Classification of moving vehicles using k-means clustering

Vehicle classification has crop up as an important area of study due of its importance in variety of applications like surveillance, security framework, traffic congestion avoidance and accidents prevention etc. The image sequences for traffic scenes are recorded by a stationary NI smart camera. The...

Full description

Saved in:
Bibliographic Details
Published in2015 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT) pp. 1 - 6
Main Authors Changalasetty, Suresh Babu, Badawy, Ahmed Said, Saroja Thota, Lalitha, Ghribi, Wade
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2015
Subjects
Area measurement
Biology
data mining
Feature extraction
Ice
image processing
k-means Clustering
LabVIEW
Vehicles
WEKA
Online AccessGet full text

Cover

More Information
Summary:Vehicle classification has crop up as an important area of study due of its importance in variety of applications like surveillance, security framework, traffic congestion avoidance and accidents prevention etc. The image sequences for traffic scenes are recorded by a stationary NI smart camera. The video clip is processed in LabVIEW to detect vehicles in images and measure characteristics like width, length, area, perimeter using image processing feature extraction techniques. The extracted vehicle features from the traffic video are used to build a cluster model with two clusters - big and small in WEKA toolbox. The cluster model implements k-means clustering technique of data mining. The cluster model is used to classify new vehicles instances as big or small based on the vehicle features in images.
ISBN:9781479960842
1479960845
DOI:10.1109/ICECCT.2015.7226041