CN114827466A - Human eye-imitated equipment image acquisition device and image acquisition method - Google Patents
Human eye-imitated equipment image acquisition device and image acquisition method Download PDFInfo
- Publication number
- CN114827466A CN114827466A CN202210413048.XA CN202210413048A CN114827466A CN 114827466 A CN114827466 A CN 114827466A CN 202210413048 A CN202210413048 A CN 202210413048A CN 114827466 A CN114827466 A CN 114827466A
- Authority
- CN
- China
- Prior art keywords
- image acquisition
- image
- equipment
- defect
- rectangular frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/95—Computational photography systems, e.g. light-field imaging systems
- H04N23/951—Computational photography systems, e.g. light-field imaging systems by using two or more images to influence resolution, frame rate or aspect ratio
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses an eye-simulated equipment image acquisition device and an eye-simulated equipment image acquisition method, belongs to the technical field of equipment running state detection, and can realize accurate acquisition of equipment panoramic images and defect part amplified images in a shooting area and accurate monitoring of the running state of equipment by carrying out Sudoku division and shooting on the shooting area of equipment to be monitored. The human eye simulating device image acquisition device is compact in structure, the method for acquiring the image is convenient and fast, the panoramic image acquisition and the local clear image acquisition of the device to be monitored can be realized, the defect part image on the device to be monitored can be accurately acquired, an accurate and sufficient judgment basis is provided for the accurate judgment of the running state of the device to be monitored, the monitoring accuracy and reliability of the device are ensured, the normal running of the corresponding device is sufficiently guaranteed, and the human eye simulating device image acquisition device has good practical value and application prospect.
Description
Technical Field
The invention belongs to the technical field of equipment running state detection, and particularly relates to an eye-imitated equipment image acquisition device and an eye-imitated equipment image acquisition method.
Background
In the operation process of the high-voltage substation, the operation states of various devices of the high-voltage substation often directly influence the safety and reliability of a power grid. Therefore, in the actual operation process of the substation, the operation states of various devices, especially important components such as transformers, need to be monitored regularly or in real time.
At present, for monitoring substation operation equipment, a common camera device is mostly arranged to perform overall shooting of the equipment, so as to complete state monitoring and judgment of related equipment. Although the method can realize the monitoring of the substation equipment to a certain extent, the monitoring precision is poor, and the abnormal states of local areas and core parts of the equipment cannot be accurately observed, so that the operation condition interpretation error of the relevant equipment of the substation is large, and the monitoring of the operation state of the substation equipment cannot be quickly and accurately realized.
Disclosure of Invention
Aiming at one or more of the defects or the improvement requirements in the prior art, the invention provides the human eye-simulated equipment image acquisition device and the human eye-simulated equipment image acquisition method, which can realize human eye-simulated monitoring of transformer substation equipment, realize accurate acquisition of panoramic images and local images and fully ensure the accuracy and reliability of monitoring of the running state of the equipment.
In order to achieve the above object, in one aspect of the present invention, there is provided an image capturing method of a human-eye-simulated device, which is implemented by using an image capturing apparatus of the device;
the equipment image acquisition device comprises a holder and an image acquisition main body which is rotatably connected to the holder through a support; the image acquisition main body comprises a variable-focus camera, an infrared camera and a binocular depth camera which are arranged in an integrated mode, and image processing modules are electrically connected with the cameras, so that the image processing modules can receive images acquired by the corresponding cameras and synthesize images for defect identification;
correspondingly, the method for acquiring the equipment image by using the equipment image acquisition device comprises the following steps:
s1, controlling the central axis of the shooting field of view of the image acquisition main body to be consistent with the central axis of the equipment to be monitored;
s2, initializing the position of the holder, and recording the position as P 0 (ii) a Meanwhile, initializing the focal length of the zoom camera to reduce the shooting picture to the minimum and maximize objects which can be shot in the camera field of view;
s3, taking the area to be shot as P 0 Divide nine palaces for the centerGrid, in turn denoted P 0 ～P 8 Starting the image acquisition main body to take a Sudoku photo of the area to be shot;
s4, transmitting the Sudoku picture obtained in the step S3 to the image processing module, and carrying out picture fusion at the image processing module to obtain a panoramic big picture of the current shooting area of the equipment;
s5, controlling the image processing module to identify the panoramic big image by using the deep learning algorithm, finding out the defect part in the image, and marking the defect part with a defect rectangular frame r n N is an integer not less than 1;
s6, determining a defect rectangular frame r n Region position P in plane Sudoku m (ii) a m is an integer, and m is more than or equal to 0 and less than or equal to 8;
s7, controlling the holder to rotate to a Sudoku area where the corresponding defect rectangular frame is located, and calculating the physical distance between the current defect part and the device by using a binocular depth camera according to the coordinates of the defect rectangular frame; controlling the variable-focus camera to adjust the focal length and amplifying the image of the defect part;
s8, controlling the tripod heads to respectively rotate to the region positions P obtained in the step S6 m And according to the defective rectangular frame r n Adjusting the position of the holder and placing the defect part in the center of a shot picture of the image acquisition main body;
s9 shooting defect rectangular frame r n Storing the image of the corresponding part to obtain a high-definition large image corresponding to the defect part; then, the cradle head is turned to reset to the initial position P 0 And repeating the step S8 until the defect images corresponding to all the defect rectangular frames are completely acquired.
