CN110769246A

CN110769246A - Method and device for detecting faults of monitoring equipment

Info

Publication number: CN110769246A
Application number: CN201910841584.8A
Authority: CN
Inventors: 周国中; 曾继平; 王伟刚
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2019-09-06
Filing date: 2019-09-06
Publication date: 2020-02-07
Anticipated expiration: 2039-09-06
Also published as: WO2021042816A1; CN110769246B

Abstract

The application provides a method and a device for detecting faults of monitoring equipment, wherein the method comprises the following steps: and acquiring background images in the front image and the rear image which are monitored and shot, and comparing the similarity of the two background images. When the similarity reaches a threshold value, the monitoring scene is changed, so that the monitoring equipment can be confirmed to send a fault, and the monitoring equipment can be automatically repaired.

Description

Method and device for detecting faults of monitoring equipment

Technical Field

The present application relates to the field of monitoring, and in particular, to a method and an apparatus for detecting a failure of a monitoring device.

Background

At present, the maintenance of the monitoring equipment mainly depends on the regular maintenance of manpower, that is, at intervals, technicians are arranged to check whether the monitoring equipment is in failure and to process the failure. On one hand, higher labor cost needs to be consumed, on the other hand, the maintenance efficiency is lower, and the fault is difficult to find and solve in time when the monitoring equipment is in fault.

Disclosure of Invention

The embodiment of the invention provides a method and a device for detecting faults of monitoring equipment, which are used for solving the technical problems of low efficiency and high cost of fault detection of the monitoring equipment in the prior art.

In a first aspect, a method for detecting a failure of a monitoring device is provided, which includes: acquiring a first background image and a second background image; the first background image is a background image in a current monitoring scene of a first monitoring device, and the second background image is a background image in a historical monitoring scene of the first monitoring device, which is stored in advance; calculating the similarity of the first background image and the second background image, and judging whether the monitoring scene of the first monitoring equipment is changed or not according to the similarity calculation result; and when the monitoring scene of the first monitoring equipment is changed, determining that the first monitoring equipment has a fault.

In the embodiment of the invention, whether the monitoring scene of the first monitoring device is changed or not is judged by comparing the background image (namely the first background image) in the current monitoring scene with the background image (namely the second background image) in the historical monitoring scene of the first monitoring device, and when the monitoring scene of the first monitoring device is changed, the first monitoring device is determined to be in fault.

In one possible embodiment, the first background image and the second background image capture the same object or the first background image and the second background image capture a part of the same object. Therefore, the current monitoring scene and the historical monitoring scene can be ensured to be in the same place, and the accuracy of monitoring equipment fault detection is improved.

In one possible design, after determining that the first monitoring device is faulty, a fault type of the first monitoring device may also be determined based on the first background image. Further, when the fault type of the first monitoring device is a fault type which does not need to be repaired manually, the first monitoring device performs automatic repair. And when the fault type of the first monitoring equipment is the fault type needing manual repair, sending a fault notification.

By the embodiment, the fault type of the first monitoring equipment can be determined, and when the fault type of the first monitoring equipment is the fault type which does not need to be repaired manually, the first monitoring equipment is automatically repaired, so that the fault processing efficiency is improved; and when the fault type of the first monitoring equipment is the fault type needing manual repair, sending a fault notification so that a technician can timely arrive at the site to carry out fault.

Two possible types of failures that do not require manual repair are listed below.

A first example, extracting a first feature point from the second background image, and defining the first feature point as a reference point; determining a second feature point matched with the reference point in the first background image; calculating a positional displacement amount of the second feature point with respect to the reference point; judging whether the shooting visual angle of the first monitoring equipment is abnormal or not according to the position offset; and when the shooting visual angle of the first monitoring equipment is abnormal, determining that the fault type of the first monitoring equipment is a fault type which does not need manual repair. Correspondingly, the automatic repair of the first monitoring device may be: and calculating the visual angle offset of the first monitoring equipment according to the position offset, and adjusting the lens parameter and/or the holder parameter of the first monitoring equipment according to the visual angle offset.

By comparing the first background image with the second background image, the camera lens parameter and/or holder parameter abnormity of the first monitoring device can be detected and processed in time, and the fault detection and maintenance efficiency of the monitoring device can be improved.

According to the second example, the monitoring parameters in the current monitoring scene of the first monitoring device are determined according to the first background image; determining whether the current shooting parameters of the first monitoring equipment are matched with the monitoring parameters in the current monitoring scene of the first monitoring equipment; when the current shooting parameters of the first monitoring equipment are not matched with the monitoring parameters in the current monitoring scene of the first monitoring equipment, determining that the shooting parameters of the first monitoring equipment are abnormal, and determining that the fault type of the first monitoring equipment is a fault type which does not need manual repair. Correspondingly, the automatic repair of the first monitoring device may be: determining shooting parameters matched with the monitoring parameters, and adjusting the shooting parameters of the first monitoring equipment to the shooting parameters matched with the monitoring parameters; or restarting the application process of the first monitoring equipment; or restarting the system of the first monitoring device. Optionally, in order to improve flexibility of the scheme, the shooting parameter may be brightness, chromaticity, saturation, contrast, sharpness, day and night mode conversion, exposure, focusing, backlight, white balance, image enhancement, light control of a fill-in lamp, and the like, which is not limited herein.

According to the embodiment, the monitoring parameters in the current monitoring scene of the first monitoring device can be determined based on the first background image, when the current shooting parameters of the first monitoring device are determined to be not matched with the monitoring parameters in the current monitoring scene of the first monitoring device, the shooting parameters are automatically adjusted to be the shooting parameters matched with the current monitoring parameters, the shooting parameters of the first monitoring device can be timely detected and processed to be abnormal, and the fault detection and maintenance efficiency of the monitoring device can be improved.

In one possible design, after the automatic repair of the first monitoring device, a third background image may also be acquired; the third background image is a background image of a monitoring scene shot by the first monitoring device after automatic restoration; calculating the similarity of the third background image and the second background image, and determining whether the fault of the first monitoring equipment is successfully repaired according to the similarity of the third background image and the second background image; and if the fault of the first monitoring equipment is not repaired successfully, sending a fault notification.

The method and the device can detect whether the automatic repair of the first monitoring device is successful or not, and remind technicians to maintain on site after the automatic repair of the first monitoring device is failed, so that the reliability and timeliness of fault maintenance of the monitoring device are further improved.

Three possible types of failures that require manual repair are listed below.

A first example of detecting whether there is a crack in the first background image; when a crack exists in the first background image, determining that the lens glass of the first monitoring device is damaged or stained, and determining that the fault type of the first monitoring device is a fault type needing manual repair. Accordingly, the sending of the failure notification may be: and sending notification information of damage or dirt of the lens glass of the first monitoring device to the terminal device linked with the first monitoring device.

This embodiment can confirm whether there is the unusual of damage, mar or dirty camera lens glass based on first background image or with first background image to when camera lens glass has the unusual such as damage, mar or dirty, in time initiate the trouble notice, so that the technical staff can in time learn and arrive the scene and change or repair first supervisory equipment's camera lens glass, improved supervisory equipment's fault detection and maintenance efficiency.

In a second example, when fog features exist in the first background image and shooting parameters of the first monitoring device are adjusted to be matched with fog days, and the fog features cannot be eliminated, it is determined that water enters a lens of the first monitoring device, and the fault type of the first monitoring device is determined to be a fault type needing manual repair. Accordingly, the sending of the failure notification may be: and sending notification information of lens water inflow of the first monitoring device to the terminal device linked with the first monitoring device.

