CN110769246B - Method and device for detecting faults of monitoring equipment - Google Patents

Abstract

The present application provides a method and a device for detecting a fault of monitoring equipment. The method includes: acquiring background images in two images taken before and after monitoring, and comparing the similarity of the two background images. When the similarity reaches the threshold, it indicates that the monitoring scene has changed, so that it can be confirmed that the monitoring equipment has sent a fault, and the monitoring equipment can be automatically repaired.

Description

A method and device for detecting and monitoring equipment faults

technical field

The present application relates to the field of monitoring, and in particular to a method and device for detecting failures of monitoring equipment.

Background technique

At present, the maintenance of monitoring equipment mainly depends on the regular maintenance of manpower, that is, every once in a while, arrange technicians to check whether the monitoring equipment is faulty and deal with the fault. On the one hand, it requires high labor costs. On the other hand, the maintenance efficiency is low, and it is difficult to detect and solve the fault in time when the monitoring equipment fails.

Contents of the invention

Embodiments of the present invention provide a method and a device for detecting a fault of monitoring equipment, which are used to solve the technical problems of low detection efficiency and high cost of fault detection of monitoring equipment in the prior art.

In a first aspect, a method for detecting a monitoring device failure is provided, including: acquiring a first background image and a second background image; wherein, the first background image is a background image in the current monitoring scene of the first monitoring device, and the The second background image is the background image in the historical monitoring scene of the first monitoring device stored in advance; the similarity between the first background image and the second background image is calculated, and the first background image is judged according to the similarity calculation result. Whether the monitoring scene of the monitoring device is changed; when the monitoring scene of the first monitoring device is changed, it is determined that the first monitoring device is faulty.

In the embodiment of the present invention, it is judged whether the monitoring scene of the first monitoring device is If there is a change, when the monitoring scene of the first monitoring device is found to be changed, it is determined that the first monitoring device is faulty. This solution does not require technicians to go to the site for inspection and can detect the fault of the monitoring device in time, which can improve the timeliness of fault detection of the monitoring device .

In a possible design, 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 this way, it can be ensured that the current monitoring scene and the historical monitoring scene are in the same place, and the accuracy of fault detection of the monitoring equipment can be improved.

In a possible design, after determining that the first monitoring device is faulty, the 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 that does not require manual repair, the first monitoring device performs automatic repair. When the fault type of the first monitoring device is a fault type requiring manual repair, a fault notification is sent.

Through this embodiment, it is possible to determine the fault type of the first monitoring device. When the fault type of the first monitoring device is a fault type that does not require manual repair, the first monitoring device is automatically repaired to improve the fault handling efficiency; When the fault type of the first monitoring device is a fault type requiring manual repair, a fault notification is sent, so that technicians can rush to the site in time to troubleshoot the fault.

The following are examples of two possible types of faults that do not require manual repair.

The first example, extracting the first feature point from the second background image, and defining the first feature point as a reference point; determining the second feature in the first background image that matches the reference point point; calculate the position offset of the second feature point relative to the reference point; judge whether the shooting angle of view of the first monitoring device is abnormal according to the position offset; When the viewing angle is abnormal, it is determined that the fault type of the first monitoring device is a fault type that does not require manual repair. Correspondingly, the automatic restoration of the first monitoring device may be: calculating the viewing angle offset of the first monitoring device according to the position offset, and adjusting the first monitoring device according to the viewing angle offset. Lens parameters and/or gimbal parameters of the device.

In this embodiment, by comparing the first background image and the second background image, abnormalities of the lens parameters and/or pan/tilt parameters 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.

The second example is to determine the monitoring parameters in the current monitoring scene of the first monitoring device according to the first background image; determine whether the current shooting parameters of the first monitoring device are the same as those in the current monitoring scene of the first monitoring device The monitoring parameters match; when the current shooting parameters of the first monitoring device do not match the monitoring parameters in the current monitoring scene of the first monitoring device, determine that the shooting parameters of the first monitoring device are abnormal, and determine that the first monitoring device A failure type of the monitoring equipment is a failure type that does not require manual repair. Correspondingly, the automatic restoration of the first monitoring device may be: determining the shooting parameters that match the monitoring parameters, and adjusting the shooting parameters of the first monitoring device to match the monitoring parameters. shooting parameters; or, restarting the application process of the first monitoring device; or restarting the system of the first monitoring device. Optionally, in order to improve the flexibility of the solution, the shooting parameters can be brightness, hue, saturation, contrast, sharpness, day and night mode conversion, exposure, focus, backlight, white balance, image enhancement, fill light light control Wait, no limit here.

In this embodiment, the monitoring parameters in the current monitoring scene of the first monitoring device can be determined based on the first background image, and when it is determined that the current shooting parameters of the first monitoring device do not match the monitoring parameters in the current monitoring scene of the first monitoring device, the shooting The parameters are adjusted to the shooting parameters that match the current monitoring parameters, which can detect and deal with the abnormality of the shooting parameters of the first monitoring device in time, and can improve the fault detection and maintenance efficiency of the monitoring device.

In a possible design, after the first monitoring device is automatically repaired, a third background image may also be obtained; wherein, the third background image is taken after the first monitoring device is automatically repaired The background image of the monitoring scene; calculate the similarity between the third background image and the second background image, and determine the first monitoring device according to the similarity between the third background image and the second background image Whether the fault is successfully repaired; if the fault of the first monitoring device is not repaired successfully, a fault notification is sent.

This embodiment can detect whether the automatic repair of the first monitoring device is successful, and promptly remind technicians to go to the site for maintenance after the automatic repair of the first monitoring device fails, further improving the reliability and timeliness of fault maintenance of the monitoring device.

The following are examples of three possible fault types that require manual repair.

The first example is to detect whether there is a crack in the first background image; when there is a crack in the first background image, determine that the lens glass of the first monitoring device is broken or dirty, and determine that the first The fault type of the monitoring equipment is a fault type requiring manual repair. Correspondingly, sending the fault notification may be: sending notification information that the lens glass of the first monitoring device is broken or dirty to the terminal device associated with the first monitoring device.

This embodiment can determine whether the lens glass is damaged, scratched or dirty based on the first background image or the first background image, and initiate a fault notification in time when the lens glass is damaged, scratched or dirty. , so that technicians can know in time and rush to the scene to replace or repair the lens glass of the first monitoring equipment, which improves the efficiency of fault detection and maintenance of the monitoring equipment.

In the second example, when there is a fog feature in the first background image, and the shooting parameters of the first monitoring device are adjusted to match the shooting parameters of the fog, the fog feature cannot be eliminated, and the fog feature is determined. The lens of the first monitoring device is flooded, and it is determined that the fault type of the first monitoring device is a fault type requiring manual repair. Correspondingly, sending the failure notification may be: sending notification information that the lens of the first monitoring device is flooded to the terminal device associated with the first monitoring device.

In this embodiment, based on the first background image, it can be determined whether the lens glass is abnormally fogged, and when the lens is abnormally fogged, a fault notification is initiated, so that technicians can know in time and rush to the scene to solve the problem of the lens of the first monitoring device. The abnormal fog entering in the monitoring device improves the fault detection and maintenance efficiency of the monitoring equipment.

The third example is to determine the environmental facilities in the current monitoring scene of the first monitoring device according to the first background image, and determine the environmental facilities in the historical monitoring scene of the first monitoring device according to the second background image Status; when the environmental facility status in the current monitoring scene of the first monitoring device is different from the environmental facility status in the historical monitoring scene, determine the change of the environmental facility in the monitoring scene of the first monitoring device, and determine the first monitoring device A fault type of the monitoring equipment is a fault type requiring manual repair. Correspondingly, sending the fault notification may be: sending notification information of scene reset to the terminal device associated with the first monitoring device, so as to remind technicians to perform a scene reset operation on the first monitoring device.