As a further improvement of the present invention, in step S3, the process of taking a nine-square photograph includes:
s301: setting the rotational speed of the holder to be uniform and rotating the holder to an initial position P 0 (ii) a After that, starting shooting and saving to obtain P 0 A picture corresponding to the position;
s302: starting said head to rotate from P a The more the position startsGo through one cell to P a+1 And (5) sequentially obtaining pictures corresponding to the positions of all the areas in the nine-square grid, wherein a is an integer and is more than or equal to 0 and less than 8.
As a further improvement of the invention, the space between two adjacent position areas in the squared figure is equal, and the rotation time of the tripod head between two adjacent positions is equal.
As a further improvement of the present invention, in step S5, the process of obtaining the defective rectangular frame is as follows:
s501: collecting data pictures of various defects corresponding to equipment to be monitored;
s502: marking, cleaning and augmenting the data picture according to different defect types;
s503: training the processed samples by adopting a yolov5 training frame to obtain a high-precision equipment defect identification model;
s504: the model is packaged and deployed on a computing platform with AI computing power in a micro-service mode, and a defect identification service is provided for the outside;
s505: carrying out scaling, mean value reduction, normalization and regularization pretreatment on the synthesized panoramic big image;
s506: and after uploading the preprocessed pictures to a defect identification service, taking the rectangular frame exceeding a certain threshold value as an alarm rectangular frame and outputting the alarm rectangular frame.
As a further improvement of the present invention, in step S6, the process of determining the defective rectangular frame position is as follows:
calculating the center coordinates (x ', y') of the defect rectangular frame according to the following formula 1 and formula 2, and calculating the area position of the coordinates in the nine-square grid according to the corresponding relation of the coordinates;
wherein x is imin Is a nine-gridMinimum x coordinate, x, of grid rectangle frame i imax The maximum x coordinate of the squared figure rectangular frame i; y is imin Is the minimum y coordinate of the squared rectangle frame i imax Is the maximum y coordinate of the squared rectangle frame i.
As a further improvement of the present invention, in step S7, the variable focus camera performs adjustment of the focal length by equation 3;
1/u +1/v ═ 1/f (equation 3)
Wherein u is the object distance, v is the image distance, and f is the focal length.
As a further improvement of the present invention, when the nine-grid shooting of the area to be shot is performed in step S3, the infrared camera is synchronously controlled to shoot the temperature state of each area in the nine-grid.
In another aspect of the invention, an image acquisition device of a human eye-simulating device is provided, which comprises a holder and an image acquisition main body;
the image acquisition main body is rotatably connected to the holder through a support and can be subjected to pitching adjustment relative to the holder;
the image acquisition main body comprises a variable-focus camera, an infrared camera and a binocular depth camera which are arranged in an integrated mode and are respectively used for acquiring a high-resolution image under the condition of zooming, acquiring the temperature state of a corresponding area and measuring distance in the image acquisition process; meanwhile, an image processing module is arranged in the image acquisition main body, is electrically connected with each camera and is used for receiving the images acquired by the corresponding cameras and synthesizing the images for defect identification.
As a further improvement of the invention, a moving mechanism is arranged corresponding to the holder; the holder is arranged on the moving mechanism in a carrying manner, and the shooting position can be changed under the driving of the moving mechanism.
As a further improvement of the present invention, a protective cover is disposed on the top of the image capturing body.
The above-described improved technical features may be combined with each other as long as they do not conflict with each other.
