A moving object detection method based on multi-threshold self-optimized background modeling

Abstract

The invention provides a moving target detection method based on multi-threshold self-optimized background modeling, which can quickly eliminate artifacts in detection results and has strong anti-interference ability to complex environments. To achieve this goal, the technical solution adopted is: use 20 neighborhoods of pixels to create a background model; use the adaptive distance threshold of the gray space and the color distortion threshold of the RGB space to judge the color of a new frame simultaneously. Whether the pixel value belongs to the background; remove the noise and fill the hole in the foreground area through noise removal, hole filling and median filter processing; count the frequency of the foreground point and update the background model accordingly, and the moving target and the background can be combined on the image Displayed using binary segmentation. The method of the invention can be widely used in the fields of traffic video monitoring, indoor security, computer vision and the like, and has broad application prospects and great economic value.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a moving target detection method, in particular to a moving target detection method based on multi-threshold self-optimizing background modeling. Background technique [0002] Moving object detection technology is a key technology in the field of computer vision. Its main purpose is to separate the moving objects in the video information from the background, so as to extract clear and complete moving objects. Currently common moving target detection methods include frame difference method, background difference method, mixed Gaussian modeling method, codebook method and visual background extraction method, etc. Among them, the visual background extraction algorithm is a moving object detection algorithm based on random background pixel modeling proposed by Barnich et al. in 2009. It occupies less memory and runs fast, and is suitable for video monitoring and automatic processing fi...

AI Technical Summary

Problems solved by technology

However, since this method uses the first frame image in the video sequence to establish a background model, it is easy to regard the moving object in the first frame as a background point, resulting in artifacts in the detection images of subsequent frames and the artifacts are not easy to eliminate

And in a complex background environment, this method is prone to noise, which leads to a decrease in detection accuracy. Therefore, it is important to study a method that can quickly suppress artifacts and have anti-interference capabilities.

Images