This implementation mode takes into account the fact that there may be changes in environmental facilities in the actual scene, and is used for users to decide whether to reset the background scene, so as to ensure that the second background image is updated in time and accurately, and further improve the reliability of fault detection and maintenance of monitoring equipment and timeliness.

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

In this embodiment, the accuracy of fault detection of the monitoring device can be further improved by analyzing and judging the type of the fault of the first monitoring device in combination with the background image collected by the second monitoring device.

In a second aspect, there is provided a device for detecting a monitoring device failure, including: an acquisition module, configured to acquire a first background image and a second background image; wherein, the first background image is the background in the current monitoring scene of the device Image, the second background image is the background image in the pre-stored historical monitoring scene of the device; the calculation module is used to calculate the similarity between the first background image and the second background image, and calculate according to the similarity As a result, it is judged whether the monitoring scene of the device is changed; the determining module is configured to determine that the device is faulty when the monitoring scene of the device is changed.

In a possible design, 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 a possible design, the determining module is further configured to: determine the fault type of the device based on the first background image after determining the fault of the device; the device further includes a repair module configured to When the fault type of the device is a fault type that does not require manual repair, the fault of the device is automatically repaired.

In a possible design, the device further includes: a sending module, configured to send a fault notification when the fault type of the device is a fault type requiring manual repair.

In a possible design, when the determination module determines the fault type of the device based on the first background image, it is specifically configured to: extract the first feature point from the second background image, and define The first feature point is a reference point; determining a second feature point in the first background image that matches the reference point; calculating a position offset of the second feature point relative to the reference point; According to the position offset, it is judged whether the shooting angle of view of the device is abnormal; when the shooting angle of view of the device is abnormal, it is determined that the fault type of the device is a fault type that does not require manual repair; the repair module is specifically used to : Calculate the angle of view offset of the device according to the position offset, and adjust the lens parameters and/or pan/tilt parameters of the device according to the angle of view offset.

In a possible design, when the determination module determines the fault type of the device based on the first background image, it is specifically configured to: determine the fault type of the device in the current monitoring scene according to the first background image monitoring parameters; determine whether the current shooting parameters of the device match the monitoring parameters in the current monitoring scene of the device; when the current shooting parameters of the device do not match the monitoring parameters in the current monitoring scene of the device, determine the The shooting parameters of the device are abnormal, and it is determined that the fault type of the device is a fault type that does not require manual repair; the repair module is specifically used to: determine the shooting parameters that match the monitoring parameters, and set the shooting Adjusting the parameters to shooting parameters that match the monitoring parameters; or restarting the application process of the device; or restarting the system of the device.

In a possible design, the shooting parameters include at least one of brightness, hue, saturation, contrast, sharpness, day-night mode conversion, exposure, focus, backlight, white balance, image enhancement, and fill light control. A sort of.

In a possible design, the acquiring module is further configured to: acquire a third background image after the device is automatically repaired; wherein, the third background image is taken after the device is automatically repaired The background image of the monitoring scene; the calculation module is also used to: calculate the similarity between the third background image and the second background image, according to the similarity between the third background image and the second background image Determine whether the fault of the device is successfully repaired; the device further includes a sending module, configured to send a fault notification if the fault of the device is not repaired successfully.

In a possible design, when the determination module determines the fault type of the device based on the first background image, it is specifically configured to: detect whether there is a crack in the first background image; When there is a crack in the background image, it is determined that the lens glass of the device is damaged or dirty, and the fault type of the device is determined to be a fault type that requires manual repair; the sending module is specifically used to: link to the device The terminal device sends a notification message that the lens glass of the device is broken or dirty; or

When the determination module determines the fault type of the device based on the first background image, it is specifically configured to: there is a fog feature in the first background image, and adjust the shooting parameters of the device to be compatible with the fog When the shooting parameters matched with the sky cannot eliminate the fog feature, it is determined that the lens of the device is flooded, and the fault type of the device is determined to be a fault type that requires manual repair; the sending module is specifically used to: The terminal device associated with the device sends a notification message that the lens of the device has been flooded; or

When the determination module determines the fault type of the device based on the first background image, it is specifically used to: determine the environmental facility status in the current monitoring scene of the device according to the first background image, and The second background image determines the environmental facility status in the historical monitoring scene of the device; when the environmental facility status in the current monitoring scene of the device is different from the environmental facility status in the historical monitoring scene, determine the environmental facility status in the monitoring scene of the device The environmental facilities are changed, and it is determined that the fault type of the device is a fault type that requires manual repair; the sending module is specifically used to: send a scene reset notification message to the terminal device linked to the device to remind technicians The above device performs scene reset operation.

In a possible design, the obtaining module is further configured to: before the determining module determines the fault type of the device based on the first background image, obtain a fourth background image; wherein, the fourth The background image is the background image in the current monitoring scene of the second monitoring device, and the current monitoring scene of the second monitoring device and the current monitoring scene of the device at least partially overlap; When the fault type of the device is used, it is used to: determine the fault type of the device according to the first background image and the fourth background image.

In a third aspect, there is provided a device for detecting a failure of monitoring equipment, including at least one processor, and the at least one processor is coupled to at least one memory; the at least one processor is configured to execute the A computer program or instruction, so that the device executes the method described in the first aspect of the embodiment of the present invention or any possible design of the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, where a computer program or an instruction is stored in the computer-readable storage medium, and when the computer reads and executes the computer program or instruction, the computer executes the computer program as described in the embodiment of the present invention. The method described in the first aspect or any possible design of the first aspect.

A fifth aspect provides a chip system, the chip system includes a processor, and may also include a memory for implementing the method described in the first aspect of the embodiment of the present invention or any possible design of the first aspect the functions involved. The system-on-a-chip may consist of chips, or may include chips and other discrete devices.

Description of drawings

Fig. 1 is the example figure of several monitoring equipments in the embodiment of the present invention;

2A is a schematic structural diagram of a monitoring device in an embodiment of the present invention;

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

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

Fig. 3 is the flow chart of the method for detecting and monitoring equipment failure in the embodiment of the present invention;

FIG. 4A is a schematic diagram of a first background image in an embodiment of the present invention;

FIG. 4B is a schematic diagram of a second background image in an embodiment of the present invention;

FIG. 4C is a schematic diagram of a second background image in an embodiment of the present invention;

FIG. 5A is a schematic diagram of a second background image in an embodiment of the present invention;

FIG. 5B is a schematic diagram of a first background image in an embodiment of the present invention;

FIG. 5C is a schematic diagram of a fourth background image in an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of a device for detecting and monitoring equipment faults in an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of another device for detecting a monitoring device failure in an embodiment of the present invention.

Detailed ways

In the field of video surveillance, surveillance equipment (such as several cameras shown in Figure 1) is often used in outdoor scenes or large public indoor scenes, and can be used to realize traffic incident detection, pedestrian detection, license plate capture, traffic intersection violation capture, Station monitoring, etc. In these scenarios, the monitoring equipment is installed at a relatively high position. After long-term use, the monitoring angle of the monitoring equipment may be shifted, rotated, or even have no picture due to natural, man-made, or aging reasons. The maintenance of existing monitoring equipment generally relies on technicians to go to the site for inspection and maintenance on a regular basis, and technicians cannot perceive the abnormality of the monitoring equipment at the first time when the monitoring equipment fails, so the maintenance efficiency is very low, and it will also consume high labor costs. .

