What is it about?
While the light of video has a sudden change, camera shakes, or some objects move, the target is easy to be detected wrongly. This paper introduce a method to eliminate these trouble and detect target well. It contains two key steps: temporal and spatial classification.
Featured Image
Why is it important?
The method thinks the background as two classes: motionless parts and moving objects which is not target. The difficulty is to distinguish the moving objects, such as a swaying tree, undulating water surface and fountain. Because these objects belong to background, their movement has different rules from moving traget.
Perspectives
Background extraction is an fondational and interesting work. I hope it will be used in many computer vision system.
Xiying Li
Sun Yat-Sen University
Read the Original
This page is a summary of: A dynamic background subtraction method based on spatio-temporal classification , IET Computer Vision, January 2018, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-cvi.2017.0339.
You can read the full text:
Contributors
The following have contributed to this page
