Incident detection algorithm based on radon transform using high-resolution remote sensing imagery

One of the most important methods to solve the traffic congestion is to detect the incident state in a roadway. This paper describes the development of segmentation methods for road traffic monitoring aims at the acquisition and analysis remote sensing imagery of traffic figures, such as presence and number of vehicles, incident detection and automatic driver warning systems. We propose a strategy for road extraction, vehicle detection and incident detection from remote sensing imagery based on radon transform method. Real time extraction and localization of incident in aerial images is an emerging research area that can be applied to vision-based traffic controlling. The intensity imagery is used to extract the incident from satellite images. Techniques based on neural network, radon transform for angle detection and traffic flow measurements are used for road extraction, vehicle detection and incident detection. The results show that the proposed approach has a good detection performance. The maximum angle of vehicles applied for incident detection is 45° and the best performance of the learning system achieved by 87% for detection rate (DR) and a false alarm rate (FAR) under 18% on 45 aerial images of roadways.