In view of this, an embodiment of the present invention provides a method for detecting a failure of a monitoring device. The method judges the monitoring device by comparing the background image in the current monitoring scene of the monitoring device with the background image in the historical monitoring scene of the monitoring device. Whether the monitoring scene of the monitoring device is changed, and when the monitoring scene of the monitoring device is found to be changed, it is determined that the monitoring device is faulty. This method can detect the fault of the monitoring device in time without the need for technicians to go to the site for inspection. Further, after determining the fault of the monitoring device, the fault type of the monitoring device can also be determined based on the background image, and then a decision is made and a fault handling strategy is executed according to the fault type to solve the fault in a timely manner.

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 capture: the same object, or a part of the same object. This object is for example a building, a pole, a plant, a decoration. It should be noted that the imaging effect of the same object (or part of the object) in the first background image and the second background image may be different, such as different definition, different amount of noise, different contrast, different sharpness, etc.

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.

Please refer to FIG. 2A , which is a schematic structural diagram of a monitoring device involved in an embodiment of the present invention. The monitoring device may include a camera part and a control part.

The camera part is the front end of the monitoring equipment and the "eyes" of the entire monitoring equipment. It is used to collect image signals corresponding to the monitored places and transmit the collected image signals to the monitor in the control center. The camera part is generally arranged at a certain position of the monitored place, and its field of view can cover all parts of the entire monitored place.

The camera part may be a camera, video camera, smart video camera, smart camcorder, smart mobile terminal (such as a mobile phone), a tablet computer, etc., which are not limited in this embodiment of the present invention.

In some possible embodiments, the camera part may only include one camera, and in other possible embodiments, the camera part may include multiple cameras, and different cameras may have different viewing angles, which are not limited in the embodiments of the present invention. . The camera can be an infrared camera, that is, the camera can capture infrared images, or it can be a visible light camera, that is, the camera can capture color images, which are not limited in this embodiment of the present invention. The camera includes an optical lens and an image sensor, and the image sensor can be a charge-coupled device (CCD), a complementary metal oxide semiconductor (CMOS), and a contact image sensor (CIS), etc. .

In some scenarios, in order to save the number of cameras used in the camera part, simplify the transmission system and the control and display system, an electric (remote control) variable focal length (variable magnification) lens can be added to the camera part to make the camera part The distance that can be observed is farther and clearer; the camera part can also be installed on the pan-tilt, and through the control of the console, the pan-tilt can drive the camera part to rotate horizontally and vertically, so that the camera part can cover a wide range of angles , The area is larger.

The control part is the "heart" and "brain" of the whole system, and it is the command center to realize the functions of the whole video surveillance system. In the embodiment of the present invention, the control part can complete image acquisition and similarity comparison, and can also adjust the direction and angle of the camera/pan/tilt. The following is an introduction to some more powerful ones. The control part is mainly composed of the main console (some systems also have sub-consoles). The main functions in the main console are: video signal amplification and distribution, image signal correction and compensation, image signal switching, image signal (or including sound signal) recording, camera and its auxiliary components (such as lens, pan/tilt, protective cover, etc.) control (remote control) and so on. Another important aspect of the main console is that it can remotely control the camera, lens, pan/tilt, protective cover, etc., so as to complete the comprehensive and detailed monitoring or tracking monitoring of the monitored place. A video recorder can also be set on the main console to record the images of the monitored places where the situation occurs, for future reference or as an important basis. "Multi-screen splitter" can also be set on the main console, such as four screens, nine screens, sixteen screens, etc., that is to say, four, nine, or sixteen screens can be displayed on one monitor at the same time. The pictures of each monitored place sent by the camera are recorded with a conventional video recorder or a long-time video recorder.

The control section includes at least one processor. The processor may include one or more of the following: general purpose processor, image signal processor (image signal processor, ISP), microprocessor, digital signal processor (digital signal processor, DSP), field programmable gate array (field- programmable gate array, FPGA), etc.

The control section may also include one or more memories. Memory can be read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (random access memory, RAM) or other types of dynamic memory devices that can store information and instructions The storage device can also be Electrically Erasable Programmable Read-Only Memory (EEPROM), CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, optical disk storage (including Compact Disc, Laser Disc, Optical Disc, Digital Versatile Disc, Blu-ray Disc, etc.), magnetic disk storage medium or other magnetic storage device, or can be used to carry or store desired program code in the form of instructions or data structures and can be stored by the device Any other medium, but not limited to. The memory can exist independently and be connected to the processor through the bus. Memory can also be integrated with the processor.

Wherein, the memory of the control part can be used to store the application program code that executes the solution of the present application, and the execution is controlled by the processor, that is, the processor is used to execute the application code stored in the memory to implement the implementation of the present application. The method for detecting the failure of the monitoring equipment in the example.

In some scenarios, the memory can be integrated with the processor, or there is no memory, such as Field-Programmable Gate Array (FPGA).

It should be noted that during specific implementation, the camera part and the control part can be integrated on the same physical device (for example: a tablet computer with a camera, a smart camera), or they can be different physical devices respectively. Embodiments of the present invention There is no limit here. When the camera part and the control part are different physical devices, the camera part and the control part can be connected and communicated in a wired or wireless manner.

In some other embodiments, the monitoring device may further include a display part, as shown in FIG. 2B , which is another schematic structural diagram of the monitoring device in an embodiment of the present invention. The display section can consist of several or more monitors (or ordinary TV sets with video inputs). Its function is to display the images collected by the camera part one by one. The display part may be integrated with the camera part and the control part on one physical device, or may be a separate physical device, which is not limited here in the embodiment of the present invention.

Of course, the method for detecting a failure of a monitoring device in the embodiment of the present invention may not be performed by the monitoring device, but may be performed by other devices connected in communication with the monitoring device.

For example, referring to FIG. 2C , the monitoring device may be externally connected to a processing device, and the processing device may include one or more processors, and optionally, one or more memories. The memory in the processing device can be used to store the application program code that executes the solution of the present application, and the execution is controlled by the processor in the processing device, that is, the processor in the processing device is used to execute the code stored in the memory in the processing device. The application program code implements the method for detecting and monitoring device failures in the embodiment of the present application.

Taking the monitoring device shown in FIG. 2B as an example (that is, the first monitoring device hereinafter may be the monitoring device shown in FIG. 2B ), the method for detecting a fault in the monitoring device provided by the embodiment of the present invention is introduced below.

1) Surveillance scene refers to the area captured by the surveillance equipment. For example, for a monitoring device installed in a station, its monitoring scene is the station area that the monitoring device can capture; for example, for a monitoring device installed at a traffic intersection, its monitoring scene is the intersection area that the monitoring device can capture.

2) The background image, or image background, background image, image background, etc., refers to the image corresponding to the background area in the area captured by the monitoring device (ie, the monitoring scene). Wherein, the background area may refer to the object or the area where the object or object is located at a distance greater than the preset distance from the monitoring device in the monitoring scene, or may refer to the object or object that frequently appears in the monitoring scene (for example, the longest time in a period of time). In other embodiments, the background area can also be a user-defined area, such as the object or the area where the object is located in the monitoring scene that the user does not want to be highlighted in the picture taken by the monitoring device, which can be selected through interaction with the user. Or system settings.

