Skip to Main Content
In this paper we present the development of a visual servo system for real-time and automatic aerial surveillance applications. The system can automatically detect the shape contours of objects within a scene and control the camera to track a target object centered at the image plane based on shape features. The system consists of a robust shape detection algorithm based on the randomized Hough transform (RHT) method, an adaptive object tracking algorithm, a probability data association (PDA) prediction filter and a fuzzy visual servo controller. We also establish a testbed to mimic the aerial surveillance environment and provide experimental results to verify the validity of the designed system.