CN114513607A - Method, device and system for self-adjusting field range of high-temperature industrial endoscope - Google Patents
Method, device and system for self-adjusting field range of high-temperature industrial endoscope Download PDFInfo
- Publication number
- CN114513607A CN114513607A CN202210102508.7A CN202210102508A CN114513607A CN 114513607 A CN114513607 A CN 114513607A CN 202210102508 A CN202210102508 A CN 202210102508A CN 114513607 A CN114513607 A CN 114513607A
- Authority
- CN
- China
- Prior art keywords
- charge level
- image
- industrial endoscope
- lens
- distance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003384 imaging method Methods 0.000 claims abstract description 84
- 239000000463 material Substances 0.000 claims description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 16
- 210000003298 dental enamel Anatomy 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000001816 cooling Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 29
- 239000000523 sample Substances 0.000 description 13
- 238000001514 detection method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000007637 random forest analysis Methods 0.000 description 8
- 230000000007 visual effect Effects 0.000 description 6
- 239000000306 component Substances 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 239000007789 gas Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013016 damping Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 239000000112 cooling gas Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
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
- H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B17/00—Details of cameras or camera bodies; Accessories therefor
- G03B17/55—Details of cameras or camera bodies; Accessories therefor with provision for heating or cooling, e.g. in aircraft
-
- G06T5/73—
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/51—Housings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/52—Elements optimising image sensor operation, e.g. for electromagnetic interference [EMI] protection or temperature control by heat transfer or cooling elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/54—Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/55—Optical parts specially adapted for electronic image sensors; Mounting thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/555—Constructional details for picking-up images in sites, inaccessible due to their dimensions or hazardous conditions, e.g. endoscopes or borescopes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/58—Means for changing the camera field of view without moving the camera body, e.g. nutating or panning of optics or image sensors
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10068—Endoscopic image
Abstract
The invention discloses a method, a device and a system for self-adjusting a field range of a high-temperature industrial endoscope, which solve the technical problem that the field range of the existing high-temperature industrial endoscope cannot be accurately self-adjusted by acquiring a fuzzy charge level image acquired by the industrial endoscope, extracting a profile image of the fuzzy charge level image, calculating a charge level imaging area according to the profile image, acquiring the charge level height according to the charge level imaging area, acquiring a lens charge level distance according to the charge level height and adjusting the distance between the charge level and the industrial endoscope according to the lens charge level distance.
Description
Technical Field
The invention mainly relates to the technical field of blast furnace smelting, in particular to a method, a device and a system for automatically adjusting the field range of a high-temperature industrial endoscope.
Background
The industrial endoscope is used as the 'eye' of the industrial kiln, can obtain the shape and appearance images of the material surface in the industrial kiln and the running state of each part of equipment, and plays a guiding role in field operation. If the distance between the lens of the industrial endoscope and the material surface of the industrial kiln is too close, all images of the material piled in the kiln cannot be acquired; if the distance is too far, the obtained imaging area is too small, and all detail information of the stockpile image in the furnace cannot be obtained. The position of the stockpile in the industrial kiln is easy to change greatly along with the processes of material distribution and the like, so that the field range is changed, however, the conventional lens focusing method can only focus in a small range, the imaging cannot be restored to be clear, and the material surface image is finally out of focus and blurred. Incomplete image information easily makes operators misjudge the site, and influences the smooth operation of the industrial kiln. However, the problem is difficult to solve all the time, and the reason is that the industrial kiln is high-temperature sealed and is filled with toxic gases such as carbon monoxide, and workers cannot enter the kiln to adjust the distance between equipment and the charge level. Aiming at the problem, the following solutions are mainly adopted at home and abroad at present: firstly, a telescopic rod is arranged below an industrial endoscope lens, and the industrial endoscope lens is extended or contracted to a proper position and distance through the expansion and contraction of the telescopic rod, but the device is controlled by a handle, needs manual operation and control and cannot be automatically expanded and contracted; and secondly, a pulley block and a traction device are arranged in the industrial endoscope shell, and the damping of a lens operating lever is adjusted, so that the angle of the lens is adjusted, and images in different directions are detected. However, obviously, the device cannot adjust the position of the lens and cannot change the size and definition of a picture acquired by the lens; and thirdly, a propeller and a guide rail are arranged below the industrial endoscope, so that the industrial endoscope can move back and forth, but the equipment has a complex structure, is difficult to install on the inner wall of the kiln, has more wiring and low safety. Therefore, according to the method, firstly, whether the positions of the charge level and the camera in the industrial kiln are greatly changed is judged in real time by utilizing the provided video fuzzy detection algorithm; then, a developed industrial endoscope kiln charge level imaging area algorithm is utilized, a proposed kiln charge level height actual measurement model is fused, and the distance between the charge level in the current industrial kiln and a camera is accurately measured; and finally, a set of high-temperature industrial endoscope view field range self-adjusting device is developed in a matched manner, the distance between the industrial endoscope and the charge level in the furnace is intelligently and fully automatically adjusted, and the charge level video image with a proper view field size and clear image is shot by the industrial endoscope.