The background image may be all of the images captured by the monitoring equipment, or may be a part of the images captured by the monitoring equipment, depending on the specific conditions of the monitoring scene. For example, the monitoring scene of the monitoring device is a traffic intersection. If there are no vehicles or pedestrians at the intersection when the monitoring device performs the shooting operation, and only road features exist in the image captured by the monitoring device, the image captured by the monitoring device is the background image. If there is a vehicle passing through the traffic intersection when the monitoring device performs the shooting operation, the image part corresponding to the vehicle in the image captured by the monitoring device may not be used as the background image. Correspondingly, the background image is other image parts in the image except the vehicle. .

3), the term "at least one" involved in the following embodiments of the present invention refers to one, or more than one, that is, including one, two, three or more; "multiple" refers to two, or two The above includes two, three and more. In addition, it should be understood that in the description of this application, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or imply order. "And/or" describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural. The character "/" generally indicates that the contextual objects are an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one item (piece) of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c can be single or multiple .

Please refer to FIG. 3 , which is a flowchart of a method for detecting a monitoring device failure in an embodiment of the present invention. The method may be executed by an image/video monitoring device (such as a camera); it may also be executed by other devices. After detecting a fault, the other device sends a repair instruction to the monitoring device, so as to instruct the monitoring device to perform repair. For the convenience of understanding, the following steps are introduced by taking the execution of S101-S103 by the monitoring equipment as an example (if the steps S101-S103 are executed by other equipment, since the principle is the same, no separate description will be made). The method includes the following steps:

S101. The first monitoring device acquires a first background image and a second background image; wherein, the first background image is a background image in the current monitoring scene of the first monitoring device, and the second background image is a pre-stored The first monitoring device historically monitors background images in scenes.

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

In the embodiment of the present invention, the location of the current monitoring scene and the historical monitoring scene are the same. That is to say, the first monitoring device is required to be at the same location when collecting the first image and the second image, where the same location refers to the relative position of the first monitoring device when collecting the first image and the location when collecting the second image. The distance is less than a preset value, such as less than 0.1m. A possible design is: the same object or a part of the same object is photographed in the first background image and the second background image. For example, if the first monitoring device is a monitoring device installed at a traffic intersection, then the first background image and the second background image have the same roads, greenery, or traffic signs.

The background modeling algorithm can be a single Gaussian model (Single Gaussian Model) algorithm, a mixed Gaussian model (Mixture of Gaussian) algorithm, a sliding Gaussian average (Running Gaussian average) algorithm, a codebook (CodeBook) algorithm, a self-organizing background detection (SOBS- Self-organization background subtraction) algorithm, sample consistency background modeling algorithm (SACON), VIBE algorithm, background modeling algorithm based on color information, statistical averaging method, intrinsic background method, etc., are not limited here in the embodiments of the present invention.

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

In specific implementation, the first monitoring device can delete the second background image originally stored locally after each restart operation or background reset operation, and add The background of is stored locally as the second background image. Optionally, the first monitoring device may also perform the background reset operation periodically according to a preset time interval, for example, perform a background reset every 5 minutes, 30 minutes, or 60 minutes, etc., to ensure that the background is updated in time. The second background image may not be stored locally, for example, stored in a dedicated storage server/storage array, and sent to the first monitoring device when needed.

It should be noted that if the first monitoring device is a camera with a variable shooting angle (such as a dome camera, barrel camera, etc.), the second image and the first image are required to be collected by the first monitoring device at the same pan-tilt position image, that is, the position parameters of the pan-tilt when the first monitoring device is required to capture the first image are the same as the position parameters of the pan-tilt when the first monitoring device is capturing the second image, such as the pitch angle of the pan-tilt (tilt angle ) is the same as the pan angle.

S102. The first monitoring device calculates a similarity between the first background image and the second background image, and judges whether a monitoring scene of the first monitoring device changes according to a similarity calculation result.

There are many ways to calculate the image similarity, such as structural similarity and perceptual hash algorithm, Bhattacharyachian distance algorithm, or grayscale color histogram algorithm, etc., which are not limited here in the embodiment of the present invention.

As an optional implementation, before the first monitoring device calculates the similarity between the first background image and the second background image, it may first perform histogram statistics and normalization on the first background image and the second background image. and then calculate the similarity based on the preprocessed first background image and the second background image.

After calculating the similarity between the first background image and the second background image, it is judged whether the similarity is smaller than the preset first similarity threshold, if yes, then it is determined that the monitoring scene of the first monitoring device has changed, otherwise, it is determined that the second The monitoring scene of a monitoring device has not changed.

S103. When the monitoring scene of the first monitoring device changes, determine that the first monitoring device is faulty.

In the technical solution of the embodiment of the present invention, the first monitoring device judges whether the monitoring scene occurs by comparing the background image (ie, the first background image) in the current monitoring scene with the background image (ie, the second background image) in the historical monitoring scene Change, when the monitoring scene of the monitoring equipment is found to be changed, it is determined that the monitoring equipment is faulty. This solution can detect the monitoring equipment failure in time without the need for technicians to go to the site for inspection, and can improve the timeliness of monitoring equipment failure detection.

As an optional manner, in the embodiment of the present invention, the method steps of the above steps S101-S103 may be performed periodically at a set time interval, for example, the above-mentioned steps S101-S103 are performed every 10s, 20s or 1min. This method can further improve the timeliness of monitoring equipment fault detection. In addition, it is also possible to trigger the first monitoring device to execute the above steps S101-S103 by triggering an event. For example, a technician sends a fault detection command remotely. After receiving the fault detection command, the first monitoring device responds to the fault detection command. The method of steps S101-S103.

As an optional implementation, after step S103 is performed, that is, after the first monitoring device is determined to be faulty, fault handling may also be performed. The fault processing methods include but are not limited to device self-test, sending fault notifications, and the like.

During specific implementation, the first monitoring device may execute different fault handling strategies according to different fault types. For example, if the fault type of the first monitoring device is a fault type that does not require manual repair, then the first monitoring device is automatically repaired to improve the efficiency of fault handling; if the fault type of the first monitoring device is a fault type that requires manual repair If the fault type is faulty, a fault notification is sent to enable technicians to arrive at the scene in time to troubleshoot the fault.

As an optional implementation manner, the first monitoring device may determine the background image of the first monitoring device based on the collected background image, such as the first background image, or a background image of a preset number of frames adjacent to the first background image. Fault type.

Several specific fault scenarios are exemplified below to describe in detail how the first monitoring device performs fault detection and fault handling.

Scenario 1. Fault detection and processing caused by abnormal lens parameters of monitoring equipment and abnormal pan/tilt.

After the first monitoring device confirms its own failure based on the above-mentioned scene change detection, it can extract at least one feature point from the second background image. In order to distinguish it from the feature point in the first background image later, the The extracted feature point is defined as the first feature point; the at least one first feature point is used as a reference point; the feature point matching the reference point is extracted from the first background image, here the extracted from the first background image The feature point is defined as the second feature point, where the number of the first feature point is equal to the number of the second feature point; then, the position offset of the second feature point relative to the reference point is calculated, and the first feature point is judged according to the position offset. Check whether the shooting angle of the monitoring device is abnormal.

If it is determined according to the position offset that the viewing angle direction of the first monitoring device has shifted (the viewing angle direction when taking the first image is different from the viewing angle direction when shooting the second image), but the viewing angle does not change (when the first image is taken, is the same as the viewing angle of the second image, or the difference between the two is smaller than the preset value), then it is determined that the viewing angle direction of the monitoring device is abnormal, and it is determined that the current failure of the first monitoring device does not require manual repair Fault type, the first monitoring device can automatically adjust the pan/tilt parameters of the monitoring device (such as the pitch angle and rotation angle of the pan/tilt), so as to restore the viewing angle direction of the first monitoring device to the viewing angle direction before the change.

