Ahmed Said Badawy

Moving vehicles classification in WEKA

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 etc. 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. The extracted vehicle features from the traffic video are used to build a neural network classifier model in WEKA data mining toolbox. The classifier model implements multi layer perceptron (MLP) technique, a classification method of data mining. A feed-forward neural network (NN) is trained to classify vehicles in WEKA using the vehicle features of traffic video. The classifier model is used to classify new vehicles instances as big or small based on the vehicle features in images.

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 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.

Identification and feature extraction of moving vehicles in LabVIEW

In recent years, video monitoring and surveillance systems have been widely used in traffic management. The image sequences for traffic scenes are recorded by a stationary camera. The video clip is sent to LabVIEW program to convert into image frames. NI LabVIEW vision assistant module is used to detect the moving vehicle. The method is based on the establishment of correspondences between regions and vehicles, as the vehicles move through the image sequence. Background subtraction is used which improves the adaptive background mixture model and makes the system learn faster and more accurately, as well as adapt effectively to changing environments. The resulting system robustly identifies vehicles, rejecting background and tracks vehicles over a specific period of time. Once the (object) vehicle is tracked, the attributes of the vehicle like width, length, perimeter, area etc are extracted by image process feature extraction techniques. In proposed system we use LabVIEW and Vision assistant module for image processing and feature extraction. The project will benefit to reduce cost of traffic monitoring system and complete automation of traffic monitoring system.

Classify vehicles: Classification or clusterization?

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.