Method for detecting characteristics of video object in finite complex background

Abstract

The invention provides a method for detecting the characteristics of a video object in a finite complex background by studying color-based and gradient-based background models. The method comprises the following steps: 1, taking a background scene graph, conducting continuous training on a background sample image to obtain a color-based background model of mixed Gaussian distribution. If the background model conforms to the mixed Gaussian distribution, the gradient distribution functions of various combinations need to be calculated, and if a certain pixel belongs to any gradient distribution, the background model is supposed to conform to the gradient background model; 2, calculating the gradient distribution functions of each image to be detected, and establishing a color- and gradient-based background model; and 3, updating the parameters and weight of Gaussian distribution according to the ambient changes, such as illumination, wind strength and the like, and further updating thecolor-based models and the color- and gradient- based models. Compared with the prior art, the invention has the characteristics of background disturbance resistance and adaption to changes in environmental illumination.

Description

technical field [0001] The invention belongs to the technical field of video monitoring, and relates to a feature detection method of a video target under a limited and complex background. Background technique [0002] Moving object detection is at the bottom of the intelligent video surveillance system and is the basis for various subsequent advanced processing such as object tracking, object classification, and behavior understanding. The intelligent video monitoring system uses a static camera to monitor a fixed area in real time. Its purpose is to segment dynamic targets from the static background, and perform operations such as classification and tracking on them. For static cameras, background modeling is an effective method to solve real-time segmentation of dynamic objects. [0003] An effective background model should be able to overcome the following problems that often exist in practical applications: [0004] (1) Extraction of the background model: The simplest...

AI Technical Summary

Problems solved by technology

[0008] (5) The influence of shadows: usually the shadow of the foreground target is also detected as a part of the moving target, which will affect the further processing and analysis of the moving target

[0009] The previous methods either cannot solve all the above problems, or solve them by constructing complex models, which requires a large amount of calculation and relatively high requirements on the system, and sometimes may not meet the requirements of real-time processing

Images