According to the embodiment, whether the lens glass has the abnormality of fogging can be determined based on the first background image, and when the lens has the abnormality of fogging, the fault notification is initiated, so that a technician can timely know and arrive at the scene to solve the abnormality of fogging in the lens of the first monitoring device, and the fault detection and maintenance efficiency of the monitoring device is improved.

In a third example, the environmental facility condition in the current monitoring scene of the first monitoring device is determined according to the first background image, and the environmental facility condition in the historical monitoring scene of the first monitoring device is determined according to the second background image; when the environmental facility condition in the current monitoring scene of the first monitoring device is different from the environmental facility condition in the historical monitoring scene, determining the environmental facility change in the monitoring scene of the first monitoring device, and determining that the fault type of the first monitoring device is the fault type needing manual repair. Accordingly, the sending of the failure notification may be: and sending scene resetting notification information to the terminal equipment linked with the first monitoring equipment so as to remind technicians of carrying out scene resetting operation on the first monitoring equipment.

The embodiment considers the situation that the environmental facilities are changed in the actual scene, so that the user can decide whether to reset the background scene, the second background image is timely and accurately updated, and the reliability and timeliness of fault detection and maintenance of the monitoring equipment are further improved.

In one possible design, a fourth background image may be further acquired before determining the fault type of the first monitoring device based on the first background image; the fourth background image is a background image in a current monitoring scene of a second monitoring device, and the current monitoring scene of the second monitoring device is at least partially overlapped with the current monitoring scene of the first monitoring device. When determining the fault type of the first monitoring device, the fault type of the first monitoring device may be specifically determined according to the first background image and the fourth background image.

According to the embodiment, the type of the fault of the first monitoring equipment is analyzed and judged by combining the background image acquired by the second monitoring equipment, so that the accuracy of fault detection of the monitoring equipment can be further improved.

In a second aspect, an apparatus for detecting a failure of a monitoring device is provided, which includes: the acquisition module is used for acquiring a first background image and a second background image; the first background image is a background image in a current monitoring scene of the device, and the second background image is a background image in a historical monitoring scene of the device, which is stored in advance; the calculation module is used for calculating the similarity of the first background image and the second background image and judging whether the monitoring scene of the device is changed or not according to the similarity calculation result; and the determining module is used for determining the fault of the device when the monitoring scene of the device is changed.

In one possible embodiment, the first background image and the second background image capture the same object or the first background image and the second background image capture a part of the same object.

In one possible design, the determining module is further configured to: after determining the device failure, determining a failure type of the device based on the first background image; the device also comprises a repairing module used for automatically repairing the fault of the device when the fault type of the device is a fault type which does not need to be repaired manually.

In one possible design, the apparatus further includes: and the sending module is used for sending a fault notification when the fault type of the device is the fault type needing manual repair.

In a possible design, the determining module, when determining the type of failure of the apparatus based on the first background image, is specifically configured to: extracting a first characteristic point from the second background image, and defining the first characteristic point as a reference point; determining a second feature point matched with the reference point in the first background image; calculating a positional displacement amount of the second feature point with respect to the reference point; judging whether the shooting visual angle of the device is abnormal or not according to the position offset; when the shooting visual angle of the device is abnormal, determining the fault type of the device as a fault type which does not need manual repair; the repair module is specifically configured to: and calculating the visual angle offset of the device according to the position offset, and adjusting the lens parameters and/or the holder parameters of the device according to the visual angle offset.

In a possible design, the determining module, when determining the type of failure of the apparatus based on the first background image, is specifically configured to: determining monitoring parameters in the current monitoring scene of the device according to the first background image; determining whether the current shooting parameters of the device are matched with the monitoring parameters in the current monitoring scene of the device; when the current shooting parameters of the device are not matched with the monitoring parameters in the current monitoring scene of the device, determining that the shooting parameters of the device are abnormal, and determining that the fault type of the device is a fault type which does not need manual repair; the repair module is specifically configured to: determining shooting parameters matched with the monitoring parameters, and adjusting the shooting parameters of the device to be the shooting parameters matched with the monitoring parameters; or restarting the application process of the device; alternatively, the system of the device is restarted.

In one possible design, the shooting parameters include at least one of brightness, chromaticity, saturation, contrast, sharpness, day and night mode conversion, exposure, focusing, backlight, white balance, image enhancement, and fill lamp light control.

In one possible design, the obtaining module is further configured to: acquiring a third background image after the device is automatically repaired; the third background image is a background image of a monitoring scene shot by the device after automatic restoration; the calculation module is further to: calculating the similarity of the third background image and the second background image, and determining whether the fault of the device is successfully repaired according to the similarity of the third background image and the second background image; the apparatus also includes a sending module for sending a failure notification if the failure of the apparatus is not successfully repaired.

In a possible design, the determining module, when determining the type of failure of the apparatus based on the first background image, is specifically configured to: detecting whether a crack exists in the first background image; when a crack exists in the first background image, determining that the lens glass of the device is damaged or dirty, and determining that the fault type of the device is the fault type needing manual repair; the sending module is specifically configured to: sending notification information of damage or dirt of lens glass of the device to terminal equipment linked with the device; or

The determining module, when determining the type of the failure of the apparatus based on the first background image, is specifically configured to: when fog features exist in the first background image and shooting parameters of the device are adjusted to be matched with the fog days, and the fog features cannot be eliminated, determining that water enters a lens of the device, and determining that the fault type of the device is a fault type needing manual repair; the sending module is specifically configured to: sending notification information of lens water inflow of the device to terminal equipment linked with the device; or

The determining module, when determining the type of the failure of the apparatus based on the first background image, is specifically configured to: determining the environmental facility condition in the current monitoring scene of the device according to the first background image, and determining the environmental facility condition in the historical monitoring scene of the device according to the second background image; when the environmental facility condition in the current monitoring scene of the device is different from the environmental facility condition in the historical monitoring scene, determining the environmental facility change in the monitoring scene of the device, and determining the fault type of the device as the fault type needing manual repair; the sending module is specifically configured to: and sending scene resetting notification information to the terminal equipment linked with the device so as to remind technicians of carrying out scene resetting operation on the device.

In one possible design, the obtaining module is further configured to: acquiring a fourth background image before the determining module determines the fault type of the device based on the first background image; the fourth background image is a background image in a current monitoring scene of second monitoring equipment, and the current monitoring scene of the second monitoring equipment is at least partially overlapped with the current monitoring scene of the device; the determining module, when determining the type of failure of the apparatus based on the first background image, is to: determining a fault type of the device according to the first background image and the fourth background image.

In a third aspect, an apparatus for detecting a failure of a monitoring device is provided, comprising at least one processor coupled with at least one memory; the at least one processor is configured to execute the computer program or instructions stored in the at least one memory to cause the apparatus to perform the method according to the first aspect of the embodiments of the present invention or any of the possible designs of the first aspect.

In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program or instructions which, when read and executed by a computer, cause the computer to perform the method as set forth in the first aspect or any one of the possible designs of the first aspect of an embodiment of the invention.

In a fifth aspect, a chip system is provided, where the chip system includes a processor and may further include a memory, and is configured to implement the functions involved in the method according to the first aspect or any one of the possible designs of the first aspect of the embodiment of the present invention. The chip system may be formed by a chip, and may also include a chip and other discrete devices.

