., Tarbiat Moallem Univ. of Sabzevar, Sabzevar, Iran ; Haddadnia, J. ; Pooshideh, M.

Calculating of vehicles density in traffic images is a challenging research topic as it has to directly deal with hostile but realistic conditions on the road, such as uncontrolled illuminations, cast shadows, and visual occlusion. Yet, the outcome of being able to accurately count and resolve vehicles under such conditions has tremendous benefit to traffic surveillance. Accurate vehicle count enables the extraction of important traffic information such as congestion level and lane occupancy. There are different methods for vehicles counting from traffic images that emphasize on the accuracy, but most of them suffer from long time process and computational complexity, so they can't be used in real-time condition. This paper proposed a novel simple method for traffic density calculation in multiple vehicle occlusions based on counting object pixels and assigning a distance index to each region of image that concentrates on time and computational complexity and has tolerable accuracy in traffic density calculation. Suppose that the occluded vehicles are segmented from the road background by previously proposed vehicle segmentation method. The proposed method has been tested on real-world monocular traffic images with multiple vehicle occlusions. The experimental results show that the proposed method can provide real-time and useful information for traffic surveillance.

Published in:

Machine Vision and Image Processing (MVIP), 2010 6th Iranian

Date of Conference:

27-28 Oct. 2010