If it is determined according to the position offset that the viewing angle of the first monitoring device has changed (the viewing angle when shooting the first image is different from the viewing angle when shooting the second image, or the difference between the two is greater than a preset value), but If there is no change in the viewing angle direction (the viewing angle direction when shooting the first image is the same as the viewing angle direction when shooting the second image, or the difference between the two is less than the set value), then it is determined that the lens parameters of the monitoring device are abnormal, and the first monitoring device is determined to be The currently occurring fault is a type of fault that does not require manual repair. The first monitoring device can automatically adjust the lens parameters (such as the focal length) of the monitoring device to restore the viewing angle of the first monitoring device to the viewing angle before the change.

If it is determined according to the position offset that the size and direction of the viewing angle of the first monitoring device have changed, then it is determined that the size and direction of the viewing angle of the monitoring device are abnormal, and it is determined that the current fault of the first monitoring device is a fault type that does not require manual repair, The first monitoring device automatically adjusts the pan/tilt parameters and lens parameters of the monitoring device, so as to restore the size and direction of the viewing angle of the first monitoring device to the size and direction of the viewing angle before the change.

For example, referring to FIG. 4A and FIG. 4B, FIG. 4A is a schematic diagram of the first background image, wherein there are two second feature points in the first background image, A and B, whose coordinates are (1, 10), ( 5, 5), Fig. 4B is a schematic diagram of the second background image, wherein the first feature points in the second background image that match the first feature points in the first background image are respectively A' and B', and their coordinates are respectively It is (2, 10), (6, 5). By comparing the coordinates of A, B and A', B', it can be determined that the viewing angle direction of the first monitoring device is shifted along the illustrated x direction. Therefore, the first monitoring device can adjust the viewing angle toward the -x direction, so as to restore the viewing angle direction of the first monitoring device to the direction before the shift.

For example, referring to FIG. 4A and FIG. 4C, FIG. 4A is a schematic diagram of the first background image, wherein there are two second feature points in the first background image, A and B, whose coordinates are (1, 10), ( 5, 5), Fig. 4C is a schematic diagram of the second background image, wherein the first feature points in the second background image that match the second feature points in the first background image are respectively A' and B', and their coordinates are respectively It is (0.5, 5), (2.5, 2.5). It can be determined by comparing A, B with A', B' that the viewing angle of the first monitoring device is reduced. Therefore, the first monitoring device can adjust the focal length of the lens, so as to restore the viewing angle of the first monitoring device to that before zooming out.

It should be noted that if the first monitoring device is a camera with a variable shooting angle (such as a dome camera, barrel camera, etc.), the second image and the first image are required to be collected by the first monitoring device at the same pan-tilt position Image. In addition, the position of the pan-tilt when the first monitoring device adjusts the lens parameters needs to be the same as the position of the pan-tilt when the first monitoring device captures the first image.

In this embodiment, by comparing the first background image and the second background image, abnormalities of the lens parameters and/or pan/tilt parameters of the first monitoring device can be detected and processed in time, and the failure maintenance efficiency of the monitoring device can be improved.

Scenario 2. Fault detection and processing caused by abnormal shooting parameters of monitoring equipment.

After the first monitoring device confirms its own failure based on the above scene change detection, it can determine the monitoring parameters in the current monitoring scene of the first monitoring device according to the first background image, and then determine whether the current shooting parameters of the first monitoring device are consistent with the current monitoring parameters of the first monitoring device. The monitoring parameters in the scene match, and when it is determined that the current shooting parameters of the first monitoring device do not match the monitoring parameters in the current monitoring scene of the first monitoring device, it is determined that the shooting parameters of the first monitoring device are abnormal, and the first monitoring device's The fault type is a fault type that does not require manual repair, and then the shooting parameters of the first monitoring device are automatically adjusted, and the shooting parameters of the first monitoring device are adjusted to match the shooting parameters of the monitoring parameters.

Wherein, the monitoring parameters in the current monitoring scene may include brightness, color temperature, definition, weather conditions (such as sunny, cloudy, rainy, snowy, foggy), shooting scenes (such as buildings, plants and flowers, sky, etc.). Shooting parameters can include brightness, hue, 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 image stabilization, noise reduction , fog penetration, etc.), fill light control, international standards organization (ISO) sensitivity and other parameters, of course, in practical applications, shooting parameters can also include other parameters, such as shutter, aperture, focal length, monitoring The file format and resolution supported by the device are not specifically limited in this embodiment of the present invention.

The first monitoring device can also pre-store the mapping relationship between the monitoring parameters and the shooting parameters, so that when adjusting the shooting parameters, the shooting parameters that match the current monitoring parameters can be determined according to the mapping relationship table.

As an optional implementation, in the embodiment of the present invention, in order to improve the accuracy of the monitoring parameters, the first monitoring device can also acquire the images of a preset number of frames (for example, 5 frames before and after) adjacent to the first background image. The background image, and then based on the first background image and the background images of the adjacent preset number of frames, the monitoring parameters in the current scene are jointly determined.

In this 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 a preset number of frames adjacent to the first background image. After determining the current shooting parameters of the first monitoring device and the first When the monitoring parameters in the current monitoring scene of the monitoring device do not match, the first monitoring device automatically adjusts the shooting parameters to the shooting parameters that match the current monitoring parameters, which can detect and deal with abnormal shooting parameters of the first monitoring device in time, and can improve monitoring Equipment failure maintenance efficiency.

Two specific types of faults that do not require manual repair are cited above. In practical applications, the types of faults that do not require manual repair may also include other specific implementation methods, which are not listed here in the embodiments of the present invention. The strategy for the automatic repair of the first monitoring device is not limited to the above-mentioned adjustments of shooting parameters, lens parameters, and pan/tilt parameters. equipment system, etc.

Scenario 3. Fault detection and handling caused by abnormality of the lens glass of the monitoring equipment.

After the first monitoring device confirms its own failure based on the above-mentioned scene change detection, it can detect whether there is a crack in the first background image (the specific implementation method can be to perform crack detection on the first background image based on an edge detection algorithm, a deep learning algorithm, etc.). When it is determined that there is a crack in the first background image, it is determined that the lens glass of the first monitoring device is broken, scratched or dirty, and the fault type of the first monitoring device is determined to be a fault type requiring manual repair, and then a fault notification is initiated, such as Send a notification message that the lens glass of the first monitoring device is broken, scratched or dirty to the terminal device linked to the first monitoring device, so that technicians can know in time and rush to the scene to replace or repair the lens glass of the first monitoring device .

Similarly, in order to improve the accuracy of crack detection, the first monitoring device can also acquire background images of a preset number of frames (such as 5 frames before and after) adjacent to the first background image, and then based on the first background image, and adjacent The background images of the preset number of frames jointly determine whether the lens glass is damaged, scratched or dirty.

In this embodiment, based on the first background image or the background images of a preset number of frames adjacent to the first background image, it can be determined whether the lens glass is damaged, scratched or dirty, and if the lens glass is damaged, scratched or In case of abnormalities such as dirt, a fault notification is initiated in time, so that technicians can be informed in time and rush to the scene to replace or repair the lens glass of the first monitoring device, which improves the fault maintenance efficiency of the monitoring device.

Scenario 4. Fault detection and treatment caused by abnormal water ingress or fogging of the monitoring equipment lens.

