An industrial monitoring system based on image data

By pre-swinging test of the camera and adjusting the number of filtered layers and aperture in the industrial monitoring system, the problem of image acquisition error in dust environments is solved, and the accuracy and clarity of the monitoring system are improved.

CN118921443BActive Publication Date: 2024-12-06TIANJIN FANGJIANG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411413021.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-11
Publication Date
2024-12-06
Estimated Expiration
2044-10-11

AI Technical Summary

Technical Problem

In the production workshop, the existing industrial video surveillance system based on satellite emergency communication network is caused by the scattering of light by dust particles and the attachment of dust to the camera lens, resulting in errors in image acquisition, affecting the accuracy of the monitoring system.

Method used

An industrial monitoring system based on image data is designed, including a monitoring module, an image transmission module and an image processing module. The actual rotation rate is determined by performing pre-swing test on the camera, and the mean filtering layer number and the The aperture amount reduces the impact of dust on image acquisition.

Benefits of technology

It improves image acquisition accuracy in dust environments, reduces image deformation and unclear problems caused by dust scattering and lens aging, and ensures the clarity and detail processing capabilities of the monitoring image.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921443B_ABST
    Figure CN118921443B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of image data processing, and in particular to an industrial monitoring system based on image data, comprising: a monitoring module, used for video monitoring of industrial production, comprising a plurality of cameras for collecting characteristic images of industrial production; an image transmission module, which is connected to the monitoring module and is used for transmitting the characteristic images of industrial production to a target position; an image processing module, which is connected to the image transmission module and comprises an image segmentation unit for segmenting the characteristic images of industrial production and an image filtering unit connected to the image segmentation unit and is used for filtering the segmented characteristic images of industrial production; a control module, which is respectively connected to the monitoring module and the image transmission module and is used for controlling the cameras to perform a pre-swing test to determine the actual rotation rate of the cameras for image acquisition. The present invention improves the monitoring accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image data processing, and in particular to an industrial monitoring system based on image data. Background Art

[0002] With the continuous development and progress of industrial production, modern industrial enterprises have higher and higher requirements for monitoring the production process. Traditional manual monitoring methods are not only inefficient, but also prone to human errors and negligence, and it is difficult to meet the needs of large-scale, high-precision production. Therefore, a more intelligent and efficient monitoring system is needed to ensure the safe, stable and efficient operation of the production process. In recent years, image acquisition and processing technology has made great progress. High-resolution image sensors, high-speed data transmission interfaces, and powerful image processing algorithms make it possible to acquire and analyze high-quality image data in real time. The development of these technologies has provided a solid technical foundation for industrial monitoring systems based on image data. With the rise of artificial intelligence and machine learning technologies, intelligent monitoring has become a development trend in the industrial field. Through deep learning and pattern recognition of image data, it is possible to automatically detect and warn of abnormal situations in the production process, thereby improving the safety and reliability of production. At the same time, the intelligent monitoring system can also analyze and mine production data to provide strong support for the production decision-making of enterprises. The development of the industrial Internet makes it possible for industrial equipment to be interconnected. Industrial monitoring systems based on image data can be integrated with other industrial equipment and systems to achieve data sharing and collaborative work, and improve the efficiency and intelligence level of the entire industrial production system.

[0003] Chinese patent publication number CN111491132A discloses an industrial video monitoring system based on a satellite emergency communication network, including: the industrial video monitoring system is constructed by a monitoring center, a monitoring front end and a remote client through a satellite IP network; the monitoring front end is configured with a network camera, a network video recorder, a microphone and an alarm, the network camera is connected to the network video recorder in the area through the network, the video code stream of the network camera is stored in the network video recorder, the microphone and the alarm are respectively accessed through the audio access terminal and the alarm access terminal set by the network camera; the monitoring center is configured with a monitoring management platform, a DVR access gateway and an operating device, the monitoring management platform has an embedded database and a network video unit, the built DVR monitoring point is connected to the monitoring center through the DVR access gateway, and the operating device is installed with the client software to realize the control, management and operation of the monitoring system; the remote client browses the monitoring image, performs PTZ control on the network camera, modifies the equipment parameters, and alarm linkage deployment and disarming. It can be seen that the industrial video monitoring system based on the satellite emergency communication network has the problem of image acquisition errors caused by the scattering of light by dust particles in the production workshop and the attachment of dust to the lens of the camera. Summary of the invention

[0004] To this end, the present invention provides an industrial monitoring system based on image data to overcome the problem in the prior art of image acquisition errors caused by light scattering by dust particles in a production workshop and dust adhesion to the lens of a camera.

