Camera masking intelligent detection method

Abstract

The present invention relates to the field of intelligent traffic, and relates to a camera masking intelligent detection method, in particular to a camera masking detection method using video images and based on machine learning method. The specific technological process of the method comprises the following steps: image down sampling, Gabor filtering processing, PCA dimensionality reduction processing, data training and masking judgment. The uniform LBP features of an image are used as features of learning classification, so that a support vector machine is trained. The trained parameters are used for judging whether the new image is masked or not. A collected image sample is subject to Gabor filtering processing, so that stability and accuracy of the uniform LBP features of the image sample are improved. The uniform LBP features are subject to PCA dimensionality reduction processing to reduce trained data size of the support vector machine. The method is reliable in principle, rapid in judgement, high in judging accuracy, low in implementation cost, and friendly in applying environment.

Description

[0001] Technical field: [0002] The invention belongs to the field of intelligent transportation, and relates to an intelligent detection method for camera occlusion, in particular to a method for detecting camera occlusion using video images and based on a machine learning method; by using the uniformLBP feature of the image as a learning classification feature to support vector machines Training, use the trained parameters to judge the new image to judge whether the camera is blocked. [0003] Background technique: [0004] With the improvement of the traffic management system and electronic surveillance, each city will have more than 1,000 video cameras. During the video surveillance process, the cameras are easily blocked, resulting in the loss of surveillance information or errors in illegal capture; at present, regular inspections are still performed manually Problematic cameras are traditionally used to solve similar problems, but this is labor-intensive, time-consuming...

AI Technical Summary

Problems solved by technology

[0004] With the improvement of the traffic management system and electronic monitoring, each city will have more than 1,000 video cameras. During the video monitoring process, the cameras are easily blocked, resulting in the loss of monitoring information or errors in illegal capture; at present, regular inspections are still carried out manually Problematic cameras The traditional method is used to solve similar problems, but the labor cost is high, time-consuming and labor-intensive, and it is prone to omissions or negligence, which brings inconvenience to the maintenance of the camera

Camera occlusion often occurs in video surveillance. There are many reasons for occlusion, some are caused by man-made occlusion, and some are occlusion caused by the growth of roadside trees and leaves. These situations are usually not noticeable, but they will affect the video. Surveillance has serious consequences

At present, camera occlusion detection through image processing is also being tried, but the result is often a failure. The reason is that the occlusion of the camera is different, and it is not well processed according to the image characteristics.

Images