Monitor image anomaly detection method and device

Abstract

The invention discloses a monitor image anomaly detection method and device, and belongs to the field of video monitoring. The method comprises the steps: foreground pixel points in a target monitor image are determined based on a mixture Gaussian background model; the amount of the foreground pixel points in the target monitor image can be counted to obtain first pixel amount; second pixel amount can be determined based on an edge detection algorithm, and the second pixel amount is the amount of pixel points of which edge detection values in the target monitor image are greater than a first preset threshold value and positions in the target monitor image do not belong to a plurality of specific positions contained by an edge model; weighting and combining are performed on the first pixel amount and the second pixel amount, and a weighted statistical value is obtained; and when the value is greater than a second preset threshold value, the target monitor image is determined as an abnormal image. According to the invention, a way of combing foreground information and edge information is adopted to perform anomaly detection on a monitor image, and the accuracy and stability of the anomaly detection can be improved.

Description

technical field [0001] Embodiments of the present invention relate to the field of video surveillance, and in particular, to a method and device for detecting anomalies in surveillance images. Background technique [0002] With the development of science and technology and people's concern about safety, the application of monitoring devices is becoming more and more extensive. Through the monitoring devices, people can obtain the monitoring video of a specified scene, so as to monitor the specified scene. In addition, in the field of video surveillance, anomaly detection can also be performed on surveillance images in surveillance videos through surveillance algorithms to automatically identify anomalies in surveillance images. [0003] In the prior art, a background modeling algorithm is usually used to construct a background model for a certain location area, so as to detect abnormalities in the surveillance images of the location area. Specifically, a plurality of sample...

AI Technical Summary

Problems solved by technology

[0004] However, because the background model constructed by the background modeling algorithm usually has a certain tolerance of color difference, that is, the pixels in the monitoring image and the color in the location area are usually judged as background pixels, so when there is When an external object with a color similar to the location area enters the specified scene, the background model often does not achieve a good anomaly detection effect, resulting in low accuracy and stability of anomaly detection

Images