[0005] To achieve the above object, the present invention provides an industrial monitoring system based on image data, comprising:

[0006] A monitoring module, used for video monitoring of industrial production, including a number of cameras for collecting characteristic images of industrial production;

[0007] An image transmission module, connected to the monitoring module, for transmitting the industrial production characteristic image to a target location;

[0008] An image processing module, which is connected to the image transmission module, and includes an image segmentation unit for segmenting the industrial production characteristic image and an image filtering unit connected to the image segmentation unit for filtering the segmented industrial production characteristic image;

[0009] A control module, which is connected to the monitoring module and the image transmission module respectively, is used to control the camera to perform a pre-swing test to determine the actual rotation rate of the camera for image acquisition, determine the image acquisition accuracy according to the deformation amplitude of the object contour in the image, and determine whether to adjust the number of layers of the mean filter,

[0010] Alternatively, the aperture value is adjusted according to the brightness difference between the contour deformation area and the non-deformation area.

[0011] Furthermore, the control module is respectively connected to the plurality of cameras to control the cameras to perform gradient tests of a plurality of rotation rates, and the rotation rate corresponding to the maximum image signal-to-noise ratio in the gradient test is used as the actual rotation rate.

[0012] Furthermore, the difference between the rotation rate of the camera in each test of the plurality of rotation rate gradient tests and the rotation rate of the camera in the adjacent test is equal.

[0013] Furthermore, the control module is connected to the image processing module to obtain the deformation amplitude of the object contour of the industrial production characteristic image.

[0014] If the deformation amplitude of the object contour is greater than a preset first deformation amplitude, the control module determines that the accuracy of image acquisition does not meet the requirements.

[0015] If the deformation amplitude of the object contour is greater than a preset second deformation amplitude, the control module controls the image segmentation unit to increase the number of layers of the mean filter.

[0016] Furthermore, the deformation amplitude of the object contour in the industrial production characteristic image is the change area of ​​the object with the largest contour deformation range in the industrial production characteristic image.

[0017] Furthermore, the number of layers of the mean filtering is the number of times the image segmentation unit performs equal-area segmentation on the industrial production feature image before the image filtering unit performs mean filtering on the industrial production feature image.

[0018] Among them, the size of the filter window of the mean filter is positively correlated with the area of ​​the segmented industrial production feature image.

[0019] Furthermore, the control module is connected to the monitoring module to preliminarily determine that the degree of light scattering by dust in the environment exceeds the allowable range when the deformation amplitude of the object contour is greater than the preset first deformation amplitude and less than or equal to the preset second deformation amplitude, and obtain the brightness of the contour deformation area and the brightness of the non-deformation area, and calculate the brightness difference.

[0020] If the brightness difference is greater than a preset brightness difference, it is further determined that the degree of light scattering by dust in the environment exceeds an allowable range, and the aperture of the camera is reduced.

[0021] Furthermore, the reduced aperture of the camera is determined by the difference between the brightness difference and the preset brightness difference.

[0022] Furthermore, the brightness difference is an absolute value of a difference between an average brightness of a number of sampling points arranged at equal intervals in the contour deformation region and an average brightness of a number of sampling points arranged at equal intervals in the non-deformation region.

[0023] Furthermore, the sampling object in the contour deformation area and the sampling object in the non-deformation area are the same object.

[0024] Compared with the prior art, the monitoring system of the present invention provides a monitoring module, an image transmission module, a storage module and a control module, and performs a pre-swing test on the camera to determine the actual rotation rate of the camera, thereby reducing the influence of inaccurate dust removal force on the camera during follow-up monitoring on the accuracy of image monitoring; by adjusting the number of mean filtering layers according to the deformation amplitude of the object contour in the image, the influence of image deformation and unclearness caused by lens aging particles on the monitoring camera or dust floating from the workshop adhering to the lens of the monitoring camera is reduced; by adjusting the aperture according to the brightness difference between the contour deformation area and the non-deformation area, the influence of errors in image acquisition caused by the scattering of light by dust particles in the production workshop is reduced, thereby achieving an improvement in the accuracy of monitoring images in the presence of dust in the workshop production process.

