Classify vehicles: Classification or clusterization?

Abstract

Vehicle classification has crop up as an important field of study due of its importance in variety of applications like surveillance, security framework, traffic congestion prevention and accidents avoidance. The image sequences for traffic scenes are recorded by a stationary NI smart camera. The video clip is processed in LabVIEW to detect vehicle and measure characteristics like width, length, area, perimeter using image process feature extraction techniques. Data mining is the use of automated data analysis techniques to uncover previously undetected relationships among data items. Two of the major data mining techniques are classification and clustering. To classify a vehicle as big or small needs to classify vehicles into classes. Among many, two techniques in WEKA are feed-forward neural network (NN) classification technique and k-means clustering techniques. To choose between the two techniques is a challenging task. We carry experiments using the extracted features of vehicles from traffic video with both techniques and found that classification model out-performed cluster model by a small degree.

Classification of Combat Wheeled Vehicles Using Cluster Analysis Methods

“…Traditionally, classification is carried out according to individual characteristics [3][4][5] for CWVs, such as, for example, the purpose, placement of the engine and cab, body type, number of axles, engine location, number of driving and controlled axles, which makes it possible to analyze by design characteristics. However, this classification does not allow establishing a relationship between the technical characteristics of CWVs and their functional purpose, which makes it necessary to develop more advanced methods for classifying CWVs.…”