Drawings

FIG. 1 is an exemplary diagram of several monitoring devices in an embodiment of the present invention;

fig. 2A is a schematic structural diagram of a monitoring device according to an embodiment of the present invention;

FIG. 2B is a schematic diagram of another monitoring device according to an embodiment of the present invention;

FIG. 2C is a schematic diagram of another monitoring device according to an embodiment of the present invention;

FIG. 3 is a flow chart of a method for detecting a failure of a monitoring device in an embodiment of the present invention;

FIG. 4A is a diagram illustrating a first background image according to an embodiment of the present invention;

FIG. 4B is a diagram illustrating a second background image according to an embodiment of the present invention;

FIG. 4C is a diagram illustrating a second background image according to an embodiment of the present invention;

FIG. 5A is a diagram illustrating a second background image according to an embodiment of the present invention;

FIG. 5B is a diagram illustrating a first background image according to an embodiment of the present invention;

FIG. 5C is a diagram illustrating a fourth background image according to an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of an apparatus for detecting faults of monitoring devices according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of another apparatus for detecting failure of monitoring equipment in an embodiment of the present invention.

Detailed Description

In the field of video monitoring, monitoring equipment (such as several types of cameras shown in fig. 1) is often applied to outdoor scenes or large public indoor scenes, and can be used for realizing traffic event detection, pedestrian detection, license plate snapshot, traffic intersection violation snapshot, station monitoring and the like. In these scenes, the installation position of the monitoring device is high, and after long-time use, the monitoring angle of the monitoring device may be deviated, rotated, or even have no picture due to natural, artificial, or aging reasons. The maintenance of the existing monitoring equipment generally depends on the manual work of technicians to detect and maintain the monitoring equipment on site regularly, and the technicians cannot sense the abnormality of the monitoring equipment at the first time of the fault of the monitoring equipment, so the maintenance efficiency is very low, and in addition, higher labor cost is consumed.

In view of this, an embodiment of the present invention provides a method for detecting a failure of a monitoring device, where the method determines whether a monitoring scene of the monitoring device is changed by comparing a background image in a current monitoring scene of the monitoring device with a background image in a historical monitoring scene of the monitoring device, and determines that the monitoring device has a failure when the monitoring scene of the monitoring device is changed. Furthermore, after the monitoring equipment fault is determined, the fault type of the monitoring equipment can be determined based on the background image, and then the fault is timely solved according to the fault type decision and the fault processing strategy.

The current monitoring scene and the historical monitoring scene are in the same place.

In the embodiment of the present invention, the first background image and the second background image are photographed with: the same object, or a portion of the same object. Such as buildings, electrical poles, plants, ornaments. It should be noted that the same object (or a part of the object) may be imaged differently in the first background image and the second background image, for example, with different sharpness, noise amount, contrast, sharpness, etc.

In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings.

Referring to fig. 2A, which is a schematic structural diagram of a monitoring device according to an embodiment of the present invention, the monitoring device may include an image capturing portion and a control portion.

The camera shooting part is the front end of the monitoring equipment, is the 'eyes' of the whole monitoring equipment and is used for collecting image signals corresponding to a monitored place and transmitting the collected image signals to a monitor of a control center. The image pickup section is generally disposed at a position of a monitored place, and its angle of view can cover various portions of the entire monitored place.

The camera portion may be a camera, a video camera, a smart camcorder, a smart mobile terminal (such as a mobile phone), a tablet computer, and the like, and the embodiment of the present invention is not limited herein.

In some possible embodiments, the image capturing portion may include only one camera, and in other possible embodiments, the image capturing portion may include a plurality of cameras, and different cameras may have different angles of view, which is not limited herein. The camera may be an infrared camera, that is, the camera may shoot an infrared image, and the camera may also be a visible light camera, that is, the camera may shoot a color image. The camera includes an optical lens and an image sensor, which may be a charge-coupled device (CCD), a Complementary Metal Oxide Semiconductor (CMOS), a Contact Image Sensor (CIS), or the like.

In some scenes, in order to save the number of cameras used by the camera part, simplify a transmission system and a control and display system, an electric (remotely controllable) variable focal length (zoom) lens can be additionally arranged on the camera part, so that the distance which can be observed by the camera part is farther and clearer; the camera shooting part can be arranged on the cloud deck, and the cloud deck can drive the camera shooting part to rotate in the horizontal and vertical directions under the control of the console, so that the camera shooting part can cover a larger angle and a larger area.

The control part is the heart and brain of the whole system, and is a command center for realizing the functions of the whole video monitoring system. In the embodiment of the invention, the control part can finish the acquisition of images and the comparison of similarity, and can also adjust the direction and the angle of the camera/the holder. Some of the systems with more powerful functions will be described below, and the control part mainly comprises a main console (some systems are also provided with auxiliary consoles). The main functions of the master control console are as follows: video signal amplification and distribution, correction and compensation of image signals, switching of image signals, recording of image signals (or including sound signals), control (remote control) of the camera and its auxiliary components (such as lens, pan-tilt, protective cover, etc.), and so on. Another important aspect of the general control station is the ability to remotely control the cameras, lenses, holders, shields, etc. to accomplish a comprehensive and detailed surveillance or tracking surveillance of the monitored site. The master control station can also be provided with a video recorder for recording the images of the monitored places where the situations occur so as to be prepared for later use or be used as an important basis. The general control desk can also be provided with a multi-picture splitter, such as four pictures, nine pictures, sixteen pictures and the like, namely, the pictures of each monitored place sent by four, nine or sixteen cameras can be displayed on one monitor at the same time, and a conventional video recorder or a long-delay video recorder is used for recording.

The control portion includes at least one processor. The processor may include one or more of: general purpose processors, Image Signal Processors (ISPs), microprocessors, Digital Signal Processors (DSPs), field-programmable gate arrays (FPGAs), and the like.

The control section may also include one or more memories. The Memory may be, but is not limited to, a Read-Only Memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by the apparatus. The memory may be self-contained and coupled to the processor via a bus. The memory may also be integral to the processor.

The memory of the control portion may be used to store application program codes for executing the scheme of the present application, and the processor controls the execution, that is, the processor is used to execute the application program codes stored in the memory to implement the method for detecting the failure of the monitoring device in the embodiment of the present application.

In some scenarios, the memory may be integrated with the processor or may be free of memory, such as a Field-Programmable Gate Array (FPGA).

It should be noted that, in a specific implementation, the image capturing part and the control part may be integrated on the same physical device (for example, a tablet computer with a camera, a smart camera), or may be different physical devices, and the embodiment of the present invention is not limited herein. When the image pickup part and the control part are different physical devices, the image pickup part and the control part can be connected and communicated in a wired or wireless mode.

In other embodiments, the monitoring device may further include a display portion, as shown in fig. 2B, which is another schematic structural diagram of the monitoring device in the embodiment of the present invention. The display section may be composed of several or more monitors (or a general television set with video input). Its function is to display the images collected by the camera part one by one. The display portion may be integrated with the image capturing portion and the control portion on a physical device, or may be a single physical device, which is not limited in this embodiment of the present invention.

Of course, the method for detecting the failure of the monitoring device in the embodiment of the present invention may also be performed not by the monitoring device but by another apparatus in communication connection with the monitoring device.

For example, referring to fig. 2C, the monitoring device may be externally connected with a processing device, and the processing device may include one or more processors, and optionally, one or more memories. The memory in the processing apparatus may be used for storing application program codes for executing the scheme of the present application, and the processor in the processing apparatus controls the execution, that is, the processor in the processing apparatus is used for executing the application program codes stored in the memory in the processing apparatus to implement the method for detecting the failure of the monitoring device in the embodiment of the present application.

The following takes the monitoring device shown in fig. 2B as an example (i.e., the first monitoring device may be the monitoring device shown in fig. 2B hereinafter), and describes a method for detecting a fault of the monitoring device according to an embodiment of the present invention.

1) And the monitoring scene refers to an area shot by the monitoring equipment. For example, a monitoring scene of monitoring equipment arranged in a station is a station area that can be shot by the monitoring equipment; for example, a monitoring scene of a monitoring device arranged at a traffic intersection is an intersection area that can be photographed by the monitoring device.

