earticle

영어

Moving object detection is an important fundamental process in intelligent vision systems and an essential preprocessing step in high-level machine vision applications such as object tracking and moving analysis. This technique helps to detect suspicious events in video monitoring and is a key process for concentration estimation in traffic management. It is also one of the methods used in advanced vehicle control systems to keep vehicle in path and prevent accidents.In this paper, an effective weighted background moving object detection is presented,which is optimized for scenes with dynamic background. The proposed detection is based on real time background subtracting with high accuracy, low computational complexity and a short processing time, which makes it a good candidate for hardware implementation. The proposed algorithm is simulated in MATLAB software. The simulation results in MATLAB on various image sequences and comparison with mixture Gaussian method and median filter algorithm shows the effective weighted background method has better performance in different evaluation criteria that approves its efficiency in dynamic scenes.