[0025] Furthermore, the present invention sets a preset first deformation amplitude and a preset second deformation amplitude, and increases the number of mean filtering layers according to the deformation amplitude of the object contour, thereby reducing the influence of inaccurate image acquisition caused by environmental dust on the camera and volatile materials formed by lens aging adhering to the lens, and increases the number of mean filtering layers, performs more refined processing on the details in the image, and avoids the interference of volatile materials on image acquisition with image processing, thereby further improving the accuracy of monitoring images in the presence of dust in the workshop production process.

[0026] Furthermore, the present invention sets a preset brightness difference and reduces the aperture of the camera according to the brightness difference, so as to reduce the effect of dust in the environment on light scattering, which causes deviation in image brightness and thus reduces the clarity of the image, thereby further improving the accuracy of monitoring images in the presence of dust in the workshop production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a block diagram of the overall structure of an industrial monitoring system based on image data according to an embodiment of the present invention;

[0028] Figure 2 A block diagram of a connection structure in which an image processing module and an image transmission module are connected in an industrial monitoring system based on image data according to an embodiment of the present invention;

[0029] Figure 3 A block diagram of a connection structure in which an image processing module and an image transmission module are connected in an industrial monitoring system based on image data according to an embodiment of the present invention;

[0030] Figure 4 The figure is an operation flow chart of an industrial monitoring system based on image data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0032] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0033] It will be understood by those skilled in the art that, unless otherwise stated, the singular forms "a", "an" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in this specification refers to the presence of features, integers, steps, operations, elements / components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements / components. It should be understood that when we refer to a module as being "connected" or "coupled" to another module, it may be directly connected or coupled to the other module, or there may be an intermediate unit. In addition, "connected" or "coupled" used herein may include wireless connection or wireless coupling.

[0034] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, they are respectively an overall structural block diagram of an industrial monitoring system based on image data according to an embodiment of the present invention, a connection structural block diagram of an image processing module and an image transmission module, and an operation flow chart. An industrial monitoring system based on image data according to an embodiment of the present invention comprises:

[0035] A monitoring module, used for video monitoring of industrial production, including a number of cameras for collecting characteristic images of industrial production;

[0036] An image transmission module, connected to the monitoring module, for transmitting the industrial production characteristic image to a target location;

[0037] An image processing module, which is connected to the image transmission module, and includes an image segmentation unit for segmenting the industrial production characteristic image and an image filtering unit connected to the image segmentation unit for filtering the segmented industrial production characteristic image;

[0038] A control module, which is connected to the monitoring module and the image transmission module respectively, is used to control the camera to perform a pre-swing test to determine the actual rotation rate of the camera for image acquisition, determine the image acquisition accuracy according to the deformation amplitude of the object contour in the image, and determine whether to adjust the number of layers of the mean filter,

[0039] Alternatively, the aperture value is adjusted according to the brightness difference between the contour deformation area and the non-deformation area.

[0040] Specifically, the camera in this embodiment is an industrial monitoring camera with the ability to rotate.

[0041] Specifically, the control module is connected to the plurality of cameras respectively to control the cameras to perform gradient tests of a plurality of rotation rates, and uses the rotation rate corresponding to the maximum image signal-to-noise ratio in the gradient test as the actual rotation rate.

[0042] Specifically, the difference between the rotation rate of the camera in each test of the plurality of rotation rate gradient tests and the rotation rate of the camera in the adjacent test is equal.

[0043] Specifically, the control module is connected to the image processing module to obtain the deformation amplitude of the object contour of the industrial production characteristic image.

[0044] If the deformation amplitude of the object contour is greater than a preset first deformation amplitude, the control module determines that the accuracy of image acquisition does not meet the requirements.

[0045] If the deformation amplitude of the object contour is greater than a preset second deformation amplitude, the control module controls the image segmentation unit to increase the number of layers of the mean filter.