2) The background image, or image background, background image, image background, etc., refers to an image corresponding to a background area in an area (i.e., a monitoring scene) photographed by a monitoring device. In other embodiments, the background area may also be a user-defined area, for example, an area where an object or an object that is not intended to be highlighted in a shooting picture of the monitoring device in the monitoring scene is located, and may be related to an interactive selection of a user or a system setting.

The background image may be all images in the image captured by the monitoring device or a part of the image captured by the monitoring device, depending on the specific situation of the monitored scene. For example, the monitoring scene of the monitoring device is a traffic intersection, if the monitoring device does not have vehicles, pedestrians, and the like at the traffic intersection when the monitoring device performs the shooting operation, and only road features exist in the image shot by the monitoring device, the image shot by the monitoring device is the background image, if the monitoring device performs the shooting operation, and the vehicles just pass through the traffic intersection, the image part corresponding to the vehicles in the image shot by the monitoring device may not be used as the background image, and correspondingly, the background image is the image part except the vehicles in the image.

3) The term "at least one" referred to below in the embodiments of the present invention means one or more than one, i.e., includes one, two, three and more; "plurality" means two, or more than two, i.e., including two, three, and more than two. In addition, it is to be understood that the terms first, second, etc. in the description of the present application are used for distinguishing between the descriptions and not necessarily for describing a sequential or chronological order. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.

Referring to fig. 3, a flowchart of a method for detecting a failure of a monitoring device according to an embodiment of the present invention is shown, where the method may be performed by an image/video monitoring device (e.g., a camera); but may be performed by other devices as well. And after the fault is detected, the other equipment sends a repair instruction to the monitoring equipment so as to instruct the monitoring equipment to repair. For convenience of understanding, the following steps are described by taking the monitoring device to execute steps S101 to S103 as an example (if steps S101 to S103 are executed by other devices, they will not be separately described because the principle is the same) the method includes the following steps:

s101, a first monitoring device acquires a first background image and a second background image; the first background image is a background image in a current monitoring scene of the first monitoring device, and the second background image is a background image in a historical monitoring scene of the first monitoring device, which is stored in advance.

Specifically, the first monitoring device may extract a first background image from the first image and a second background image from the second image by using a background modeling algorithm. The first image is an image currently acquired by the first monitoring device, and the second image is a historical image acquired by the first monitoring device before (for example, an image acquired by the first monitoring device one hour before the current time). The first background image is a background image in the first image, and the second background image is a background image in the second image.

In the embodiment of the present invention, the current monitoring scene and the historical monitoring scene are located at the same place. That is, the first monitoring device is required to be located at the same place when acquiring the first image and the second image, where the same place means that the relative distance between the position of the first monitoring device when acquiring the first image and the position of the first monitoring device when acquiring the second image is smaller than a preset value, for example, smaller than 0.1 m. One possible design is: the first background image and the second background image are captured with the same object, or a part of the same object. For example, if the first monitoring device is a monitoring device provided at a traffic intersection, the first background image and the second background image have the same road, green or traffic sign, and the like.

The background modeling algorithm may be a Single Gaussian Model (Single Gaussian Model) algorithm, a mixed Gaussian Model (Mixture of Gaussian) algorithm, a Running Gaussian average (Running Gaussian average) algorithm, a CodeBook (CodeBook) algorithm, a Self-organizing background detection (SOBS-Self-organizing background) algorithm, a sample consistency background modeling algorithm (SACON), a VIBE algorithm, a background modeling algorithm based on color information, a statistical averaging method, an intrinsic background method, etc., and embodiments of the present invention are not limited herein.

As an optional implementation manner, in the embodiment of the present invention, the second background image may also be pre-calculated and stored locally. Accordingly, a specific implementation manner of obtaining the second background image may be to locally read a pre-stored second background image.

In specific implementation, the first monitoring device may delete the second background image originally stored in the local area after each execution of the restart operation or the background reset operation, and store the background in the first frame image acquired after the restart or the background reset as the second background image in the local area. Optionally, the first monitoring device may also perform a background reset operation periodically according to a preset time interval, for example, perform a background reset every 5min, 30min, or 60min, so as to ensure that the background is updated in time. The second background image may also be stored not locally, e.g. in a dedicated storage server/storage array, to the first monitoring device when required.

It should be noted that, if the first monitoring device is a camera (such as a ball machine, a barrel machine, etc.) whose shooting angle can be changed, the second image and the first image are required to be images acquired by the first monitoring device at the same pan/tilt head position, that is, the position parameter of the pan/tilt head when the first monitoring device shoots the first image is required to be the same as the position parameter of the pan/tilt head when the first monitoring device shoots the second image, such as a pitch angle (tilt angle) and a rotation angle (pan angle) of the pan/tilt head.

S102, the first monitoring device calculates the similarity of the first background image and the second background image, and judges whether the monitoring scene of the first monitoring device is changed according to the similarity calculation result.

The method for calculating the similarity of the images may have various implementation manners, such as a structural similarity and perceptual hash algorithm, a babbitt distance algorithm, or a gray-scale color histogram algorithm, and the like, and the embodiment of the present invention is not limited herein.

As an optional implementation manner, before the similarity calculation is performed on the first background image and the second background image, the first monitoring device may perform histogram statistics and normalization preprocessing on the first background image and the second background image, and then calculate the similarity based on the preprocessed first background image and the preprocessed second background image.

After the similarity between the first background image and the second background image is calculated, whether the similarity is smaller than a preset first similarity threshold value is judged, if yes, the monitoring scene of the first monitoring device is determined to be changed, and otherwise, the monitoring scene of the first monitoring device is determined not to be changed.

S103, when the monitoring scene of the first monitoring device is changed, determining that the first monitoring device is in fault.

In the technical scheme of the embodiment of the invention, the first monitoring device judges whether the monitoring scene is changed or not by comparing the background image (namely the first background image) in the current monitoring scene with the background image (namely the second background image) in the historical monitoring scene, and when the monitoring scene of the monitoring device is found to be changed, the monitoring device is determined to be in fault.

As an alternative, in the embodiment of the present invention, the method steps of steps S101 to S103 may be periodically executed at set time intervals, for example, the method of steps S101 to S103 is executed every 10S, 20S or 1min, so that the timeliness of the fault detection of the monitoring device may be further improved. In addition, the first monitoring device may also be triggered to execute the methods of steps S101 to S103 through a trigger event, for example, a technician remotely sends a fault detection instruction, and after receiving the fault detection instruction, the first monitoring device responds to the fault detection instruction to execute the methods of steps S101 to S103.

As an optional implementation manner, after step S103 is executed, that is, after it is determined that the first monitoring device is faulty, fault processing may be performed, where the fault processing manner includes, but is not limited to, an apparatus self-test, a fault notification sending manner, and the like.

In specific implementation, the first monitoring device may execute different fault handling policies according to different fault types. Exemplarily, if the fault type of the first monitoring device is a fault type which does not need to be repaired manually, the first monitoring device is automatically repaired, so as to improve the fault processing efficiency; and if the fault type of the first monitoring equipment is the fault type needing manual repair, sending a fault notification so that a technician can arrive at the site in time to carry out fault.

As an alternative embodiment, the first monitoring device may determine the fault type of the first monitoring device based on the acquired background image, such as the first background image, or the background images of a preset number of frames adjacent to the first background image in front of and behind the first background image.

The following describes a manner of performing fault detection and fault handling for the first monitoring device in detail by taking several specific fault scenarios as examples.

Scene 1, abnormal parameters of a lens of the monitoring equipment and fault detection and processing caused by abnormal pan-tilt.

