Moving Vehicle Detection Using AdaBoost and Haar-Like Feature in Surveillance Videos
This work addresses vehicle detection for traffic management applications, but it is incremental as it applies an existing method to a specific domain.
The paper tackled vehicle detection in surveillance videos by applying the Viola-Jones boosting technique with Haar-like features, achieving accuracy, completeness, and quality scores of about 94%, 92%, and 87%, respectively, which outperformed previous methods.
Vehicle detection is a technology which its aim is to locate and show the vehicle size in digital images. In this technology, vehicles are detected in presence of other things like trees and buildings. It has an important role in many computer vision applications such as vehicle tracking, analyzing the traffic scene and efficient traffic management. In this paper, vehicles detected based on the boosting technique by Viola Jones. Our proposed system is tested in some real scenes of surveillance videos with different light conditions. The experimental results show that the accuracy,completeness, and quality of the proposed vehicle detection method are better than the previous techniques (about 94%, 92%, and 87%, respectively). Thus, our proposed approach is robust and efficient to detect vehicles in surveillance videos and their applications.