An intelligent monitoring method, system, device and storage medium

Abstract

The present application discloses an intelligent monitoring method, system, device and storage medium. The method includes: step S11: creating a mixed Gaussian model; step S12: comparing each pixel of the current image to be processed with the current K Gaussian distributions Matching; Step S13: Classify different pixels in the current image to be processed into corresponding areas to obtain the first type of area and the second type of area; Step S14: Assign an update rate to the area, and update the current K Gaussian distributions , and then re-enter step S12 until the number of cycles reaches the preset cycle number threshold; the update rate corresponding to the first type of area is greater than the update rate corresponding to the motion area; step S15: select B Gaussian distributions closest to the actual background; step S16: Match each pixel point in the new video frame image with the B Gaussian distributions to obtain foreground points and background points. The application avoids the phenomenon of voids when detecting moving objects, and improves the accuracy of foreground detection.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to an intelligent monitoring method, system, equipment and storage medium. Background technique [0002] At present, intelligent video surveillance is widely used, and can be used for infant monitoring, car environment monitoring, etc. The key issue of intelligent monitoring is foreground detection. The most commonly used and common detection method for foreground detection is the detection algorithm based on the mixed Gaussian model. For example, the patent number is "201310595061.2", an invention patent titled "Motion detection method based on shared Gaussian model under disturbing motion environment", the invention discloses a motion detection method based on shared Gaussian model under disturbing motion environment. The motion is modeled in real time, and the established Gaussian model is shared to every point of every frame of the video stream. When the target object...

AI Technical Summary

Problems solved by technology

However, when the mixed Gaussian model algorithm detects the internal pixels of a moving object with a large and consistent color, it is easy to generate a hole phenomenon inside the moving object, which leads to false detection.

Images