After confirming the self fault based on the scene change detection, the first monitoring device may extract at least one feature point from the second background image, where the feature point extracted from the second background image is defined as a first feature point in order to be distinguished from a feature point in a subsequent first background image; taking the at least one first feature point as a reference point; extracting feature points matched with the reference points from the first background image, wherein the feature points extracted from the first background image are defined as second feature points, and the number of the first feature points is equal to that of the second feature points; then, the position offset of the second feature point relative to the reference point is calculated, and whether the shooting visual angle of the first monitoring equipment is abnormal or not is judged according to the position offset.

If the visual angle direction of the first monitoring equipment is determined to be deviated according to the position deviation amount (the visual angle direction when the first image is shot is different from the visual angle direction when the second image is shot), but the visual angle is unchanged (the visual angle direction when the first image is shot is the same as the visual angle direction when the second image is shot, or the difference value of the two is smaller than the preset value), the visual angle direction of the monitoring equipment is determined to be abnormal, the current fault of the first monitoring equipment is determined to be a fault type which does not need to be repaired manually, and the first monitoring equipment can automatically adjust the holder parameters (such as the pitch angle and the rotation angle of the holder) of the monitoring equipment so as to restore the visual angle direction of the first monitoring equipment to the visual angle direction before change.

If the visual angle of the first monitoring device is determined to be changed according to the position offset (the visual angle when the first image is shot is different from the visual angle when the second image is shot, or the difference value between the two is larger than the preset value), but the visual angle is not changed (the visual angle when the first image is shot is the same as the visual angle when the second image is shot, or the difference value between the two is smaller than the set value), determining that the lens parameters of the monitoring device are abnormal, determining that the current fault of the first monitoring device is a fault type which does not need manual repair, and automatically adjusting the lens parameters (such as the focal length) of the monitoring device by the first monitoring device so as to restore the visual angle of the first monitoring device to the visual angle before the change.

If the visual angle size and the direction of the first monitoring equipment are determined to be changed according to the position offset, the visual angle size and the direction of the monitoring equipment are determined to be abnormal, the current fault of the first monitoring equipment is determined to be a fault type which does not need manual repair, and the first monitoring equipment automatically adjusts the holder parameters and the lens parameters of the monitoring equipment so as to restore the visual angle size and the direction of the first monitoring equipment to the visual angle size and the direction before the change.

Exemplarily, referring to fig. 4A and 4B, fig. 4A is a schematic diagram of a first background image, in which the first background image has two second feature points, A, B, whose coordinates are (1, 10), (5, 5), respectively, and fig. 4B is a schematic diagram of a second background image, in which the first feature points in the second background image matching the first feature points in the first background image are a ', B', whose coordinates are (2, 10), (6, 5), respectively. By comparing A, B with the coordinates of A 'and B', it can be determined that the viewing direction of the first monitoring device is shifted in the x-direction as shown. Thus, the first monitoring device can adjust the viewing angle in the-x direction to restore the viewing angle direction of the first monitoring device to before the offset.

Exemplarily, referring to fig. 4A and 4C, fig. 4A is a schematic diagram of a first background image, in which the first background image has two second feature points, A, B, whose coordinates are (1, 10), (5, 5), respectively, and fig. 4C is a schematic diagram of a second background image, in which the first feature points in the second background image matching the second feature points in the first background image are a 'and B', respectively, and their coordinates are (0.5, 5), (2.5 ), respectively. By comparing A, B with A 'and B', it can be determined that the size of the viewing angle of the first monitoring device has been reduced. Therefore, the first monitoring device can adjust the focal length of the lens to restore the size of the angle of view of the first monitoring device to the size before zooming out.

It should be noted that, if the first monitoring device is a camera (such as a ball machine, a barrel machine, etc.) whose shooting angle can be changed, the second image and the first image are required to be images captured by the first monitoring device at the same pan-tilt position. In addition, the position of the pan/tilt head of the first monitoring device when adjusting the lens parameters needs to be the same as the position of the pan/tilt head of the first monitoring device when shooting the first image.

According to the embodiment, the first background image and the second background image are compared, so that the lens parameter and/or holder parameter abnormity of the first monitoring device can be detected and processed in time, and the fault maintenance efficiency of the monitoring device can be improved.

And in the scene 2, detecting and processing faults caused by abnormal shooting parameters of the monitoring equipment.

After the first monitoring device detects and confirms the self fault based on the scene change, the monitoring parameters in the current monitoring scene of the first monitoring device can be determined according to the first background image, whether the current shooting parameters of the first monitoring device are matched with the monitoring parameters in the current monitoring scene of the first monitoring device is judged, when the current shooting parameters of the first monitoring device are determined to be not matched with the monitoring parameters in the current monitoring scene of the first monitoring device, the shooting parameters of the first monitoring device are determined to be abnormal, the fault type of the first monitoring device is determined to be the fault type which does not need manual repair, then the shooting parameters of the first monitoring device are automatically adjusted, and the shooting parameters of the first monitoring device are adjusted to be the shooting parameters matched with the monitoring parameters.

The monitoring parameters in the current monitoring scene may include brightness, color temperature, definition, weather conditions (such as sunny, cloudy, rainy, snowy, and foggy), and shooting scenes (such as buildings, plant flowers, sky, etc.). The shooting parameters may include brightness, chromaticity, saturation, contrast, sharpness, day and night mode conversion (black and white mode, color mode, automatic mode, etc.), exposure, focus, backlight, white balance, image enhancement (electronic anti-shake, noise reduction, fog penetration, etc.), sensitivity of an International Standards Organization (ISO), etc., and of course, in practical applications, the shooting parameters may also include other parameters, such as a shutter, an aperture, a focal length, a file format supported by a monitoring device, a resolution, etc., and the embodiment of the present invention is not limited herein.

The first monitoring device may also store a mapping relationship between the monitoring parameters and the shooting parameters in advance, so that the shooting parameters matched with the current monitoring parameters may be determined according to the mapping relationship table when the shooting parameters are adjusted.

As an optional implementation manner, in an embodiment of the present invention, in order to improve accuracy of the monitoring parameter, the first monitoring device may further obtain background images of a preset number of frames (for example, 5 frames before and after) adjacent to the first background image, and then determine the monitoring parameter in the current scene based on the first background image and the background images of the adjacent preset number of frames.

In the embodiment, the monitoring parameters in the current monitoring scene of the first monitoring device can be determined based on the first background image or the background images of the preset number of frames adjacent to the first background image, and when it is determined that the current shooting parameters of the first monitoring device are not matched with the monitoring parameters in the current monitoring scene of the first monitoring device, the first monitoring device automatically adjusts the shooting parameters to the shooting parameters matched with the current monitoring parameters, so that abnormal shooting parameters of the first monitoring device can be detected and processed in time, and the fault maintenance efficiency of the monitoring device can be improved.

Two specific fault types which do not need to be repaired manually are exemplified above, and in practical application, the fault types which do not need to be repaired manually can also comprise other specific implementation manners. The strategy for the first monitoring device to perform automatic repair is not limited to the adjustment of the shooting parameters, the lens parameters, the pan-tilt parameters, and the like, and other specific implementation manners may also be available, such as restarting a related application process of the first monitoring device, restarting a system of the first monitoring device, and the like.

And detecting and processing faults caused by scene 3 and abnormal lens glass of the monitoring equipment.

After the first monitoring device determines that the first monitoring device has a fault based on the scene change detection, it may detect whether a crack exists in the first background image (a specific implementation manner may be that crack detection is performed on the first background image based on an edge detection algorithm, a deep learning algorithm, and the like), when it is determined that the crack exists in the first background image, it is determined that the lens glass of the first monitoring device is damaged, scratched, or dirty, and it is determined that the fault type of the first monitoring device is a fault type that needs to be manually repaired, and then a fault notification is initiated, for example, notification information of damage, scratches, or dirty of the lens glass of the first monitoring device is sent to a terminal device linked with the first monitoring device, so that a technician can timely learn and arrive at a site to replace or repair the lens glass of the first monitoring device.