Generally, compared with the prior art, the technical scheme conceived by the invention has the following beneficial effects:
(1) the invention relates to a human eye simulating equipment image acquisition method, which utilizes the corresponding arrangement of an image acquisition main body with a variable-focus camera, a binocular depth camera and an infrared camera on a holder, divides a shooting area of equipment to be monitored into nine-grid squares, controls the image acquisition main body to shoot the nine-grid squares, and then accurately obtains a panoramic image in the shooting area; meanwhile, through the arrangement of the image processing module, the defect positions in the panoramic image are determined in real time based on the AI technology, the defect positions are marked and the amplified image is shot correspondingly, so that the defect state of the equipment to be monitored is accurately acquired, the accurate monitoring of the corresponding equipment is realized, and the running reliability of the equipment is ensured.
(2) According to the human eye simulating equipment image acquisition method, the photographing process of the nine-square grid, the acquiring process of the defect rectangular frame, the position determining process of the defect rectangular frame and the like are preferably designed, so that the accurate completion of the monitoring photographing process of the equipment can be realized, the determination and clear photographing of the defect part can be quickly realized, the precision and the efficiency of defect part state acquisition are improved, the running state of related equipment is fed back in time, the normal work of the equipment is ensured, and an enough basis is provided for the subsequent maintenance of the defect equipment.
(3) The human eye simulating equipment image acquisition device is compact in structure and convenient to carry, can realize the shooting process of human eye simulation through the integrated arrangement of the zoom camera, the infrared camera, the binocular depth camera and the image processing module, realizes the accurate acquisition of a panoramic large image and a regional defect image of equipment to be monitored and shot, ensures the accuracy and reliability of monitoring the running state of the equipment, realizes the accurate monitoring and shooting of corresponding equipment, and ensures the normal running of a corresponding system.
(4) The human eye simulating device image acquisition device is compact in structure, convenient and fast in acquisition method, capable of achieving panoramic image acquisition and local clear image acquisition of the device to be monitored, capable of accurately acquiring the defect part image on the device to be monitored, providing accurate and sufficient judgment basis for accurate judgment of the running state of the device to be monitored, capable of guaranteeing the accuracy and reliability of monitoring of the device, capable of providing sufficient guarantee for normal running of corresponding devices, and good in practical value and application prospect.
Drawings
FIG. 1 is a flow chart of the embodiment of the present invention when an apparatus image acquisition device is used for acquiring an apparatus image;
FIG. 2 is a schematic structural diagram of an image acquisition device of a human eye simulation device in an embodiment of the invention;
FIG. 3 is a track diagram of a Sudoku image acquisition process performed by an apparatus image acquisition device according to an embodiment of the present invention;
in all the figures, the same reference numerals denote the same features, in particular:
1. an image acquisition subject; 2. a holder; 3. a support; 4. a protective cover;
101. a variable focus camera; 102. an infrared camera; 103. a binocular depth camera.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are not to be considered limiting of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
Example (b):
referring to fig. 2, the image capturing device of the eye-imitating apparatus in the preferred embodiment of the present invention includes an image capturing main body 1 rotatably connected to a cradle head 2 through a bracket 3, so that the image capturing main body 1 can rotate in a pitching manner with respect to the cradle head 2, thereby achieving accurate alignment of the image capturing main body 1 and an object to be photographed. Simultaneously, through the corresponding setting of cloud platform 2 for image acquisition main part 1 can follow cloud platform 2 and carry out the rotation regulation in the horizontal plane, realizes that image acquisition main part 1 upwards shoots the adjustment of visual angle at the level.
In addition, in a preferred embodiment, the pan/tilt head 2 can rotate 360 ° in all directions, and is further preferably mounted on a movable trolley (not shown in the figure), and the change of the shooting position can be realized by using the mounting movement of the movable trolley, so that the monitoring of the image acquisition main body 1 on different positions of the same device or different devices is completed, and images of different areas and different devices are acquired correspondingly.
Specifically, the image capturing body 1 in the preferred embodiment is a box-shaped structure, and the variable focus camera 101, the infrared camera 102 and the binocular depth camera 103 are integrally disposed inside the image capturing body 1, and an image processing module is correspondingly disposed inside the image capturing body 1. Wherein the variable focus camera 101 is used to acquire a high resolution image with a corresponding zoom; the infrared camera 102 is used for monitoring and shooting abnormal heating of the equipment; the binocular depth camera 103 is used for completing ranging in an image acquisition process, the center of the field of view of the variable focus camera 101 is the same as that of the binocular depth camera 103, and the field of view of the two cameras is always consistent. Accordingly, the image processing module is electrically connected with each camera respectively and is used for receiving the images collected by the corresponding camera and synthesizing the images for defect identification.
