Block-based motion region detection method

Abstract

The invention relates to a video analyzing and monitoring technology, in particular to a block-based motion region detection method during monitoring a video sequence. The method comprises the following steps of: converting a pixel point difference into a pixel subblock difference by using a statistical method by using a pixel subblock as a minimum detection unit; setting on a background modeling basis; counting a noise level in time and space by utilizing a background difference method; then, dividing an image to be detected into mutually stacked pixel subblocks; and judging whether a motion target exits in a pixel subblock by using a background as a reference frame and counting a brightness difference, a gradient difference and a gradient direction difference between each pixel point in the pixel subblock and a corresponding pixel point in the reference background. By the invention, a low-contrast scene can be effectively processed, the uniform illumination change is suppressed, and the integrity of the motion region is guaranteed.

Description

technical field [0001] The invention relates to video analysis and monitoring technology, in particular to a block-based motion region detection method in monitoring video sequences. Background technique [0002] Video moving target detection algorithms mainly include background difference method, frame difference method and optical flow method. The optical flow method uses the optical flow characteristics of the moving target over time. The main advantage is that the target has less movement restrictions between frames; the disadvantage is that the calculation method is complicated and the real-time performance is difficult to guarantee. The inter-frame method detects moving objects based on the difference between adjacent frames. The inter-frame difference method has a strong ability to adapt to scene changes, and has a relatively strong anti-scene interference ability, which can avoid the interference of light changes in the scene. The disadvantage is that there is a "ho...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the background difference method in the prior art, which is sensitive to the interference of the scene, cannot well adapt to sudden changes in illumination, and cannot recognize dynamic backgrounds such as various swaying branches or water flows, etc., and provides a method set in On the basis of background modeling, the background difference method is used to count the noise level in space and time, and then the image to be detected is divided into overlapping pixel sub-blocks, and the background is used as the reference frame, and the pixel points in the pixel sub-block correspond to the reference background by counting The brightness, gradient and gradient direction difference of the pixel point are used to judge whether there is a moving object in the pixel sub-block. A block-based moving area detection method