Optical Flow Estimation for Flame Detection in Videos

摘要

High-level computer vision tasks such as security and authentication, robot navigation, collision avoidance, path planning, and video surveillance require detection of the moving objects in the surrounding environment at real time. In this project, a new algorithm based on a multi-modal distribution is presented to detect the moving objects in image sequence taken from a static camera with a small number of calculations. The idea of background subtraction is to subtract or difference the current image from a reference background model. This paper proposes a new method to detect moving object based on background subtraction and establish a reliable background updating model based on statistical and use a dynamic optimization threshold method to obtain a more complete moving object. This paper also proposes image segmentation technique by background subtraction and implemented in FPGA.