A Real-time Scheme of Video Stabilization for Mobile Surveillance Robot

摘要

The purpose of this research is to develop a mobile surveillance robot capable of capturing and transmitting video on rough terrains. Recorded video is affected by jitters resulting into significant error between the desired and captured video flow. Image registration with a contrario RANSAC variant has been used to minimize the error between present and desired output video as it has proved to be a fast algorithm for video stabilization as compared to the conventional stabilization methods. This is the first paper which makes use of this method to design mobile wireless robot for surveillance applications. The video captured by the robot is stabilized and transmitted to the controller in the control room. Once the video is stabilized the controller moves the objects from one place to another with the help of robotic arm mounted to the robot using a wireless transmitter and receiver. The surveillance capabilities of the system are also tested in low illumination situations as spying in dark is an important requirement of todays advanced surveillance systems.