Preferably, in order to protect the image capturing body 1, a protective cover 4 is preferably provided on the top thereof, thereby providing shielding and protection to the image capturing body 1 during use.
Further, in a preferred embodiment, the process of monitoring the operation state of the device by using the device image acquisition apparatus is as follows:
and S1, controlling the device image acquisition device to move and travel to one side of the device to be monitored, and ensuring that the central axis of the image acquisition main body 1 is consistent with the central axis of the device to be monitored.
In actual work, the method for keeping the central axis of the image acquisition main body 1 consistent with the central axis of the equipment to be monitored mainly comprises the following steps: firstly, the focal length of the zoom camera 101 is reduced, so that a shooting picture comprises the whole equipment to be monitored; after the image acquisition main body 1 identifies the whole outline of the equipment, the central position of the whole outline of the equipment is taken, and the central position is coincided with the central position of the shot picture, namely the central axis is consistent. Thereafter, the focal length is enlarged and the pan/tilt head 2 is adjusted again.
S2, initializing the position of the pan-tilt head 2, and recording the position as P 0 (ii) a At the same time, the focal length of the zoom camera 101 is initialized to minimize the frame size and maximize the number of objects that can be captured within the camera's field of view.
S3, dividing the area to be shot into nine-grid forms, and recording the forms as P in sequence 0 ～P 8 Starting the image acquisition main body 1 to take a nine-grid photo of the equipment to be monitored, and acquiring an image of the equipment to be monitored;
during actual shooting, the tripod head 2 firstly generates a virtual Sudoku shooting area for an object to be monitored; secondly, the tripod head 2 preferably starts from the nine-square-grid center position, and locally shoots the equipment according to nine directions of center, left, upper right, lower left and lower left in sequence to obtain nine-square-grid pictures; after the shooting is finished, the pan-tilt 2 returns to the initial position P 0 。
It can be seen that, in the above-described photographing process, the image capturing subject 1 is completing P 0 After the point location is shot, the subsequent shooting paths are sequentially carried out along the clockwise direction, and the shooting is sequentially finished (P) 1 、P 2 、……、P 8 ) The image of each spot is taken as shown in fig. 3. It can be understood that, when the motion path of the pan/tilt head 2 is actually set, the shooting path of the image capturing body 1 may also be set to be performed in a "counterclockwise" manner, or any free and scattered shooting path may be adopted as long as the shot can be taken with the nine-grid center P 0 Nine images at the center are sufficient.
Further specifically, the implementation process of the squared figure shooting method in step S3 is as follows:
s301: setting the rotation speed of the pan/tilt head 2 to be uniform and rotating the pan/tilt head 2 to the initial position P 0 When starting shooting, the picture is saved and is P 0 And (5) pictures corresponding to the positions.
S302: starting upThe head 2 rotates from P 0 Starting position and starting timing, when the rotation time is t 0 When it is, it means to cross one cell to P 1 Position, after that, taking a picture and storing to obtain P 1 A picture of a spatial region.
S303: the rotation route of the control cloud deck 2 is shown in the attached figure 3, and so on until all the areas corresponding to the nine-square grid are shot.
In a preferred embodiment, each spatial zone in the nine-grid area is preferably square, i.e. the distance between adjacent grids is equal, so as to ensure that the duration t of each rotation of the head 2 is equal m Are equal.
In addition, in actual operation, the size of one side of the device is not very large, and in this case, the division into the nine-square grids is performed, so that the whole area of one side of the device can be determined by the nine-square grids. Of course, it can be understood that when the single-side area of the device is larger, a part of the area of the device can be selected first, and then the selected area is divided into nine-grid squares.
And S4, transmitting the Sudoku picture obtained in the step S3 to an image processing module, and carrying out picture fusion at the image processing module to obtain a panoramic large picture of the current shooting area of the equipment.
When the fusion of the panoramic large image is actually performed, the fusion method preferably includes the following steps: and firstly fusing single-layer images and then fusing layers. Taking the form in FIG. 3 as an example, P is first introduced 2 、P 3 、P 4 Merged into a big picture P x (ii) a Then P is put 1 、P 0 、P 5 Merged into a big picture P y (ii) a And P is 8 、P 7 、P 6 Merged into a big picture P z (ii) a Then, P is added x 、P y 、P z Rotating 90 degrees anticlockwise and then fusing in sequence to obtain a complete big picture; and finally, rotating the obtained complete large image by 90 degrees clockwise to obtain the panoramic large image.
S5, controlling the image processing module to recognize the panorama by using the deep learning algorithm, finding the defect position in the panorama, and marking the defect position with a rectangular frame (r) 1 、r 2 、……、r n (ii) a Wherein n is an integer of not less than 1).
