Motion detecting method and apparatus

Abstract

The invention discloses a method for motion test which includes the following steps: according to the same rule, a current frame image and a reference frame image are respectively divided into at least a current window image and a reference window image; then according to the same rule, the current window image and the reference window image are divided into at least two current sub-window images and reference sub-window images; relative values of brightness of the current sub-window images, and of the reference sub-window images are obtained; then the difference between the relative value of brightness of the current sub-window images and that of the reference sub-window images is obtained and compared, and the preset threshold value is also compared; at last, the result of motion test is obtained according to the result of comparison. The invention also discloses a motion test device at the same time. The method and device of the invention are capable of avoiding the effect on motion test result which is obtained from change of brightness in the environment and increasing accuracy rate of the motion test.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a motion detection method and device. Background technique [0002] Generally speaking, the brightness of different areas of an object is different, so when the object is photographed or monitored at a certain position, if the object is in a moving state, the brightness value of the image captured by the camera or monitor will also vary with the changes with the movement of the object. Utilizing the connection between the brightness value change of the image and the motion state of the object, it is possible to detect whether the object has moved. [0003] Fig. 1 is the flow chart of the motion detection method in the prior art, as shown in Fig. 1, this method is specifically realized by the following steps: [0004] Step 101, acquire a reference frame image and a current frame image, divide the reference frame image and the current frame image into a current window image and a ...

AI Technical Summary

Problems solved by technology

[0011] It can be seen from the above technical solutions that the motion detection method in the prior art judges whether the object of motion detection has moved by judging whether the difference between the current luminance statistical value and the reference luminance statistical value is greater than the threshold value. The object of motion detection does not move, but the brightness of the environment where the motion detection object is located has a large change, so that the environment brightness value has a large change, then it will also cause the current brightness statistical value and The difference between the reference luminance statistical values ​​is greater than the threshold, so that the result of motion detection using the motion detection method described in Figure 1 does not match the actual situation, and the accuracy of motion detection is not high

Images