Patent publication No. CN107544134 patent application of invention is a telescopic bending industrial endoscope, which is designed to be nested under the industrial endoscope according to the telescopic and bending characteristics of a fishing rod and a selfie stick, so that the camera of the endoscope is extended or contracted to a proper observation position and distance. The staff utilizes the handle to control the telescopic link, and the adjustment camera lens angle finds better detection position. However, the device needs manual operation and control, cannot automatically adjust the position to enable imaging to be clear, and has no real-time performance, so the practical value is not high.
The patent publication No. CN113189767 patent application of the invention is a damping adjustment device for an industrial endoscope control lever, a base is fixed in a device shell, a control shaft sleeve is fixed on the base, a first pulley assembly and a second pulley assembly are installed on the base, and a traction device is arranged on the assemblies. The device utilizes the assembly pulley to adjust control lever damping to adapt to various detection environment. However, the device is mainly used for adjusting the steering of the industrial endoscope lens, and the distance between the lens and the material surface can be adjusted only in a small range, so that the definition and the size of a shot picture cannot be adjusted.
Patent publication No. CN213512863 utility model is a high temperature high definition industry TV propeller, and frame inner wall one side sliding connection has the slider, and slider middle part fixed mounting has the industry TV, and frame top mid-mounting has the guide rail, and guide rail inner wall mid-connection has the movable block, and the movable block top is connected with the connecting plate, and the concave plate has been cup jointed at connecting plate surface top. The device is reasonable in structure and can push the industrial television to move back and forth. However, the device has a complex structure, a plurality of connecting wires, is inconvenient to install on the inner wall of the arc-shaped industrial kiln and has higher installation cost.
Disclosure of Invention
The invention provides a self-adjusting method and a self-adjusting system for the field range of a high-temperature industrial endoscope, which solve the technical problem that the field range of the existing high-temperature industrial endoscope cannot be accurately self-adjusted.
In order to solve the technical problem, the self-adjusting method for the field range of the high-temperature industrial endoscope comprises the following steps:
acquiring a fuzzy charge level image acquired by an industrial endoscope;
extracting a contour image of the fuzzy charge level image, and calculating the charge level imaging area according to the contour image;
acquiring the height of the charge level according to the charge level imaging area;
acquiring the distance between the lens charge levels according to the charge level height;
and adjusting the distance between the material level and the industrial endoscope according to the distance between the lens material level.
Further, acquiring the blurred charge level image acquired by the industrial endoscope comprises the following steps:
extracting a video key frame of a charge level image acquired by an industrial endoscope;
carrying out gray level processing on the video key frame to obtain a charge level gray level image;
calculating the definition evaluation value of the material surface gray level image by adopting a Tenengrad evaluation function;
and acquiring a fuzzy charge level image according to the definition evaluation value and a preset definition evaluation threshold value.