Specifically, the process of obtaining the rectangular frame of the defect portion in the preferred embodiment includes the following steps:
s501: collecting data pictures of various defects corresponding to equipment to be monitored;
s502: marking, cleaning and augmenting the data picture according to different defect types;
s503: training the processed samples by adopting a yolov5 training frame to obtain a high-precision equipment defect identification model;
s504: the model is packaged and deployed on a computing platform with AI computing power in a micro-service mode, and a defect identification service is provided for the outside;
s505: and carrying out preprocessing such as scaling, mean value reduction, normalization, regularization and the like on the synthesized panoramic large image.
S506: and after uploading the preprocessed pictures to a defect identification service, taking the rectangular frame exceeding a certain threshold value as an alarm rectangular frame and outputting the alarm rectangular frame.
S6, finding out the area position of the defect rectangular frame in the plane Sudoku, and recording as (P) 0 、P 1 、……、P m (ii) a Wherein m is an integer, and m is more than or equal to 0 and less than or equal to 8).
Specifically, in the preferred embodiment, the process of determining the position of each defective rectangular box in the squared figure is as follows:
according to the following formula 1 and formula 2, the center coordinates (x ', y') of the defect rectangular frame are calculated, and the area of the coordinates in the squared figure is calculated according to the coordinate correspondence.
Wherein x is imin Is the minimum x coordinate, x, of the squared rectangle frame i imax Is the best of a squared figure rectangular frame iA large x coordinate; y is imin Is the minimum y coordinate of the squared rectangle frame i imax Is the maximum y coordinate of the squared rectangle frame i.
S7, controlling the pan-tilt 2 to rotate to the corresponding Sudoku area where the defect rectangular frame is located, calculating the physical distance dis between the current defect part and the device by the binocular depth camera 103 according to the coordinates of the defect rectangular frame, and adjusting the focal length and amplifying the image of the defect part by the zoom camera 101 according to a conversion formula (namely formula 3) of the distance and the focal length.
1/u +1/v ═ 1/f (equation 3)
Wherein u is the object distance, v is the image distance, and f is the focal length.
S8, controlling the pan/tilt head 2 to rotate to the position (P) obtained in the step S6 0 、P 1 、……、P n ) Corresponding region P in n And according to a rectangular frame (r) 1 、r 2 、……、r n ) The coordinate of the starting point, the width and the height of the cradle head 2 are finely adjusted, and the defect part is arranged in the center of the shot picture of the image acquisition main body 1.
S9, shooting and storing to obtain P m After the high-definition large image of the defect position, turning to a pan-tilt 2 to an initial position P 0 . Thereafter, step S8 is repeated until a rectangular frame (r) 1 、r 2 、……、r n ) All the processes are finished.
After the steps are completed, the running state of the monitoring object is judged according to the acquired defect part image.
In more detail, in a specific preferred embodiment, the device image capturing apparatus is used for detecting the state of a device associated with a substation, for example, detecting the state of a transformer device in a high-voltage substation, and during the detection, in addition to the monitoring contents, shooting is performed in a nine-grid area by using the infrared camera 102, and simultaneously shooting the temperature state in the nine-grid area is performed, so that the defect state of a corresponding portion of the device can be fully reflected by combining image capturing of defect portions in each area of the nine-grid, and the accuracy of device monitoring is further improved. Through monitoring and shooting each device in the transformer substation, the abnormal state of the corresponding device can be found in real time, the normal work of the transformer substation and a related power grid is ensured, and the reliability and the stability of the power grid operation are improved.
