Target detection method based on background reconstruction

Abstract

The invention discloses a target detection method based on background reconstruction. The method comprises a step of determining a value range of N to be a range from ft to 2f according to the a time t of detection system initialization and a frame frequency f of an image acquisition device in the detection system, a step of obtaining continuous N frames of video images from a k-(N-1) frame to a current frame k and obtaining a reconstruction background image through taking a pixel average value, a step of using a background difference method to cut images for the reconstruction background image and the current frame k images, and carrying out morphological filtering to obtain a background difference image B (k), a step of calculating a difference image D(k) of images of a kth frame and a (k-r) frame with r as a frame difference, wherein r is larger than or equal to 5, and a step of determining a target position through comparing the background difference image B (k) and the difference image D(k). By using the method, an ideal background model can be obtained, and thus the accuracy of a detection result is improved.

Description

technical field [0001] The invention relates to the technical field of automatic detection of moving targets, in particular to a target detection method based on background reconstruction. Background technique [0002] As the basic work of the entire video surveillance, moving object detection affects the performance of the entire monitoring system. Only by separating the moving object from the background in real time, accurately and reliably can the accuracy of the subsequent steps be guaranteed. However, the detection of moving objects is not an easy task, and it remains a challenging subject. When detecting a moving target, we cannot simply consider the pixel changes in the image, the corresponding pixel changes of the moving object, the pixel changes caused by camera shake, weather conditions, light changes, shadow movement, and object disturbance in the background, etc. will give a moving target detection. Timeliness and reliability are affected. People always hope th...

AI Technical Summary

Problems solved by technology

However, when the contrast between the moving area and the background image is too small, or there is noise in the image, the optical flow field method to detect the moving area simply based on the gray intensity of the image will lead to a high false alarm rate.

In addition, the calculation of this method is complex and time-consuming, unless there is special hardware support, it is difficult to achieve real-time motion area detection

As a result, the practicability of the optical flow calculation method is relatively poor

[0006] The advantage of the background subtraction algorithm is that it is easy to operate, has a small amount of calculation, good real-time performance, and accurate detection position, and generally can provide the most complete moving target information, but the usual background subtraction method is not suitable for dynamic scene changes, such as lighting It is particularly sensitive to interference from external unrelated events, and the shadow of a moving target is often detected as a part of the moving target, which affects the accuracy of the detection result

Images