Camera fault detection method, device and computer equipment

Abstract

Embodiments of the invention provide a camera fault detection method and device, computer equipment and a computer readable storage medium. The camera fault detection method includes the following steps: obtaining a first image currently used for fault detection, wherein the first image is an image in a monitoring video collected by a first camera of a to-be-detected fault; performing target detection on the first image and obtaining a number of targets included in the first image; determining a first traffic threshold corresponding to the first camera; and determining whether the first camerahas faults according to the number and the first traffic threshold. Through the camera fault detection method provided by the embodiments, the accuracy of camera fault detection can be improved.

Description

technical field [0001] The invention relates to the technical field of monitoring, in particular to a camera fault detection method, device, computer equipment and a readable storage medium. Background technique [0002] With the continuous development of information technology, the application level of urban informatization has been continuously improved, and the construction of smart cities has emerged as the times require. Building a smart city is of great significance in achieving sustainable urban development, leading the application of information technology, and enhancing the city's comprehensive competitiveness. [0003] As a link in the construction of smart cities, the video surveillance system has become increasingly important. As an important part of the video surveillance system, the camera is mainly used to collect video image information and transmit the collected video image information to the video surveillance platform to provide information support for th...

AI Technical Summary

Problems solved by technology

Specifically, traditional image processing algorithms are used to analyze and judge the brightness, color cast, clarity, stripes, noise, etc. of the image. If there are problems, such as abnormal image texture and high noise, it means that the corresponding camera may have Fault

[0005] However, the above-mentioned fault detection algorithm has poor adaptability. For scenes such as rainy and snowy days, forward and reverse light, the image obtained by the camera itself has many noises and other problems, and false alarms are prone to occur; in addition, for artificial torsion damage, the camera cannot work normally. , such as turning the camera to face the sky or a corner, etc., as long as the obtained image is normal, it is impossible to judge whether the corresponding camera is faulty, which leads to low fault detection accuracy of the camera

Images