Moving object detection method based on self-adapting kernel density estimation model

Abstract

The invention discloses a moving object detection method based on a self-adapting kernel density estimation model. The method includes the steps that a background model based on kernel density estimation is built according to input videos, and accordingly the width of a probability density function of pixels of the input videos and the width of a kernel function are obtained; according to the width of a probability density function of gray values of the pixels of the input videos and the width of the kernel function, a probability value interval of a sample point is determined, then probabilities of the gray values of all the pixels are traversed, and accordingly a probability distribution histogram is formed; secondary linear interpolation and small threshold difference are carried out on the probability distribution histogram, and accordingly a difference histogram is obtained; a foreground threshold and a background threshold are solved in a self-adaptive mode according to the difference histogram; the built background model is updated according to the probability values of the gray values of the pixels of the input videos, the foreground threshold and the background threshold. The method has the advantages of being little in calculation quantity, good in instantaneity and few in error, and can be widely used in the field of computer visual analysis.

Description

technical field [0001] The invention relates to the field of computer vision analysis, in particular to a moving target detection method based on an adaptive kernel density estimation model. Background technique [0002] Moving object detection in video sequences has a wide range of applications, including intelligent transportation, bank monitoring, and human-computer interaction. The background subtraction method is a commonly used moving target detection method, which mainly removes the background from the current frame through "subtraction operation", so as to obtain a complete foreground moving target. Background modeling is very sensitive to dynamic environments such as illumination and climate. When the update of the background model cannot adapt well to changes in the dynamic environment, it will greatly affect the detection results of moving objects. Therefore, how to obtain a stable and reliable background is the key to moving target detection based on the backgro...

AI Technical Summary

Problems solved by technology

Elgammal et al. proposed a non-parametric background model based on kernel density estimation. This method makes full use of recent historical frame information to represent the background model, which can adapt to complex pixel distribution densities and overcome frequent changes in pixel values ​​in a short period of time. Because it uses a single threshold, it inevitably brings classification errors, and its calculation cost is too high

Mao Yanfen and others used the kernel density estimation method based on the principle of diversity sampling to establish a background model, and extracted smaller samples with high frequency and diversity from the original samples, thereby reducing the amount of calculation for background estimation, although improving time efficiency , but still cannot meet the real-time requirements of the system

Hu Min et al proposed to use the inter-frame difference combined with the background difference method before kernel density estimation to filter out relatively static background points, and only perform kernel density estimation on typical moving pixels to reduce the amount of calculation, but the introduction of inter-frame difference combined When the background is differentiated, its error is also introduced, which may easily lead to incomplete extraction of the foreground target

Images