Analysis and Classification of Vehicle using KNN and Decision Tree

Vishakha Gaikwad, Balwant Sonkamble


Classification of vehicles is becoming useful technique of intelligent transportation system for the traffic analysis. Increased number of accidents and busy intersections on road are making traffic analysis more important. The main cause of these problems is avoidance of traffic rules and increased number of vehicles. Intelligent transportation system detects the vehicles which are not following the traffic rules and takes some action before the problem arises. Previous techniques are highly expensive or unsuccessful in some constraints. In case, the number of features to detect vehicle and number of samples in train increases, the performance decreases. Types of feature take performance to another level which is variant and invariant. It becomes difficult to classify vehicle when some features are invariant and some features are variant with one classifier. In this paper, the combination of KNN and Decision tree is proposed to classify the vehicle with its lane allowance on single virtual detection line. KNN is used with the invariant features followed by decision tree applied on variant features to classify vehicle shape and lane wise. Invariant shape based features of vehicle are detected on single virtual detection line instead of multiple virtual detection line. Consideration of combined features gives good performance on the single virtual detection line. Experimental results demonstrates that proposed method improves classification of vehicle with some variant and invariant features.

Keywords— Active Contours, Classification, Computer Vision, Decision tree, Image processing, K- Nearest Neighbor, Pattern recognition.

Full Text:




  • There are currently no refbacks.

Copyright (c) 2016 International Journal of Advanced Research in Computer Science