After the first monitoring device confirms its own failure based on the above-mentioned scene change detection, it can detect whether there is a fog feature in the first background image; If there is an abnormality of fogging on the lens of the monitoring equipment, or if the fog feature cannot be eliminated even after adjusting the shooting parameters of the first monitoring equipment to match the shooting parameters of the foggy weather, then it is determined that the lens of the monitoring equipment has an abnormality of fogging; Determine that the fault type of the first monitoring device is a fault type that requires manual repair, and initiate a fault notification, such as sending a notification message that the lens of the first monitoring device is fogged to a terminal device linked to the first monitoring device. Wherein, the notification method may be an email, a short message, a notification message of an instant messaging application, etc., which is not limited in this embodiment of the present invention.

In addition, the first monitoring device can also detect whether there is a water drop feature in the first background image; if it exists, it can obtain the weather information in the current monitoring scene, and when it is determined that the weather condition is not rainy, it is determined that there is water in the lens of the monitoring device abnormality, or when the shooting parameters of the first monitoring device are adjusted to match the shooting parameters of the rainy day, but the feature of water drops cannot be eliminated, it is determined that there is an abnormality of water ingress in the lens of the monitoring device; it is determined that the first monitoring device The fault type is a fault type that requires manual repair, and a fault notification is initiated, such as sending a notification message that the lens of the first monitoring device is flooded to a terminal device linked with the first monitoring device.

Similarly, in order to improve the accuracy of water ingress or fogging detection, the first monitoring device can also acquire background images of a preset number of frames (such as 5 frames before and after) adjacent to the first background image, and then based on the first background image , and the background images of the adjacent preset number of frames jointly determine whether there is an abnormality of water ingress or fogging in the lens glass.

In this embodiment, based on the first background image or the background images of a preset number of frames adjacent to the first background image, it can be determined whether the lens glass has water ingress or fogging abnormality, and when the lens has water ingress or fogging abnormality, A fault notification is initiated, so that technicians can be notified in time and rush to the scene to solve the abnormal water ingress or fogging in the lens of the first monitoring device, which improves the fault maintenance efficiency of the monitoring device.

Scenario 5. Fault detection and handling caused by changes in environmental facilities.

After the first monitoring device confirms its own failure based on the above scene change detection, it can recognize the environmental facility status in the current monitoring scene of the first monitoring device according to the first background image, and then recognize the historical monitoring scene of the first monitoring device according to the second background image The environmental facility condition in; Then judge whether the environmental facility condition in the current monitoring scene of the first monitoring device and the environmental facility condition in the historical monitoring scene are the same, determine the environmental facility condition and the historical monitoring scene in the first monitoring device current monitoring scene When the conditions of the environmental facilities are different, determine the change of the environmental facilities in the monitoring scene of the first monitoring device, determine that the fault type of the first monitoring device is a fault type that needs manual repair, and initiate a fault notification, such as linkage to the first monitoring device The terminal device sends scene reset notification information to remind technicians to perform a scene reset operation on the first monitoring device. Further, after receiving the background reset operation performed by the user, the first monitoring device may locally store the background in the first frame of image collected after the background reset as a new second background image.

Considering that in the actual scene, there will be changes in environmental facilities, such as road resurfacing, greening maintenance and other actual scenes, this method is used for users to decide whether to reset the background scene, so as to ensure that the second background image is updated in a timely and accurate manner, and further Improve the reliability and timeliness of fault maintenance of monitoring equipment.

Three specific types of faults that require manual repair are listed above. In practical applications, the types of faults that require manual repair may also include other specific fault types, which are not listed here in this embodiment of the present invention.

As an optional implementation, after the first monitoring device performs automatic repair, it can also judge whether the fault of the first monitoring device is successfully repaired, and if not, it can initiate a fault notification to remind technicians to go to the site for maintenance .

Specifically, the first monitoring device may obtain a third background image, where the third background image is the background image of the monitoring scene captured by the first monitoring device after automatic repair, and then calculate the similarity between the third background image and the second background image According to the similarity between the third background image and the second background image, it is determined whether the fault of the first monitoring device is repaired successfully. If the similarity is lower than the preset second similarity threshold, it is determined that the fault repair is not successful, and you can initiate Fault notification, such as sending a notification message that the fault cannot be automatically repaired to the terminal device linked to the first monitoring device, so as to remind technicians to go to the site for maintenance. Wherein, the second similarity threshold is less than or equal to the above-mentioned first similarity threshold.

This embodiment can detect whether the automatic repair of the first monitoring device is successful, and promptly remind technicians to go to the site for maintenance after the automatic repair of the first monitoring device fails, further improving the reliability and timeliness of fault maintenance of the monitoring device.

As an optional implementation, in order to further improve the accuracy of fault detection, the embodiment of the present invention can also analyze the background image collected by the second monitoring device to determine whether the first monitoring device is faulty and the type of fault, wherein the second monitoring device The current monitoring scene of the device and the current monitoring scene of the first monitoring device are at least partially overlapped.

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 the background image in the current monitoring scene of the second monitoring device. Correspondingly, when determining the fault type of the first monitoring device, the first monitoring device determines the fault type of the first monitoring device according to the first background image and the fourth background image.

Wherein, the second monitoring device may be the same type of electronic device as the first monitoring device, such as a smart camera, or may be a different type of electronic device from the first monitoring device, for example, the first monitoring device is a smart camera, and the second monitoring device is a smart camera. The second monitoring device is an ordinary camera, which is not limited in this embodiment of the present invention.

Exemplarily, the above scenario 5 is taken as an example. Referring to Figures 5A to 5C, Figure 5A is the second background image in the historical monitoring scene of the first monitoring device, Figure 5B is the first background image in the current monitoring scene of the first monitoring device, and Figure 5C is the current monitoring image of the second monitoring device The fourth background image in the scene. Wherein, the viewing direction of the first monitoring device is the y direction shown in the figure, and the viewing direction of the second monitoring device is the x direction shown in the drawing. The first monitoring device detects that the trees on the road above the screen of the first monitoring device disappear according to the first background image and the second background image, and further detects that there are no trees on the road on the left side of the screen of the second monitoring device according to the fourth background image, Then it can be determined that the environmental facility (greening facility) in the monitoring scene of the first monitoring device has changed, and then a notification message can be sent to the electronic device of the technician linked to the first monitoring device to notify the technician to reset the first monitoring device. Device background.

In this embodiment, by analyzing the background image collected by the second monitoring device to determine whether the first monitoring device is faulty and the type of the fault, the accuracy of fault detection of the monitoring device can be further improved.

Based on the same technical concept, the implementation of the present invention also provides a device 200 for detecting and monitoring equipment failure. Referring to Figure 6, the device 200 includes:

The acquiring module 201 is configured to acquire a first background image and a second background image; wherein, the first background image is the background image in the current monitoring scene of the device 200, and the second background image is the pre-stored The background image in the historical monitoring scene of the device 200;

A calculation module 202, configured to calculate the similarity between the first background image and the second background image, and determine whether the monitoring scene of the device 200 has changed according to the similarity calculation result;

The determining module 203 is configured to determine that the device 200 is faulty when the monitoring scene of the device 200 changes.

In a possible design, 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 a possible design, the determination module 203 is further configured to: after determining the fault of the device 200, determine the fault type of the device 200 based on the first background image; the device 200 also includes a repairing A module configured to automatically repair the fault of the device 200 when the fault type of the device 200 is a fault type that does not require manual repair.

In a possible design, the device 200 further includes: a sending module, configured to send a fault notification when the fault type of the device 200 is a fault type requiring manual repair.

