A computer vision approach for detection and counting of motorcycle riders in university campus

Author

Waranusast, Rattapoom ; Timtong, Vasan ; Bundon, Nannaphat ; Tangnoi, Chainarong

Author_Institution

Dept. of Electr. & Comput. Eng., Naresuan Univ., Phitsanulok, Thailand

fYear

2014

fDate

19-21 March 2014

Firstpage

1

Lastpage

4

Abstract

Essential tasks of automatic traffic monitoring are a vehicle classification and a vehicle or passenger counting system. These tasks provide useful data in planning transportation system. This paper presents an automatic system to classify a motorcycle and count riders on it. The system extracts moving objects and classifies them as a motorcycle or other moving objects based on features derived from their region properties using K-Nearest Neighbor (KNN) classifier. The heads of the riders on the recognized motorcycle are then counted based on projection profiling. Experiment results show an average correct motorcycle classification at 95.31% and correct rider count at 83.82%.

Keywords

computer vision; feature extraction; image classification; learning (artificial intelligence); motorcycles; traffic engineering computing; KNN classifier; automatic system; automatic traffic monitoring; average correct motorcycle classification; computer vision approach; correct rider count; k-nearest-neighbor classifier; motorcycle recognition; motorcycle riders counting; motorcycle riders detection; moving objects extraction; passenger counting system; projection profiling; region properties; rider heads; university campus; vehicle classification; vehicle counting system; Conferences; Monitoring; Motorcycles; Pattern recognition; Visualization; K-nearest neighbor; computer vision; motorcycle recognition; moving object detection; people counting;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Engineering Congress (iEECON), 2014 International

Conference_Location

Chonburi

Type

conf

DOI

10.1109/iEECON.2014.6925906

Filename

6925906