[0046] In implementation, the optional range of the preset first deformation amplitude is [0.04cm², 0.09cm²], and the optional range of the preset second deformation amplitude is [0.1cm², 0.2cm²].

[0047] Preferably, the preferred embodiment of the preset first deformation amplitude is 0.06 cm², and the preferred embodiment of the preset second deformation amplitude is 0.15 cm².

[0048] In implementation, when the deformation amplitude of the object contour exceeds the preset second deformation amplitude by within 0.05cm², the number of mean filtering layers is adjusted to 0.8 times the current number of layers. When the deformation amplitude of the object contour exceeds the preset second deformation amplitude by 0.05cm², the number of mean filtering layers is reduced by 1 for every 0.005cm² increase in the amount exceeding the preset second deformation amplitude. For example, if the current number of mean filtering layers is 10 and the deformation amplitude of the object contour is 0.18cm², the number of mean filtering layers is adjusted to 10 layers × 0.8 = 8 layers. When the calculated value is not an integer, the number of mean filtering layers is determined by rounding up.

[0049] Furthermore, the present invention sets a preset first deformation amplitude and a preset second deformation amplitude, and increases the number of mean filtering layers according to the deformation amplitude of the object contour, thereby reducing the influence of inaccurate image acquisition caused by environmental dust on the camera and volatile materials formed by lens aging adhering to the lens, and increases the number of mean filtering layers, performs more refined processing on the details in the image, and avoids the interference of volatile materials on image acquisition with image processing, thereby further improving the accuracy of monitoring images in the presence of dust in the workshop production process.

[0050] Specifically, the deformation amplitude of the object contour in the industrial production characteristic image is the change area of ​​the object with the largest contour deformation range in the industrial production characteristic image.

[0051] Specifically, the number of layers of the mean filter is the number of times the image segmentation unit performs equal-area segmentation on the industrial production feature image before the image filtering unit performs mean filtering on the industrial production feature image.

[0052] Among them, the size of the filter window of the mean filter is positively correlated with the area of ​​the segmented industrial production feature image.

[0053] Specifically, the control module is connected to the monitoring module to preliminarily determine that the degree of light scattering by dust in the environment exceeds the allowable range when the deformation amplitude of the object contour is greater than the preset first deformation amplitude and less than or equal to the preset second deformation amplitude, and obtain the brightness of the contour deformation area and the brightness of the non-deformation area, and calculate the brightness difference.

[0054] If the brightness difference is greater than a preset brightness difference, it is further determined that the degree of light scattering by dust in the environment exceeds an allowable range, and the aperture of the camera is reduced.

[0055] Furthermore, the present invention sets a preset brightness difference and reduces the aperture of the camera according to the brightness difference, so as to reduce the effect of dust in the environment on light scattering, which causes deviation in image brightness and thus reduces the clarity of the image, thereby further improving the accuracy of monitoring images in the presence of dust in the workshop production process.

[0056] Specifically, the reduced aperture of the camera is determined by the difference between the brightness difference and the preset brightness difference.

[0057] In implementation, the preset brightness difference is generally available in a range of [5cd / m², 10cd / m²].

[0058] Preferably, the preferred embodiment of the preset brightness difference is 7cd / m².

[0059] In implementation, when the brightness difference between the contour deformation area and the non-deformed area exceeds the preset brightness difference within 6cd / m², the aperture of the camera is adjusted to the first aperture before the current aperture of the camera; when the brightness difference between the contour deformation area and the non-deformed area exceeds the preset brightness difference by more than 6cd / m², the aperture of the camera is adjusted to the second aperture before the current aperture of the camera; for example, if the brightness difference between the contour deformation area and the non-deformed area is 10cd / m² and the current aperture of the camera is f / 2.8, the adjusted aperture becomes f / 2.

[0060] Specifically, Aperture Value (Av or A for short) is a relative value used to express the size of the aperture opening; it is a logarithmic unit used to control the aperture size of the camera lens in photography, thereby adjusting the amount of light passing through the lens into the camera's photosensitive element (such as film or digital sensor).

[0061] Apertures are usually arranged in the following series, with the size of the aperture opening differing by approximately one stop between each adjacent aperture value, so the amount of light allowed in by each aperture value differs by approximately one stop: f / 1, f / 1.4, f / 2, f / 2.8,f / 4, f / 5.6, f / 8, f / 11, f / 16, f / 22, f / 32, f / 45, f / 64, ...

[0062] Specifically, the brightness difference is the absolute value of the difference between the average brightness of a number of sampling points arranged at equal intervals in the contour deformation area and the average brightness of a number of sampling points arranged at equal intervals in the non-deformation area.

[0063] Specifically, the sampling object in the contour deformation area and the sampling object in the non-deformation area are the same object.

[0064] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An industrial monitoring system based on image data, characterized in that: include: A monitoring module, used for video monitoring of industrial production, including a number of cameras for collecting characteristic images of industrial production; An image transmission module, connected to the monitoring module, for transmitting the industrial production characteristic image to a target location; An image processing module, which is connected to the image transmission module, and includes an image segmentation unit for segmenting the industrial production characteristic image and an image filtering unit connected to the image segmentation unit for filtering the segmented industrial production characteristic image; A control module, which is connected to the monitoring module and the image transmission module respectively, is used to control the camera to perform a pre-swing test to determine the actual rotation rate of the camera for image acquisition, determine the image acquisition accuracy according to the deformation amplitude of the object contour in the image, and determine whether to adjust the number of layers of the mean filter, Alternatively, the aperture value is adjusted according to the brightness difference between the contour deformation area and the non-deformation area.

2. The industrial monitoring system based on image data according to claim 1, characterized in that: The control module is connected to the plurality of cameras respectively to control the cameras to perform gradient tests of a plurality of rotation rates, and uses the rotation rate corresponding to the maximum image signal-to-noise ratio in the gradient test as the actual rotation rate.

3. The industrial monitoring system based on image data according to claim 2, characterized in that: The difference between the rotation rate of the camera in each test of the plurality of rotation rate gradient tests and the rotation rate of the camera in the adjacent test is equal.

4. The industrial monitoring system based on image data according to claim 3 is characterized in that: The control module is connected to the image processing module to obtain the deformation amplitude of the object contour of the industrial production characteristic image. If the deformation amplitude of the object contour is greater than a preset first deformation amplitude, the control module determines that the accuracy of image acquisition does not meet the requirements. If the deformation amplitude of the object contour is greater than a preset second deformation amplitude, the control module controls the image segmentation unit to increase the number of layers of the mean filter.

5. The industrial monitoring system based on image data according to claim 4, characterized in that: The deformation amplitude of the object contour of the industrial production characteristic image is the change area of ​​the object with the largest contour deformation range in the industrial production characteristic image.

6. The industrial monitoring system based on image data according to claim 5, characterized in that: The number of layers of the mean filter is the number of times the image segmentation unit performs equal-area segmentation on the industrial production feature image before the image filtering unit performs mean filtering on the industrial production feature image. Among them, the size of the filter window of the mean filter is positively correlated with the area of ​​the segmented industrial production feature image.

7. The industrial monitoring system based on image data according to claim 6, characterized in that: The control module is connected to the monitoring module, and is used to preliminarily determine that the degree of light scattering by dust in the environment exceeds the allowable range when the deformation amplitude of the object contour is greater than the preset first deformation amplitude and less than or equal to the preset second deformation amplitude, and obtain the brightness of the contour deformation area and the brightness of the non-deformation area, and calculate the brightness difference. If the brightness difference is greater than a preset brightness difference, it is further determined that the degree of light scattering by dust in the environment exceeds an allowable range, and the aperture of the camera is reduced.

8. The industrial monitoring system based on image data according to claim 7, characterized in that: The reduced aperture of the camera is determined by the difference between the brightness difference and the preset brightness difference.

9. The industrial monitoring system based on image data according to claim 8, characterized in that: The brightness difference is an absolute value of a difference between an average brightness of a plurality of equally spaced sampling points in the contour deformation region and an average brightness of a plurality of equally spaced sampling points in the non-deformation region.

10. The industrial monitoring system based on image data according to claim 9, characterized in that: The sampling object in the contour deformation area and the sampling object in the non-deformation area are the same object.