In a possible design, when the determining module 203 determines the fault type of the device 200 based on the first background image, it is specifically configured to: extract the first feature point from the second background image, And define the first feature point as a reference point; determine the second feature point in the first background image that matches the reference point; calculate the position offset of the second feature point relative to the reference point amount; judge whether the shooting angle of view of the device 200 is abnormal according to the position offset; when the shooting angle of the device 200 is abnormal, determine that the fault type of the device 200 is a fault type that does not require manual repair; the The repairing module is specifically configured to: calculate the angle of view offset of the apparatus 200 according to the position offset, and adjust the lens parameters and/or pan/tilt parameters of the apparatus 200 according to the angle of view offset.

In a possible design, when the determination module 203 determines the fault type of the device 200 based on the first background image, it is specifically configured to: determine the current monitoring status of the device 200 according to the first background image Monitoring parameters in the scene; determining whether the current shooting parameters of the device 200 match the monitoring parameters in the current monitoring scene of the device 200; the current shooting parameters of the device 200 and the monitoring parameters in the current monitoring scene of the device 200 When it does not match, it is determined that the shooting parameters of the device 200 are abnormal, and the fault type of the device 200 is determined to be a fault type that does not require manual repair; the repair module is specifically used to: determine the shooting parameters that match the monitoring parameters parameters, and adjust the shooting parameters of the device 200 to match the monitoring parameters; or restart the application process of the device 200; or restart the system of the device 200.

In a possible design, the shooting parameters include at least one of brightness, hue, saturation, contrast, sharpness, day-night mode conversion, exposure, focus, backlight, white balance, image enhancement, and fill light control. A sort of.

In a possible design, the acquiring module 201 is further configured to: acquire a third background image after the device 200 is automatically repaired; wherein, the third background image is for the device 200 to be automatically repaired The background image of the monitoring scene taken afterwards; the calculation module 202 is also used to: calculate the similarity between the third background image and the second background image, according to the third background image and the second background The similarity of the images determines whether the fault of the device 200 is repaired successfully; the device 200 also includes a sending module, configured to send a fault notification if the fault of the device 200 is not repaired successfully.

In a possible design, when the determining module 203 determines the fault type of the device 200 based on the first background image, it is specifically configured to: detect whether there is a crack in the first background image; When there is a crack in the first background image, it is determined that the lens glass of the device 200 is damaged or dirty, and the fault type of the device 200 is determined to be a fault type requiring manual repair; the sending module is specifically used to: The terminal device linked with the device 200 sends a notification message that the lens glass of the device 200 is broken or dirty; or

When the determination module 203 determines the type of failure of the device 200 based on the first background image, it is specifically configured to: there is a fog feature in the first background image and adjust the shooting parameters of the device 200 When the shooting parameters that match the foggy weather fail to eliminate the fog feature, it is determined that the lens of the device 200 is flooded, and the fault type of the device 200 is determined to be a fault type that requires manual repair; the sending module Specifically, it is used to: send notification information that the lens of the device 200 is flooded to the terminal device linked with the device 200; or

When the determination module 203 determines the fault type of the device 200 based on the first background image, it is specifically configured to: determine the environmental facility status in the current monitoring scene of the device 200 according to the first background image, and Determine the environmental facility status in the historical monitoring scene of the device 200 according to the second background image; when the environmental facility status in the current monitoring scene of the device 200 is different from the environmental facility status in the historical monitoring scene, determine the 200 monitors changes in environmental facilities in the scene, and determines that the fault type of the device 200 is a fault type requiring manual repair; the sending module is specifically used to: send a scene reset notification to the terminal device linked by the device 200 information, so as to remind technicians to reset the scene on the device 200.

In a possible design, the acquiring module 201 is further configured to acquire a fourth background image before the determining module 203 determines the fault type of the device 200 based on the first background image; wherein, the The fourth background image is a background image in the current monitoring scene of the second monitoring device, and the current monitoring scene of the second monitoring device and the current monitoring scene of the device 200 at least partially overlap; the determining module 203 is based on the first The background image, when determining the fault type of the device 200 , is used to: determine the fault type of the device 200 according to the first background image and the fourth background image.

All relevant content of the steps involved in the above method embodiments can be referred to the function descriptions of the corresponding functional modules, and will not be repeated here.

It should be noted that the division of the units in the embodiment of the present invention is schematic, and is only a logical function division, and there may be another division manner in actual implementation. Each functional unit in the embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

Exemplarily, the functions of the acquisition module 201, the calculation module 202 and the determination module 203 may be implemented by one or more processors. The processor can be realized by 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 devices, transistor logic devices, hardware components, or any combination thereof. Various exemplary logical blocks, modules and circuits described in conjunction with the disclosed content of the embodiments of the present application may be implemented or executed. The processor can also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and the like.

Based on the same technical concept, an embodiment of the present invention also provides an apparatus 300 for detecting a monitoring device failure. Referring to FIG. 7 , the device 300 includes at least one processor 301 coupled to at least one memory 302; the at least one processor 301 is configured to execute the computer stored in the at least one memory 302 programs or instructions, so that the apparatus 300 executes the above-mentioned method for detecting and monitoring equipment faults in the embodiment of the present invention.

Based on the same technical concept, an embodiment of the present invention also provides a computer-readable storage medium, in which a computer program or instruction is stored, and when the computer reads and executes the computer program or instruction, the computer Execute the above-mentioned method for detecting and monitoring equipment faults in the embodiment of the present invention.

Based on the same technical idea, the embodiment of the present invention also provides a chip system, which includes a processor and may also include a memory, for implementing the functions involved in the method for detecting and monitoring equipment faults in the embodiment of the present invention. The system-on-a-chip may consist of chips, or may include chips and other discrete devices.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. 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, etc.) having computer-usable program code embodied therein.

Embodiments of the present application are described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it 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 the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, from a website, computer, server, or data center via Wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) transmission to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (digital versatile disc, DVD)), or a semiconductor medium (for example, a solid state disk (solid state disk, SSD) ))wait.

Apparently, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the present application. In this way, if the modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and equivalent technologies, the present application also intends to include these modifications and variations.

Claims (13)

