KNN Network Based Intelligent Aerial Surveillance System

In this paper, we proposed an automatic vehicle detection system for aerial surveillance with advance use of detecting vehicle colors, and its model. It does not assume any prior information of camera heights, vehicle sizes, and vehicle colors. Vehicle classification has evolved into a significant subject of study due to its importance in autonomous navigation, traffic analysis, surveillance and security systems, and transportation management. While numerous approaches have been introduced for this purpose, no specific study has been conducted to provide a robust and complete video-based vehicle classification system based on the rear-side view where the camera's field of view is directly behind the vehicle. In this paper features including vehicle colors and local features are considered. Feature extraction performs the edge detection and corner detection using canny edge detector. Color classification executes the color a transformation. Finally KNN classifier is used for classification purpose. By finding the nearest neighbors pixelwise classification is accomplished.