Motion detecting method, motion detecting device, background model establishing method and background model establishing device

Abstract

The invention discloses a motion detecting method which comprises the following steps: expressing a current training area sequence of a training background image sequence into a high-level tensor; analyzing a high-level singular value of the tensor to obtain a tensor subspace of the tensor; and detecting the motion of a corresponding area to be detected of the current image to be detected by using the tensor subspace. Moreover, the invention also discloses a motion detecting device, a background model establishing method and a background model establishing device. The disclosed technical scheme of the invention can increase motion detecting accuracy.

Description

technical field [0001] The invention relates to motion detection technology, in particular to a motion detection method and device, and a background model establishment method and device. Background technique [0002] Motion Detection is an important field of Computer Vision research, and has a wide range of applications in video surveillance and intelligent transportation. Current motion detection methods mainly include pixel-based detection methods and region-based detection methods. [0003] In the prior art, the pixel-based detection method, such as the hybrid Gaussian motion detection method (MoG), only considers the information of each pixel independently and ignores the correlation between each pixel in the image area, and loses a lot Valuable information; and usually all pixels are processed, the amount of calculation is large, which is not conducive to real-time applications. Region-based detection methods, such as the feature background method (EigenBackground), ...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the pixel-based detection method, such as the hybrid Gaussian motion detection method (MoG), only considers the information of each pixel independently and ignores the correlation between each pixel in the image area, and loses a lot Valuable information; and usually all pixels are processed, the amount of calculation is large, which is not conducive to real-time applications

Region-based detection methods, such as the feature background method (EigenBackground), first collect training background images, and then use principal component analysis (also known as principal component analysis, PCA) technology to extract the characteristics of the background image to describe the background, but the PCA technology ignores the training The temporal characteristics of the background image sequence, so the trained background model loses the temporal characteristics of the background image sequence, which affects the accuracy of motion detection

Images