Similarly, in order to improve the crack detection accuracy, the first monitoring device may further acquire a preset number of frames (for example, 5 frames before and after) of background images adjacent to the first background image, and then determine whether the lens glass has an abnormality of breakage, scratch, or dirt based on the first background image and the preset number of frames of background images adjacent to the first background image.

This embodiment can confirm whether there is the unusual of damage, mar or dirty lens glass based on first background image or the background image of the adjacent predetermined number frame of first background image to when lens glass has the unusual such as damage, mar or dirty, in time initiate the fault notice, so that technical staff can in time learn and arrive the scene and change or repair first supervisory equipment's lens glass, improved supervisory equipment's fault maintenance efficiency.

And detecting and processing faults caused by abnormal water inflow or fogging of a scene 4 and a monitoring device lens.

After the first monitoring device confirms the self fault based on the scene change detection, whether fog characteristics exist in the first background image can be detected; if the weather information exists, the weather information in the current monitoring scene can be acquired, and when the weather condition is determined not to be in foggy days, the monitoring device lens is determined to have the fog abnormality, or when the fog characteristic cannot be eliminated after the shooting parameter of the first monitoring device is adjusted to be the shooting parameter matched with the foggy days, the monitoring device lens is determined to have the fog abnormality; and determining that the fault type of the first monitoring device is a fault type needing manual repair, and initiating a fault notification, for example, sending notification information of lens fogging of the first monitoring device to a terminal device linked with the first monitoring device. The notification mode may be a mail, a short message, a notification message of an instant messaging application, and the like, and the embodiment of the present invention is not limited here.

In addition, the first monitoring device can also detect whether the first background image has water drop characteristics; if the weather information exists, the weather information in the current monitoring scene can be acquired, and when the weather condition is determined not to be rainy, the fact that the lens of the monitoring device is abnormal in water inflow is determined, or when the water drop characteristic cannot be eliminated after the shooting parameter of the first monitoring device is adjusted to be the shooting parameter matched with the rainy day, the fact that the lens of the monitoring device is abnormal in water inflow is determined; and determining the fault type of the first monitoring device as a fault type needing manual repair, and initiating a fault notification, for example, sending notification information of lens water inflow of the first monitoring device to a terminal device linked with the first monitoring device.

Similarly, in order to improve the accuracy of the water inflow or fogging detection, the first monitoring device may further acquire a preset number of frames (for example, 5 frames before and after) of background images adjacent to the first background image, and then determine whether the lens glass has the abnormality of water inflow or fogging based on the first background image and the preset number of frames of background images adjacent to the first background image.

The method and the device can determine whether the lens glass has water inflow or fog-forming abnormity based on the first background image or the background images of the preset number of frames adjacent to the first background image, and initiate fault notification when the lens has water inflow or fog-forming abnormity, so that technical personnel can timely know and arrive at the scene to solve the water inflow or fog-forming abnormity in the lens of the first monitoring device, and the fault maintenance efficiency of the monitoring device is improved.

Scenario 5, detection and handling of faults caused by environmental facility changes.

After the first monitoring device confirms the self fault based on the scene change detection, the environmental facility condition in the current monitoring scene of the first monitoring device can be identified according to the first background image, and then the environmental facility condition in the historical monitoring scene of the first monitoring device can be identified according to the second background image; then, whether the environmental facility condition in the current monitoring scene of the first monitoring device is the same as the environmental facility condition in the historical monitoring scene is judged, when the environmental facility condition in the current monitoring scene of the first monitoring device is determined to be different from the environmental facility condition in the historical monitoring scene, the environmental facility change in the monitoring scene of the first monitoring device is determined, the fault type of the first monitoring device is determined to be the fault type needing manual repair, and a fault notification is initiated, for example, a notification message of scene reset is sent to the terminal device linked with the first monitoring device, so as to remind a technician of performing scene reset operation on the first monitoring device. Further, the first monitoring device may store the background in the first frame image acquired after the background reset as a new second background image locally after receiving a background reset operation performed by the user.

Considering that the actual scene has the change of environmental facilities, such as the actual scene of road resurfacing, greening maintenance and the like, the actual mode is used for the user to decide whether to reset the background scene, so as to ensure that the second background image is timely and accurately updated, and further improve the reliability and timeliness of fault maintenance of the monitoring equipment.

In practical applications, the types of faults requiring manual repair may also include other specific types of faults, which is not illustrated here in the embodiments of the present invention.

As an optional implementation manner, after the first monitoring device performs automatic repair, it may be further determined whether the fault of the first monitoring device is successfully repaired, and if the fault is not successful, a fault notification may be initiated to remind a technician to go to a field for maintenance.

Specifically, the first monitoring device may obtain a third background image, where the third background image is a background image of a monitoring scene shot after the first monitoring device performs automatic repair, then calculate a similarity between the third background image and the second background image, determine whether the fault of the first monitoring device is successfully repaired according to the similarity between the third background image and the second background image, and if the similarity is lower than a preset second similarity threshold, determine that the fault is not successfully repaired, may initiate a fault notification, for example, send a notification message that the fault is not automatically repaired to a terminal device linked with the first monitoring device, so as to remind a technician to perform maintenance on site. Wherein, the second similarity threshold is less than or equal to the first similarity threshold.

As an optional implementation manner, in order to further improve accuracy of fault detection, in the embodiment of the present invention, whether the first monitoring device fails and a type of the failure may be further determined by combining with a background image acquired by the second monitoring device, where a current monitoring scene of the second monitoring device and a current monitoring scene of the first monitoring device at least partially coincide.

Specifically, the first monitoring device acquires a fourth background image before determining the fault type of the first monitoring device, where the fourth background image is a background image in a current monitoring scene of the second monitoring device. Correspondingly, when the first monitoring device determines the fault type of the first monitoring device, the fault type of the first monitoring device is determined according to the first background image and the fourth background image.

The second monitoring device may be an electronic device of the same type as the first monitoring device, for example, both the second monitoring device and the first monitoring device are intelligent cameras, or an electronic device of a different type from the first monitoring device, for example, the first monitoring device is an intelligent camera, and the second monitoring device is a general camera.

Exemplarily, the above scenario 5 is taken as an example. Referring to fig. 5A to 5C, fig. 5A is a second background image in a historical monitoring scene of the first monitoring device, fig. 5B is a first background image in a current monitoring scene of the first monitoring device, and fig. 5C is a fourth background image in the current monitoring scene of the second monitoring device. The viewing direction of the first monitoring device is the y direction of the figure, and the viewing direction of the second monitoring device is the x direction of the figure. The first monitoring device detects that trees on the road above the first monitoring device image disappear according to the first background image and the second background image, and at the moment, the first monitoring device further detects that no trees are on the road on the left of the second monitoring device image according to the fourth background image, so that the change of environmental facilities (greening facilities) in the monitoring scene of the first monitoring device can be determined, and further notification information can be sent to the electronic device of the technician linked with the first monitoring device to notify the technician of resetting the first monitoring device background.

According to the embodiment, whether the first monitoring equipment fails and the type of the failure are analyzed and judged by combining the background image collected by the second monitoring equipment, so that the accuracy of failure detection of the monitoring equipment can be further improved.

