Analysis and Classification of Vehicle using KNN and Decision Tree
Main Article Content
Abstract
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.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.