Camera movement self-detecting method on the basis of image identification

Abstract

The present invention discloses a camera movement self-detecting method on the basis of image identification. The reliability and the accuracy of camera self detection may be effectively improved through an image matching identification technology. Through combination of partial characteristics and a global model, the camera movement self-detecting method on the basis of image identification may accurately estimate the state of the camera so as to determine whether the camera is moved or not, and the camera movement self-detecting method on the basis of image identification comprises an image obtaining module, a feature extraction module, an image retrieval module, an accurate matching module, a filtering module and a movement determination module. The method comprises the steps: (1) collecting static scenes at different times and different illuminations, and taking the collected static scenes as a set of reference images; (2) performing feature extraction of the set of reference images and real-time images; (3) retrieving images being the most similar to the real-time images in the set of the reference images; (4) performing accurate matching of the real-time images and the retrieved images; (5) effectively identifying the matching points, removing noise interference and choosing appropriate feature points; and (6) calculating corresponding transformation matrixes through adoption matching key points, and determining whether the camera is moved or not.

Description

technical field [0001] The invention belongs to the technical field of video monitoring, and relates to a monitoring system, more specifically, to a camera movement detection system in the monitoring system; meanwhile, the invention also relates to a camera movement detection method in the monitoring system. Through the collection of real-time images, the method of image recognition is used to detect the slow movement of the camera in the monitoring system. Background technique [0002] Surveillance cameras are widely used in public security and play a role of escort for social security. With the continuous increase of the surveillance system network, the number of cameras deployed in the network continues to increase, and there are more and more cameras in the surveillance system, which cannot be arranged Enough security personnel to check the working status of each camera. Many cameras cannot work normally due to long-term unmaintained, such as interference, virtual focus...

AI Technical Summary

Problems solved by technology

Although the method used in this invention is to track the variation range of pixel values ​​in the image to judge whether there is movement, the basis of its detection method is still based on whether the pixel intensity value changes at the same position between two images, but the invention uses The Gaussian statistical model establishes a statistical authority range for each pixel, and changes within a certain range are still regarded as the background. Therefore, although this invention can partially suppress the influence of noise and illumination, it is more sensitive to light changes, especially when the ambient light changes. When it is too fast, such as lightning, changes in sunlight, car lights, street lights, etc., will affect the performance of its algorithm and cause misjudgment

[0008] Most of the traditional camera movement self-detection methods judge whether the camera is moving based on changes in pixel values. This method is sensitive to light, noise, and moving objects in and out, and is prone to misjudgment.

Images