Motion detection optimization method based on ViBe algorithm

Abstract

The invention discloses a motion detection optimization method based on a ViBe background modeling algorithm. A novel method is used for obtaining a group of background models, the novel background models have time information and space information simultaneously, the false detection rate can be lowered, and the error rate of background updating can be reduced; an ideal background model is composed of true background points, and therefore it is hoped to obtain a background model with credibility as high as possible in the background updating process. According to the method, samples of the background models are divided into a group with high credibility and a group with low credibility through a simple method, the samples with the high credibility are reserved, and the background models with the low credibility are updated randomly; by the adoption of the updating method, the credibility of the reserved background model samples can be higher and higher; in terms of postprocessing, filtering processing is added in addition to morphological operation, and abnormal points in a foreground image are further removed.

Description

technical field [0001] The invention relates to the field of moving target detection algorithms in image processing, in particular to a motion detection optimization method based on ViBe algorithm. Background technique [0002] Moving object detection technology is one of the key steps in information extraction in computer vision. Its core is how to quickly and accurately extract moving objects from video sequences, which is an important basis for subsequent image analysis. Widely used in video surveillance, human detection, 2D-3D video conversion and traffic detection and other fields. [0003] Motion detection algorithms are mainly divided into three categories according to their working principles: optical flow method, frame difference method, and background subtraction method. The optical flow method can realize the extraction of moving objects in the video shot by the moving camera, but it has a large amount of calculation and is less useful; the frame difference metho...

AI Technical Summary

Problems solved by technology

However, it does not perform well in scenes with dynamic backgrounds, the detection results have a lot of noise, and the integrity of moving objects is also lacking.

From the perspective of the principle of the ViBe algorithm, the process of establishing the background model is to sample 20 times from the eight field pixels of the pixel point x, and there will be repeated sample points. In the threshold segmentation process, it may be due to these erroneous repetitions Points get wrong segmentation results, and the random update of the model is also difficult to remove these abnormal sample points as soon as possible

The ViBe algorithm also has poor processing results for slow moving large objects

Images