Multi-object tracking and detection system based on feature detection of the intelligent transportation system

Author

Nizar, Taufiq Nuzwir ; Anbarsanti, Nurfitri ; Prihatmanto, Ary S.

Author_Institution

Sch. of Electr. Eng. & Inf., Inst. Teknol., Bandung, Indonesia

Volume

4

fYear

2014

Firstpage

1

Lastpage

6

Abstract

This study aims to develop a system to detect traffic conditions by using computer vision. The system detects the presence of cars, motorcycles and pedestrians in the traffic; and also calculates the detected objects. The system detects the objects by using feature extraction method that is Histogram Oriented Gradient (HOG) and using linear Support Vector Machine (SVM) classifier. The system calculates the number of detected object by using the Kanade-Lucas-Tomasi (KLT) feature tracker. The implemented system has an average accuracy of 95.15%. Performance of HOG method and KLT algorithm was good enough to deal with the change of the brightness changes, but was not good enough to deal with pepper noise.

Keywords

computer vision; feature extraction; intelligent transportation systems; object tracking; Kanade-Lucas-Tomasi feature tracker; cars; computer vision; feature detection; feature extraction method; histogram oriented gradient; intelligent transportation system; linear support vector machine classifier; motorcycles; multiobject detection system; multiobject tracking system; pedestrians; Brightness; Computer vision; Feature extraction; Histograms; Motorcycles; Noise; Object detection; feature detection; histogram oriented gradient; intelligent transportation system; kanade-lucas-tomasi feature tracker;

fLanguage

English

Publisher

ieee

Conference_Titel

System Engineering and Technology (ICSET), 2014 IEEE 4th International Conference on

Print_ISBN

978-1-4799-7188-6

Type

conf

DOI

10.1109/ICSEngT.2014.7111795

Filename

7111795