The human eye simulating equipment image acquisition device has a compact structure, is convenient and fast in acquisition method, can realize panoramic image acquisition and local clear image acquisition of equipment to be monitored, can accurately acquire the defect part image on the equipment to be monitored, provides an accurate and sufficient judgment basis for accurately judging the running state of the equipment to be monitored, ensures the accuracy and reliability of equipment monitoring, provides a sufficient guarantee for the normal running of corresponding equipment, and has good practical value and application prospect.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A human eye-imitating equipment image acquisition method is characterized by being realized by an equipment image acquisition device;
the equipment image acquisition device comprises a holder and an image acquisition main body which is rotatably connected to the holder through a support; the image acquisition main body comprises a variable-focus camera, an infrared camera and a binocular depth camera which are arranged in an integrated mode, and image processing modules are electrically connected with the cameras, so that the image processing modules can receive images acquired by the corresponding cameras and synthesize images for defect identification;
correspondingly, the method for acquiring the equipment image by using the equipment image acquisition device comprises the following steps:
s1, controlling the central axis of the shooting field of view of the image acquisition main body to be consistent with the central axis of the equipment to be monitored;
s2, initializing the position of the holder, and recording the position as P 0 (ii) a Meanwhile, initializing the focal length of the zoom camera to reduce the shooting picture to the minimum and maximize objects which can be shot in the camera field of view;
s3, taking the area to be shot as P 0 Dividing the nine-grid into two parts, sequentially marking as P 0 ～P 8 Starting the image acquisition main body to take a Sudoku photo of the area to be shot;
s4, transmitting the Sudoku picture obtained in the step S3 to the image processing module, and carrying out picture fusion at the image processing module to obtain a panoramic big picture of the current shooting area of the equipment;
s5, controlling the image processing module to identify the panoramic big image by using the deep learning algorithm, finding out the defect part in the image, and marking the defect part with a defect rectangular frame r n N is an integer not less than 1;
s6, determining a defect rectangular frame r n Region position P in plane Sudoku m (ii) a m is an integer, and m is more than or equal to 0 and less than or equal to 8;
s7, controlling the holder to rotate to a Sudoku area where the corresponding defect rectangular frame is located, and calculating the physical distance between the current defect part and the device by using a binocular depth camera according to the coordinates of the defect rectangular frame; controlling the variable-focus camera to adjust the focal length and amplifying the image of the defect part;
s8, controlling the tripod heads to respectively rotate to the region positions P obtained in the step S6 m And according to the defect rectangular frame r n Adjusting the position of the holder and placing the defect part in the center of a shot picture of the image acquisition main body;
s9 shooting defect rectangular frame r n Storing the image of the corresponding part to obtain a high-definition large image corresponding to the defect part; then, the cradle head is turned to reset to the initial position P 0 And repeating the step S8 until the defect images corresponding to all the defect rectangular frames are completely acquired.
2. The eye-liked apparatus image-capturing method of claim 1, wherein in step S3, the process of taking a nine-grid photo includes:
s301: setting the rotational speed of the holder to be uniform and rotating the holder to an initial position P 0 (ii) a After that, starting shooting and saving to obtain P 0 Picture corresponding to position；
S302: starting said head to rotate from P a Position starts and goes over a lattice to P a+1 And (5) sequentially obtaining pictures corresponding to the positions of all the areas in the nine-square grid, wherein a is an integer and is more than or equal to 0 and less than 8.
3. The image acquisition method of the human eye-imitating equipment according to claim 2, wherein the intervals between two adjacent position areas in the squared figure are equal, and the rotation time of the holder between two adjacent positions is equal.
4. The image capturing method of an eye-liked device according to any one of claims 1 to 3, wherein in step S5, the procedure of obtaining the defective rectangular frame is as follows:
s501: collecting data pictures of various defects corresponding to equipment to be monitored;
s502: marking, cleaning and augmenting the data picture according to different defect types;
s503: training the processed samples by adopting a yolov5 training frame to obtain a high-precision equipment defect identification model;
s504: the model is packaged and deployed on a computing platform with AI computing power in a micro-service mode, and a defect identification service is provided for the outside;
s505: carrying out scaling, mean value reduction, normalization and regularization pretreatment on the synthesized panoramic big image;
s506: and after uploading the preprocessed pictures to a defect identification service, taking the rectangular frame exceeding a certain threshold value as an alarm rectangular frame and outputting the alarm rectangular frame.
5. The image capturing method of an eye-liked device according to any one of claims 1 to 4, wherein in step S6, the process of determining the position of the defective rectangular frame is as follows:
calculating the center coordinates (x ', y') of the defect rectangular frame according to the following formula 1 and formula 2, and calculating the area position of the coordinates in the nine-square grid according to the corresponding relation of the coordinates;
wherein x is imin Is the minimum x coordinate, x, of the squared rectangle frame i imax The maximum x coordinate of the squared figure rectangular frame i; y is imin Is the minimum y coordinate of the squared rectangle frame i imax Is the maximum y coordinate of the squared rectangle frame i.
6. The image acquisition method of the human-eye-imitating equipment according to any one of claims 1 to 5, wherein in step S7, the variable-focus camera adjusts the focal length by formula 3;
1/u +1/v ═ 1/f (equation 3)
Wherein u is the object distance, v is the image distance, and f is the focal length.
7. The human eye simulating device image acquisition method according to any one of claims 1 to 6, wherein when the photographing of the nine-palace lattice of the region to be photographed is performed in step S3, the infrared camera is synchronously controlled to photograph the temperature state of each region in the nine-palace lattice.