1. A method for detecting and monitoring equipment failure, characterized in that, comprising: Acquiring a first background image and a second background image; wherein, the first background image is the background image in the current monitoring scene of the first monitoring device, and the second background image is the pre-stored historical monitoring of the first monitoring device The background image in the scene; calculating the similarity between the first background image and the second background image, and judging whether the monitoring scene of the first monitoring device has changed according to the similarity calculation result; When the monitoring scene of the first monitoring device changes, determine that the first monitoring device is faulty; After determining that the first monitoring device is faulty, the method further includes: When there is a crack in the first background image, it is determined that the lens glass of the first monitoring device is damaged or dirty, and the fault type of the first monitoring device is determined to be a fault type requiring manual repair; A terminal device linked to a monitoring device sends a notification message that the lens glass of the first monitoring device is broken or dirty; or When there is a fog feature in the first background image, it is determined that the lens of the first monitoring device is flooded, and the fault type of the first monitoring device is determined to be a fault type requiring manual repair; report to the first monitoring device The terminal device associated with the device sends a notification message that the lens of the first monitoring device is flooded; or Determining the environmental facility status in the current monitoring scene of the first monitoring device according to the first background image, and determining the environmental facility status in the historical monitoring scene of the first monitoring device according to the second background image; When the environmental facility status in the current monitoring scene of the first monitoring device is different from the environmental facility status in the historical monitoring scene, determine the change of the environmental facility in the monitoring scene of the first monitoring device, and determine the failure of the first monitoring device The type is a fault type requiring manual repair; sending a scene reset notification message to the terminal device linked to the first monitoring device to remind technicians to perform a scene reset operation on the first monitoring device; After determining that the first monitoring device is faulty, the method further includes: Determine the monitoring parameters in the current monitoring scene of the first monitoring device according to the first background image; determine whether the current shooting parameters of the first monitoring device match the monitoring parameters in the current monitoring scene of the first monitoring device; When the current shooting parameters of the first monitoring device do not match the monitoring parameters in the current monitoring scene of the first monitoring device, determine that the shooting parameters of the first monitoring device are abnormal, and determine that the first monitoring device is faulty The type is a failure type that does not require manual repair; determining a shooting parameter that matches the monitoring parameter, and adjusting the shooting parameter of the first monitoring device to the shooting parameter that matches the monitoring parameter; or restarting the application process of the first monitoring device; or , restarting the system of the first monitoring device; Wherein, before determining the fault type of the first monitoring device based on the first background image, it further includes: Acquiring a fourth background image; wherein, the fourth background image is a background image in the current monitoring scene of the second monitoring device, and the current monitoring scene of the second monitoring device and the current monitoring scene of the first monitoring device at least partially overlap; Based on the first background image, determining the fault type of the first monitoring device includes: Determining the fault type of the first monitoring device according to the first background image and the fourth background image. 2. The method according to claim 1, wherein after determining that the first monitoring device fails, the method further comprises: determining a fault type of the first monitoring device based on the first background image; When the fault type of the first monitoring device is a fault type that does not require manual repair, the first monitoring device performs automatic repair. 3. The method according to claim 2, wherein, after determining the fault type of the first monitoring device based on the first background image, the method further comprises: When the fault type of the first monitoring device is a fault type requiring manual repair, a fault notification is sent. 4. The method according to claim 2, wherein, based on the first background image, determining the fault type of the first monitoring device comprises: 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 matching the reference point in the first background image; calculating the The position offset of the second feature point relative to the reference point; judging according to the position offset whether the shooting angle of view of the first monitoring device is abnormal; when the shooting angle of the first monitoring device is abnormal, determine The fault type of the first monitoring device is a fault type that does not require manual repair; Carrying out automatic repair to the first monitoring device, including: Calculate an angle of view offset of the first monitoring device according to the position offset, and adjust lens parameters and/or pan/tilt parameters of the first monitoring device according to the angle of view offset. 5. The method according to claim 1, wherein the shooting parameters include brightness, chroma, saturation, contrast, sharpness, day and night mode conversion, exposure, focus, backlight, white balance, image enhancement, complement At least one of light control. 6. The method according to claim 2, further comprising: after performing automatic repair on the first monitoring device: Acquiring a third background image; wherein, the third background image is the background image of the monitoring scene taken after the first monitoring device performs automatic repair; calculating the similarity between the third background image and the second background image, and determining whether the failure of the first monitoring device is successfully repaired according to the similarity between the third background image and the second background image; If the failure of the first monitoring device is not repaired successfully, a failure notification is sent. 7. The method according to any one of claims 1-6, characterized in that: 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. 8. A device for detecting and monitoring equipment faults, characterized in that it comprises: An acquisition module, configured to acquire a first background image and a second background image; wherein, the first background image is the background image in the current monitoring scene of the first monitoring device, and the second background image is the pre-stored first background image A background image in the historical monitoring scene of the monitoring equipment; A calculation module, configured to calculate the similarity between the first background image and the second background image, and determine whether the monitoring scene of the first monitoring device has changed according to the similarity calculation result; A determining module, configured to determine that the first monitoring device is faulty when the monitoring scene of the first monitoring device changes; Wherein, the determining module is further configured to: when there is a crack in the first background image, determine that the lens glass of the first monitoring device is broken or dirty, and determine that the failure type of the first monitoring device is Types of faults that require manual repair; the device also includes: a sending module, configured to send notification information that the lens glass of the first monitoring device is broken or dirty to the terminal device linked to the first monitoring device; or Wherein, the determining module is further configured to: when fog features exist in the first background image, determine that the lens of the first monitoring device has water ingress, and determine that the fault type of the first monitoring device requires manual labor. The type of fault to be repaired; the device also includes: a sending module, configured to send a notification message of water ingress to the lens of the first monitoring device to the terminal device linked with the first monitoring device; or Wherein, the determination module is further configured to: determine the environmental facility status in the current monitoring scene of the first monitoring device according to the first background image, and determine the history of the first monitoring device according to the second background image Monitoring the environmental facility status in the scene; when the environmental facility status in the current monitoring scene of the first monitoring device is different from the environmental facility status in the historical monitoring scene, determine the change of the environmental facility in the monitoring scene of the first monitoring device , and determine that the fault type of the first monitoring device is a fault type requiring manual repair; the device further includes: a sending module, configured to send notification information of scene reset to the terminal device linked with the first monitoring device, To remind the technician to perform scene reset operation on the first monitoring device; Wherein, the determination module is also used to: determine the monitoring parameters in the current monitoring scene of the first monitoring device according to the first background image; determine whether the current shooting parameters of the first monitoring device are the same as those of the first monitoring device The monitoring parameters in the current monitoring scene match; when the current shooting parameters of the first monitoring device do not match the monitoring parameters in the current monitoring scene of the first monitoring device, determining that the shooting parameters of the first monitoring device are abnormal, and determining that the fault type of the first monitoring device is a fault type that does not require manual repair; The device also includes a repair module, configured to: determine the shooting parameters that match the monitoring parameters, and adjust the shooting parameters of the first monitoring device to the shooting parameters that match the monitoring parameters; or restart The application process of the first monitoring device; or, restarting the system of the first monitoring device; Wherein, the obtaining module is further configured to: before the determining module determines the fault type of the first monitoring device based on the first background image, obtain a fourth background image; wherein, the fourth background image is A background image in the current monitoring scene of the second monitoring device, where the current monitoring scene of the second monitoring device and the current monitoring scene of the first monitoring device overlap at least in part; When determining the fault type of the first monitoring device based on the first background image, the determining module is configured to: determine the fault type of the first monitoring device according to the first background image and the fourth background image Fault type. 9. The apparatus according to claim 8, wherein the determining module is further configured to: after determining that the first monitoring device is faulty, based on the first background image, determine Fault type; The repair module is configured to automatically repair the fault of the first monitoring device when the fault type of the first monitoring device is a fault type that does not require manual repair. 10. The device of claim 9, further comprising: A sending module, configured to send a fault notification when the fault type of the first monitoring device is a fault type requiring manual repair. 11. The device according to claim 9, wherein when the determination module determines the fault type of the first monitoring device based on the first background image, it is specifically configured to: from the second background image Extract the first feature point from the image, and define the first feature point as a reference point; determine the second feature point that matches the reference point in the first background image; calculate the second feature point relative to The position offset of the reference point; judging whether the shooting angle of view of the first monitoring device is abnormal according to the position offset; when the shooting angle of the first monitoring device is abnormal, determine the first monitoring device The type of failure is the type of failure that does not require manual repair; The repair module is specifically configured to: calculate the angle of view offset of the first monitoring device according to the position offset, and adjust the lens parameters and/or pan/tilt of the first monitoring device according to the angle of view offset parameter. 12. A device for detecting a failure of a monitoring device, characterized in that it comprises at least one processor, and the at least one processor is coupled to at least one memory; A computer program or instruction for causing the device to perform the method according to any one of claims 1-7. 13. A computer-readable storage medium, wherein a computer program or instruction is stored in the computer-readable storage medium, and when the computer reads and executes the computer program or instruction, the computer executes the computer program according to claim 1. The method described in any one of to 7.

Images