Based on the same technical concept, the embodiment of the invention also provides a device 200 for detecting the faults of the monitoring equipment. Referring to fig. 6, the apparatus 200 includes:

an obtaining module 201, configured to obtain a first background image and a second background image; wherein, the first background image is a background image in a current monitoring scene of the apparatus 200, and the second background image is a background image in a historical monitoring scene of the apparatus 200 stored in advance;

a calculating module 202, configured to calculate a similarity between the first background image and the second background image, and determine whether a monitoring scene of the apparatus 200 is changed according to a similarity calculation result;

a determining module 203, configured to determine that the apparatus 200 is faulty when a monitoring scenario of the apparatus 200 changes.

In one possible design, the determining module 203 is further configured to: after determining that the apparatus 200 is out of order, determining a type of the out of order of the apparatus 200 based on the first background image; the apparatus 200 further comprises a repair module for automatically repairing the failure of the apparatus 200 when the failure type of the apparatus 200 is a failure type that does not require manual repair.

In one possible design, the apparatus 200 further includes: a sending module, configured to send a failure notification when the failure type of the apparatus 200 is a failure type that needs to be repaired manually.

In one possible design, the determining module 203, when determining the type of failure of the apparatus 200 based on the first background image, is specifically configured to: extracting a first characteristic point from the second background image, and defining the first characteristic point as a reference point; determining a second feature point matched with the reference point in the first background image; calculating a positional displacement amount of the second feature point with respect to the reference point; judging whether the shooting visual angle of the device 200 is abnormal or not according to the position offset; when the shooting visual angle of the device 200 is abnormal, determining the fault type of the device 200 as a fault type which does not need manual repair; the repair module is specifically configured to: and calculating the visual angle offset of the device 200 according to the position offset, and adjusting the lens parameters and/or the holder parameters of the device 200 according to the visual angle offset.

In one possible design, the determining module 203, when determining the type of failure of the apparatus 200 based on the first background image, is specifically configured to: determining monitoring parameters in the current monitoring scene of the device 200 according to the first background image; determining whether the current shooting parameters of the device 200 are matched with the monitoring parameters in the current monitoring scene of the device 200; when the current shooting parameters of the device 200 are not matched with the monitoring parameters in the current monitoring scene of the device 200, determining that the shooting parameters of the device 200 are abnormal, and determining that the fault type of the device 200 is a fault type which does not need manual repair; the repair module is specifically configured to: determining shooting parameters matched with the monitoring parameters, and adjusting the shooting parameters of the device 200 to the shooting parameters matched with the monitoring parameters; or restarting the application process of the device 200; alternatively, the system of the device 200 is restarted.

In one possible design, the obtaining module 201 is further configured to: acquiring a third background image after the device 200 is automatically repaired; wherein the third background image is a background image of the monitored scene captured after the device 200 performs automatic restoration; the calculation module 202 is further configured to: calculating the similarity of the third background image and the second background image, and determining whether the fault of the device 200 is successfully repaired according to the similarity of the third background image and the second background image; the apparatus 200 further comprises a sending module for sending a failure notification if the failure of the apparatus 200 is not successfully repaired.

In one possible design, the determining module 203, when determining the type of failure of the apparatus 200 based on the first background image, is specifically configured to: detecting whether a crack exists in the first background image; when a crack exists in the first background image, determining that the lens glass of the device 200 is damaged or dirty, and determining that the fault type of the device 200 is a fault type needing manual repair; the sending module is specifically configured to: sending notification information of lens glass breakage or contamination of the device 200 to a terminal device associated with the device 200; or

The determining module 203, when determining the fault type of the apparatus 200 based on the first background image, is specifically configured to: when fog features exist in the first background image and shooting parameters of the device 200 are adjusted to be matched with the fog days, and the fog features cannot be eliminated, determining that water enters a lens of the device 200, and determining that the fault type of the device 200 is a fault type needing manual repair; the sending module is specifically configured to: sending notification information of lens water intake of the device 200 to a terminal device linked with the device 200; or

The determining module 203, when determining the fault type of the apparatus 200 based on the first background image, is specifically configured to: determining the environmental facility condition in the current monitoring scene of the device 200 according to the first background image, and determining the environmental facility condition in the historical monitoring scene of the device 200 according to the second background image; when the environmental facility conditions in the current monitoring scene and the historical monitoring scene of the device 200 are different, determining the environmental facility change in the monitoring scene of the device 200, and determining the fault type of the device 200 as the fault type needing manual repair; the sending module is specifically configured to: and sending scene reset notification information to the terminal device linked with the apparatus 200 to remind a technician of performing scene reset operation on the apparatus 200.

In one possible design, the obtaining module 201 is further configured to: acquiring a fourth background image before the determining module 203 determines the fault type of the apparatus 200 based on the first background image; the fourth background image is a background image in a current monitoring scene of a second monitoring device, and the current monitoring scene of the second monitoring device is at least partially overlapped with the current monitoring scene of the apparatus 200; the determining module 203, when determining the type of fault of the apparatus 200 based on the first background image, is configured to: determining a fault type of the apparatus 200 from the first background image and the fourth background image.

All relevant contents of each step related to the above method embodiment may be referred to the functional description of the corresponding functional module, and are not described herein again.

It should be noted that the division of the unit in the embodiment of the present invention is schematic, and is only a logic function division, and there may be another division manner in actual implementation. The functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

Illustratively, the functions of the above-mentioned obtaining module 201, calculating module 202 and determining module 203 may be implemented by one or more processors. The processor may be implemented as a central processing unit, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, transistor logic, hardware components, or any combination thereof that may implement or execute the various illustrative logical blocks, modules, and circuits described in connection with the embodiments disclosed herein. A processor may also be a combination of computing functions, e.g., a combination comprising one or more microprocessors, a digital signal processor and a microprocessor, or the like.

Based on the same technical concept, the embodiment of the present invention further provides an apparatus 300 for detecting a failure of a monitoring device. Referring to fig. 7, the apparatus 300 comprises at least one processor 301, the at least one processor 301 being coupled to at least one memory 302; the at least one processor 301 is configured to execute the computer program or the instructions stored in the at least one memory 302, so as to enable the apparatus 300 to perform the method for detecting the failure of the monitoring device according to the embodiment of the present invention.

Based on the same technical concept, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program or an instruction is stored in the computer-readable storage medium, and when the computer program or the instruction is read and executed by a computer, the computer is enabled to execute the method for detecting a failure of a monitoring device according to the embodiment of the present invention.

Based on the same technical concept, an embodiment of the present invention further provides a chip system, where the chip system includes a processor and may further include a memory, and is used to implement the functions related to the method for detecting and monitoring the device fault in the embodiment of the present invention. The chip system may be formed by a chip, and may also include a chip and other discrete devices.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a Digital Versatile Disk (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.

It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to encompass such modifications and variations.

Claims

1. A method of detecting a failure of a monitoring device, comprising:

acquiring a first background image and a second background image; the first background image is a background image in a current monitoring scene of a first monitoring device, and the second background image is a background image in a historical monitoring scene of the first monitoring device, which is stored in advance;

calculating the similarity of the first background image and the second background image, and judging whether the monitoring scene of the first monitoring equipment is changed or not according to the similarity calculation result;

and when the monitoring scene of the first monitoring equipment is changed, determining that the first monitoring equipment has a fault.

2. The method of claim 1, wherein after determining that the first monitoring device is malfunctioning, the method further comprises:

determining a fault type of the first monitoring equipment based on the first background image;

and when the fault type of the first monitoring equipment is a fault type which does not need to be repaired manually, the first monitoring equipment carries out automatic repair.

3. The method of claim 2, wherein after determining the type of failure of the first monitoring device based on the first background image, the method further comprises:

and when the fault type of the first monitoring equipment is the fault type needing manual repair, sending a fault notification.