8. An eye-imitating equipment image acquisition device is characterized by comprising a holder and an image acquisition main body;
the image acquisition main body is rotatably connected to the holder through a support and can be subjected to pitching adjustment relative to the holder;
the image acquisition main body comprises a variable-focus camera, an infrared camera and a binocular depth camera which are arranged in an integrated mode, and the image acquisition main body is used for acquiring a high-resolution image under the zooming condition, acquiring the temperature state of a corresponding area and measuring distance in the image acquisition process; meanwhile, an image processing module is arranged in the image acquisition main body, is electrically connected with each camera and is used for receiving the images acquired by the corresponding cameras and synthesizing the images for defect identification.
9. The human eye simulation equipment image acquisition device as claimed in claim 8, wherein a moving mechanism is arranged corresponding to the holder; the holder is arranged on the moving mechanism in a carrying manner, and the shooting position can be changed under the driving of the moving mechanism.
10. The eye-liked apparatus image-capturing device according to claim 8 or 9, wherein a protective cover is provided on a top of the image-capturing body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210413048.XA CN114827466B (en) | 2022-04-20 | 2022-04-20 | Human eye-like equipment image acquisition device and image acquisition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210413048.XA CN114827466B (en) | 2022-04-20 | 2022-04-20 | Human eye-like equipment image acquisition device and image acquisition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114827466A true CN114827466A (en) | 2022-07-29 |
| CN114827466B CN114827466B (en) | 2023-07-04 |
Family
ID=82505922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210413048.XA Active CN114827466B (en) | 2022-04-20 | 2022-04-20 | Human eye-like equipment image acquisition device and image acquisition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827466B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101883261A (en) * | 2010-05-26 | 2010-11-10 | 中国科学院自动化研究所 | Method and system for abnormal target detection and relay tracking under large-range monitoring scene |
| JP2011114788A (en) * | 2009-11-30 | 2011-06-09 | Sanyo Electric Co Ltd | Imaging apparatus and imaging method |
| CN106809710A (en) * | 2015-11-30 | 2017-06-09 | 福建省特种设备检验研究院泉州分院 | Elevator magnetic buffering protection device |
| US20190096054A1 (en) * | 2017-05-15 | 2019-03-28 | HKC Corporation Limited | Image acquiring device and method of correcting coordinates thereof |
| CN109979468A (en) * | 2019-03-05 | 2019-07-05 | 武汉三江中电科技有限责任公司 | A kind of lightning stroke optical path monitoring system and method |
| CN111614875A (en) * | 2020-05-13 | 2020-09-01 | 深圳供电局有限公司 | Remote photography holder control system for transformer substation inspection robot |
| CN111698413A (en) * | 2019-03-13 | 2020-09-22 | 杭州海康威视数字技术股份有限公司 | Object image acquisition method and device and electronic equipment |
| CN111951237A (en) * | 2020-08-04 | 2020-11-17 | 上海微亿智造科技有限公司 | Visual appearance detection method |
| CN112396116A (en) * | 2020-11-24 | 2021-02-23 | 武汉三江中电科技有限责任公司 | Thunder and lightning detection method and device, computer equipment and readable medium |
| CN112947567A (en) * | 2021-03-02 | 2021-06-11 | 广州科腾信息技术有限公司 | Method for inspecting power transmission line by using multi-rotor unmanned aerial vehicle |
| CN113702777A (en) * | 2021-07-27 | 2021-11-26 | 广西电网有限责任公司电力科学研究院 | High-voltage equipment on-line inspection monitoring system |
| CN113796064A (en) * | 2020-06-28 | 2021-12-14 | 深圳市大疆创新科技有限公司 | Shooting control method and device, holder and shooting system |
| WO2022000300A1 (en) * | 2020-06-30 | 2022-01-06 | 深圳市大疆创新科技有限公司 | Image processing method, image acquisition apparatus, unmanned aerial vehicle, unmanned aerial vehicle system, and storage medium |
| WO2022082856A1 (en) * | 2020-10-19 | 2022-04-28 | 广东科凯达智能机器人有限公司 | Method and system for automatically identifying and tracking inspection target, and robot |
-
2022
- 2022-04-20 CN CN202210413048.XA patent/CN114827466B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011114788A (en) * | 2009-11-30 | 2011-06-09 | Sanyo Electric Co Ltd | Imaging apparatus and imaging method |
