Traffic Control and Monitoring Based upon Density Estimation in Various Traffic Condition using Artificial Intelligence

In this survey paper the design and development of an application that aims to detect and estimate the number of vehicle are presented on road, in order to maximize traffic light functioning. First, a selection process of interest region is applied to the image sequences, multiplying a mask image with the original image to focus the segmentation in this region. Then, it is segmented by an iterative algorithm, which estimates the background to offset the light intensity variation; it extracts the objects on the road and, through morphological processing, removes the small lines and shapes. Now, object detection, tracking and classification of objects are done. The Objects are detected using optical flow method and traced using kalman filtering method. The objects extracted are classified using ten features including shape based features such as area, height, width, compactness factor, elongation factor, skewness, perimeter, orientation, aspect ratio and extend. A comparative analysis is presented in this paper for the classification of objects (car, truck, auto, human, motorcycle, none) based on Multi-class SVM (one vs. all), Back-propagation, and Adaptive Hierarchical Multi-class SVM (Support Vector Machine).