4. The method of claim 2, wherein determining the type of fault of the first monitoring device based on the first background image comprises:

extracting a first characteristic point from the second background image, and defining the first characteristic point as a reference point; determining a second feature point matched with the reference point in the first background image; calculating a positional displacement amount of the second feature point with respect to the reference point; judging whether the shooting visual angle of the first monitoring equipment is abnormal or not according to the position offset; when the shooting visual angle of the first monitoring equipment is abnormal, determining the fault type of the first monitoring equipment as a fault type which does not need manual repair;

automatically repairing the first monitoring device, comprising:

and calculating the visual angle offset of the first monitoring equipment according to the position offset, and adjusting the lens parameter and/or the holder parameter of the first monitoring equipment according to the visual angle offset.

5. The method of claim 2, wherein determining the type of fault of the first monitoring device based on the first background image comprises:

determining monitoring parameters in the current monitoring scene of the first monitoring device according to the first background image; determining whether the current shooting parameters of the first monitoring equipment are matched with the monitoring parameters in the current monitoring scene of the first monitoring equipment; when the current shooting parameters of the first monitoring equipment are not matched with the monitoring parameters in the current monitoring scene of the first monitoring equipment, determining that the shooting parameters of the first monitoring equipment are abnormal, and determining that the fault type of the first monitoring equipment is a fault type which does not need manual repair;

automatically repairing the first monitoring device, comprising:

determining shooting parameters matched with the monitoring parameters, and adjusting the shooting parameters of the first monitoring equipment to the shooting parameters matched with the monitoring parameters; or restarting the application process of the first monitoring equipment; or restarting the system of the first monitoring device.

6. The method of claim 5, wherein the photographing parameters include at least one of brightness, chrominance, saturation, contrast, sharpness, day and night mode conversion, exposure, focus, backlight, white balance, image enhancement, fill light control.

7. The method of claim 2, further comprising, after automatically repairing the first monitoring device:

acquiring a third background image; the third background image is a background image of a monitoring scene shot by the first monitoring device after automatic restoration;

calculating the similarity of the third background image and the second background image, and determining whether the fault of the first monitoring equipment is successfully repaired according to the similarity of the third background image and the second background image;

and if the fault of the first monitoring equipment is not repaired successfully, sending a fault notification.

8. The method of claim 3, wherein determining the type of fault of the first monitoring device based on the first background image comprises: detecting whether a crack exists in the first background image; when a crack exists in the first background image, determining that the lens glass of the first monitoring device is damaged or stained, and determining that the fault type of the first monitoring device is a fault type needing manual repair; sending a fault notification, comprising: sending notification information of damage or dirt of lens glass of the first monitoring device to the terminal device linked with the first monitoring device; or

Determining a fault type of the first monitoring device based on the first background image, including: when fog features exist in the first background image and shooting parameters of the first monitoring equipment are adjusted to shooting parameters matched with fog days, and the fog features cannot be eliminated, determining that water enters a lens of the first monitoring equipment, and determining that the fault type of the first monitoring equipment is a fault type needing manual repair; sending a fault notification, comprising: sending notification information of lens water inflow of the first monitoring device to a terminal device linked with the first monitoring device; or

Determining a fault type of the first monitoring device based on the first background image, including: determining the environmental facility condition in the current monitoring scene of the first monitoring device according to the first background image, and determining the environmental facility condition in the historical monitoring scene of the first monitoring device according to the second background image; when the environmental facility condition in the current monitoring scene of the first monitoring device is different from the environmental facility condition in the historical monitoring scene, determining the environmental facility change in the monitoring scene of the first monitoring device, and determining the fault type of the first monitoring device as the fault type needing manual repair; sending a fault notification, comprising: and sending scene resetting notification information to the terminal equipment linked with the first monitoring equipment so as to remind technicians of carrying out scene resetting operation on the first monitoring equipment.

9. The method of any of claims 2-8, further comprising, prior to determining the type of failure of the first monitoring device based on the first background image:

acquiring a fourth background image; the fourth background image is a background image in a current monitoring scene of a second monitoring device, and the current monitoring scene of the second monitoring device is at least partially overlapped with the current monitoring scene of the first monitoring device;

determining a fault type of the first monitoring device based on the first background image, including:

and determining the fault type of the first monitoring equipment according to the first background image and the fourth background image.

10. The method of any one of claims 2-8, wherein:

the first background image and the second background image shoot the same object; or

The first background image and the second background image capture a portion of the same object.

11. An apparatus for detecting a failure in a monitoring device, comprising:

the acquisition module is used for acquiring a first background image and a second background image; the first background image is a background image in a current monitoring scene of the device, and the second background image is a background image in a historical monitoring scene of the device, which is stored in advance;

the calculation module is used for calculating the similarity of the first background image and the second background image and judging whether the monitoring scene of the device is changed or not according to the similarity calculation result;

and the determining module is used for determining the fault of the device when the monitoring scene of the device is changed.

12. The apparatus of claim 11, wherein the determination module is further configured to: after determining the device failure, determining a failure type of the device based on the first background image;

the device also comprises a repairing module used for automatically repairing the fault of the device when the fault type of the device is a fault type which does not need to be repaired manually.

13. The apparatus of claim 12, wherein the apparatus further comprises:

and the sending module is used for sending a fault notification when the fault type of the device is the fault type needing manual repair.

14. The apparatus of claim 12, wherein the determining module, when determining the type of failure of the apparatus based on the first background image, is specifically configured to: extracting a first characteristic point from the second background image, and defining the first characteristic point as a reference point; determining a second feature point matched with the reference point in the first background image; calculating a positional displacement amount of the second feature point with respect to the reference point; judging whether the shooting visual angle of the device is abnormal or not according to the position offset; when the shooting visual angle of the device is abnormal, determining the fault type of the device as a fault type which does not need manual repair;

the repair module is specifically configured to: and calculating the visual angle offset of the device according to the position offset, and adjusting the lens parameters and/or the holder parameters of the device according to the visual angle offset.

15. The apparatus of claim 12, wherein the determining module, when determining the type of failure of the apparatus based on the first background image, is specifically configured to: determining monitoring parameters in the current monitoring scene of the device according to the first background image; determining whether the current shooting parameters of the device are matched with the monitoring parameters in the current monitoring scene of the device; when the current shooting parameters of the device are not matched with the monitoring parameters in the current monitoring scene of the device, determining that the shooting parameters of the device are abnormal, and determining that the fault type of the device is a fault type which does not need manual repair;

the repair module is specifically configured to: determining shooting parameters matched with the monitoring parameters, and adjusting the shooting parameters of the device to be the shooting parameters matched with the monitoring parameters; or restarting the application process of the device; alternatively, the system of the device is restarted.

16. The apparatus of claim 13, wherein the determining module, when determining the type of failure of the apparatus based on the first background image, is specifically configured to: detecting whether a crack exists in the first background image; when a crack exists in the first background image, determining that the lens glass of the device is damaged or dirty, and determining that the fault type of the device is the fault type needing manual repair; the sending module is specifically configured to: sending notification information of damage or dirt of lens glass of the device to terminal equipment linked with the device; or

17. The apparatus of any of claims 11-16, wherein the acquisition module is further to: acquiring a fourth background image before the determining module determines the fault type of the device based on the first background image; the fourth background image is a background image in a current monitoring scene of second monitoring equipment, and the current monitoring scene of the second monitoring equipment is at least partially overlapped with the current monitoring scene of the device;

the determining module, when determining the type of failure of the apparatus based on the first background image, is to: determining a fault type of the device according to the first background image and the fourth background image.

18. An apparatus for detecting failure of a monitoring device, comprising at least one processor coupled to at least one memory; the at least one processor configured to execute computer programs or instructions stored in the at least one memory to cause the apparatus to perform the method of any of claims 1-10.

19. A computer-readable storage medium, having stored thereon a computer program or instructions, which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 10.