Multi-scale structural similarity index for motion detection

Abstract

The most recent approach for measuring the image quality is the structural similarity index (SSI). This paper presents a novel algorithm based on the multi-scale structural similarity index for motion detection (MS-SSIM) in videos. The MS-SSIM approach is based on modeling of image luminance, contrast and structure at multiple scales. The MS-SSIM has resulted in much better performance than the single scale SSI approach but at the cost of relatively lower processing speed. The major advantages of the presented algorithm are both: the higher detection accuracy and the quasi real-time processing speed.

Keywords

• Motion detection
• Multi-scale structural similarity index
• Dynamic template matching