| CN101883261A (en) * | 2010-05-26 | 2010-11-10 | 中国科学院自动化研究所 | Method and system for abnormal target detection and relay tracking under large-range monitoring scene |
| CN106809710A (en) * | 2015-11-30 | 2017-06-09 | 福建省特种设备检验研究院泉州分院 | Elevator magnetic buffering protection device |
| US20190096054A1 (en) * | 2017-05-15 | 2019-03-28 | HKC Corporation Limited | Image acquiring device and method of correcting coordinates thereof |
| CN109979468A (en) * | 2019-03-05 | 2019-07-05 | 武汉三江中电科技有限责任公司 | A kind of lightning stroke optical path monitoring system and method |
| CN111698413A (en) * | 2019-03-13 | 2020-09-22 | 杭州海康威视数字技术股份有限公司 | Object image acquisition method and device and electronic equipment |
| CN111614875A (en) * | 2020-05-13 | 2020-09-01 | 深圳供电局有限公司 | Remote photography holder control system for transformer substation inspection robot |
| CN113796064A (en) * | 2020-06-28 | 2021-12-14 | 深圳市大疆创新科技有限公司 | Shooting control method and device, holder and shooting system |
| WO2022000300A1 (en) * | 2020-06-30 | 2022-01-06 | 深圳市大疆创新科技有限公司 | Image processing method, image acquisition apparatus, unmanned aerial vehicle, unmanned aerial vehicle system, and storage medium |
| CN111951237A (en) * | 2020-08-04 | 2020-11-17 | 上海微亿智造科技有限公司 | Visual appearance detection method |
| WO2022082856A1 (en) * | 2020-10-19 | 2022-04-28 | 广东科凯达智能机器人有限公司 | Method and system for automatically identifying and tracking inspection target, and robot |
| CN112396116A (en) * | 2020-11-24 | 2021-02-23 | 武汉三江中电科技有限责任公司 | Thunder and lightning detection method and device, computer equipment and readable medium |
| CN112947567A (en) * | 2021-03-02 | 2021-06-11 | 广州科腾信息技术有限公司 | Method for inspecting power transmission line by using multi-rotor unmanned aerial vehicle |
| CN113702777A (en) * | 2021-07-27 | 2021-11-26 | 广西电网有限责任公司电力科学研究院 | High-voltage equipment on-line inspection monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114827466B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846415B (en) | A kind of multichannel fisheye camera binocular calibration device and method | |
| WO2018103408A1 (en) | Aerial image capturing method and system for unmanned aerial vehicle to survey traffic accident scene | |
| CN111462304B (en) | 3D acquisition and size measurement method for space field | |
| JP6708790B2 (en) | Image generation device, image generation system, image generation method, and image generation program | |
| CN109940603B (en) | Point-of-arrival error compensation control method for inspection robot | |
| CN108574825B (en) | Method and device for adjusting pan-tilt camera | |
| CN109739239B (en) | Planning method for uninterrupted instrument recognition of inspection robot | |
| CN112425148B (en) | Imaging device, unmanned mobile object, imaging method, imaging system, and recording medium | |
| CN105184784B (en) | The method that monocular camera based on movable information obtains depth information | |
| JP5989719B2 (en) | Shallow water observation system | |
| CN112949478A (en) | Target detection method based on holder camera | |
| KR20160129779A (en) | Method for obtaining light-field data using a non-light-field imaging device, corresponding device, computer program product and non-transitory computer-readable carrier medium | |
| CN106767720A (en) | Single-lens oblique photograph measuring method, device and system based on unmanned plane | |
| CN106625673A (en) | Narrow space assembly system and assembly method | |
| CN106447735A (en) | Panoramic camera geometric calibration processing method | |
| CN206460515U (en) | A kind of multichannel fisheye camera caliberating device based on stereo calibration target | |
| CN113884519B (en) | Self-navigation X-ray imaging system and imaging method | |
| CN109584309A (en) | A kind of twin-lens emergency cloth ball-handling of rifle ball linkage | |
| CN109765747B (en) | Aerial image focus detection method, aerial image focus detection system and camera | |
| CN112585956A (en) | Track rehearsal method, system, movable platform and storage medium | |
| CN110533728A (en) | Scaling method, device and the medium of binocular stereo vision camera based on Zhang Zhengyou calibration | |
| CN108510537B (en) | 3D modeling method and device | |
| KR101175628B1 (en) | Obtaining method for 3d data | |
| CN112764052A (en) | Air defense missile flight monitoring system | |
| CN114827466A (en) | Human eye-imitated equipment image acquisition device and image acquisition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |