Self-adaptive threshold value moving object detection method based on codebook background model

Abstract

The invention discloses a self-adaptive threshold value moving object detection method based on a codebook background model, which belongs to the technical field of intelligent video monitoring. The method comprises the following steps of (1) classifying an inputted video image sequence into a training set and a detection result set, and creating an initial codebook background model for the inputted training set through a self-adaptive threshold value method; (2) purifying and optimizing the created initial codebook background model through a time filtering way; (3) applying the purified codebook background model to the foreground detection, and subtracting the codebook background model adopting the front n frames of image which is used as a training sample as the training set by the subsequently inputted video image sequence; and (4) binarizing the obtained differential image, and utilizing the binary image as a final detection result image. By adopting the method, the threshold value can be self-adaptively adjusted, so that compared with the traditional detection method, the method has the advantages that a better detection result can be obtained, and the accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of intelligent video monitoring, and relates to an adaptive threshold moving target detection method based on a codebook background model. Background technique [0002] In recent years, with the wide application and rapid development of intelligent video surveillance technology in the field of computer vision, moving object detection as the basis of intelligent video surveillance and intelligent video analysis has also achieved fruitful results. Various moving object detection algorithms It has been proposed and improved continuously, and more and more intelligent monitoring systems based on moving object detection have been put into use. However, there are still many problems in the research of moving target detection that have not been well resolved. The reason is that there are many situations that cause background changes whether it is outdoors or indoors: outdoors and other environments that cannot cont...

AI Technical Summary

Problems solved by technology

[0005] Since the codebook background modeling algorithm manually sets the thresholds of different matching conditions according to different videos, and the thresholds of different videos will vary greatly, this manual setting of thresholds not only increases the number of algorithm implementers. The impact of human factors on the test results also makes the test results unstable

Images