High-efficient low-complexity motion detection method applicable to image processing

Abstract

The invention provides a high-efficient low-complexity motion detection method applicable to image processing, which comprises the following steps: (1) converting the format of images, and zooming the images to obtain the image size in actual use; (2) dividing each image into an integral number of pixel sub blocks according to the image size in the actual use; (3) calculating the accumulated sum of each pixel sub block in the current frame of image, and calculating the ratio of the accumulated sums of the adjacent pixel sub blocks; (4) calculating the accumulated sum of each pixel sub block in a next frame of image, and calculating the ratio of the accumulated sums of the adjacent pixel sub blocks; (5) calculating the difference ratios of the ratio of the accumulated sums of the corresponding adjacent pixel sub blocks of the current frame and the next frame, and calculating the total number of the difference ratios greater than a set threshold value; (6) calculating the ratio of the total number of the difference ratios greater than a set threshold value to all the pixel sub blocks in the current frame and the next frame; and (7) judging whether the ratio is greater than a warningthreshold value according to the calculation result in step (6), and if so, indicating that motion is detected in the images.

Description

technical field [0001] The invention relates to the field of digital video monitoring, in particular to an efficient and low-complexity motion detection method applied to image processing. Background technique [0002] With intelligence being more and more applied in the monitoring field. In some monitoring places, the security requirements are relatively high, and moving objects need to be detected and tracked in time, so we need some accurate image detection technologies to provide automatic alarm and target detection. Motion detection refers to the ability to identify image changes in a specified area, detect the existence of moving objects and avoid interference caused by light changes. But how to extract the changing area from the background image from the real-time sequence image requires an effective motion detection algorithm to make motion feature judgment. Currently commonly used algorithms include: Background Subtraction Obtain a "background frame" or "backgroun...

AI Technical Summary

Problems solved by technology

Currently commonly used algorithms include: Background Subtraction Obtain a "background frame" or "background model" such as the commonly used Gaussian background model through modeling and certain learning, and then calculate the difference between the current frame and the background frame, and the difference exceeds Pixels with a certain threshold are considered to be foreground points or moving objects. If the number of these points exceeds a certain threshold, the current image is considered to be in motion. The disadvantage is that it is particularly sensitive to changes in dynamic scenes, such as lighting and interference from external irrelevant events.

Temporal Difference (Temporal Difference) calculates the difference between all corresponding position pixels in consecutive 2 and 3 frames in the image sequence, and counts the number of pixels whose difference is greater than a certain threshold. When the number of these points exceeds a certain threshold, the current image is considered There is movement, but the disadvantage is that it is generally impossible to fully extract all the relevant feature pixels, and it is easy to generate holes in the moving entity

If there is no moving target in the image, the optical flow vector changes continuously in the entire image area. When there is relative motion between the object and the image background, the velocity vector formed by the moving object must be different from the field background velocity vector, so as to detect the current image There is movement, the disadvantage is that the calculation method is quite complicated, and the anti-noise performance is poor, etc.

Images