Vehicle type recognition using multiple-feature combinations

Nguyen, Quang and Irhebhude, Martins.E and Ali, Mohammad Athar and Edirisinghe, Eran A. (2016) Vehicle type recognition using multiple-feature combinations. In: IS&T International Symposium on Electronic Imaging 2016, 14-18 Feb 2016, San Francisco.

[img] Text
Vehicle type recognition using multiple feature combinations.pdf
Restricted to Registered users only

Download (1MB) | Request a copy
Official URL: https://doi.org/10.2352/ISSN.2470-1173.2016.3.VSTI...

Abstract

This paper proposes a real-time vehicle tracking and type recognition system. An object tracker is recruited to detect vehicles within CCTV video footage. Subsequently, the vehicle regionof-interest within each frame are analysed using a set of features that consists of Region Features, Histogram of Oriented Gradient (HOG) and Local Binary Pattern (LBP) histogram features. Finally, a Support Vector Machine (SVM) is recruited as the classification tool to categorize vehicles into two classes: cars and vans. The proposed technique was tested on a dataset of 60 vehicles comprising of a mix of frontal/rear and angular views. Experimental results prove that the proposed technique offers a very high level of accuracy thereby promising applicability in real-life situations

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: HOG; Histogram of Oriented Gradient; LBP histogram; Local Binary Pattern histogram; SVM; Support Vector Machine; Vehicle Type Recognition; region descriptors
Subjects: T Technology > T Technology (General) > Management information systems
Divisions: School of Computing
Depositing User: Athar Ali
Date Deposited: 12 Mar 2020 14:40
Last Modified: 12 Mar 2020 14:40
URI: http://bear.buckingham.ac.uk/id/eprint/463

Actions (login required)

View Item View Item