Further, extracting the video key frame of the charge level image collected by the industrial endoscope comprises:
extracting image definition characteristics, wherein the image definition characteristics comprise edge intensity, normalized brightness value and noise quantity;
and training a classifier according to the image definition characteristics, and classifying the charge level image acquired by the industrial endoscope according to the trained classifier so as to obtain a video key frame of the charge level image.
Further, calculating the imaging area of the charge level according to the contour image comprises:
performing wavelet decomposition and single-branch reconstruction on the contour image to obtain a high-frequency image and a low-frequency image;
using two mask operators of different orders to respectively detect the edges of the high-frequency image and the low-frequency image to obtain a high-frequency edge image and a low-frequency edge image;
carrying out weighted fusion on the high-frequency edge image and the low-frequency edge image to obtain a fused charge level profile;
and calculating the charge level imaging area according to the fused charge level profile.
Further, according to the charge level imaging area, acquiring the charge level height comprises:
establishing an endoscope view field conical equation by using a parallel latitude circle method;
acquiring an angle of view imaging ellipse equation corresponding to the height of the charge level based on an endoscope field cone equation;
establishing a charge level height model according to the view angle image-taking elliptic equation and a cross section circular equation corresponding to the furnace wall of the blast furnace;
and obtaining the height of the charge level according to the charge level imaging area and the charge level height model.
Further, establishing an endoscope field of view cone equation by using a parallel latitude circle method comprises:
selecting a bus AB of an industrial endoscope view field cone to rotate around a rotating shaft DA for a circle, wherein an end point A in the rotating shaft DA is an end point of the industrial endoscope, a D is an intersection point of the industrial endoscope and an industrial kiln, and obtaining a view field cone equation by using a parallel latitude circle method, wherein the specific calculation formula is as follows:
(x-xA)2+(y-yA)2+(z-zA)2＝C0g2(x,y,z)g-2(xB,yB,zB)
g(x,y,z)＝([xA,yA,zA]T-[x,y,z]T)T([xA,yA,zA]T-[xD,yD,zD]T)，
C0＝|AB|2＝(xA-xB)2+(yA-yB)2+(zA-zB)2
wherein (x, y, z) is the space coordinate of any point in the industrial endoscope view field cone, (x)A,yA,zA) And (x)B,yB,zB) The spatial coordinates of the end points A and B of the bus AB, respectively, (x)D,yD,zD) Is the spatial coordinate of the end point D of the rotation axis DA, | AB | is the length of the bus AB [ ·]TRepresenting a transpose operation.
Further, the specific calculation formula of the charge level height model is as follows:
wherein S is the charge level imaging area, xR1And xR3Coordinate value in x direction of intersection point of imaging ellipse and cross-section circle corresponding to view angle imaging ellipse equation, yR1And yR3Is a coordinate value of the intersection point in the y direction, R is the radius of the cross-sectional circle, (x)B,yB,zB) Is the spatial coordinate of endpoint B of bus AB, and:
g(xB,yB,zB)＝([xA,yA,zA]T-[xB,yB,zB]T)T([xA,yA,zA]T-[xD,yD,zD]T)，C1、C2、C3、C4、C5and C6The specific calculation formula is as follows:
wherein (x)A,yA,zA) And (x)B,yB,zB) The spatial coordinates of the end points A and B of the bus AB, respectively, (x)D,yD,zD) Is the spatial coordinate of the end point D of the rotation axis DA, q is the level heightAnd (4) degree.
The invention provides a high-temperature industrial endoscope field range self-adjusting device, which comprises: shell module, lens module, camera lens charge level interval obtain module and visual field range self-adjusting module, wherein:
the outer shell module comprises an outer layer unit and an inner layer unit, and the inner layer unit comprises an enamel sleeved on the industrial endoscope and a mirror rod arranged in the enamel;
the lens module is arranged in the inner layer unit and used for collecting a charge level image;
the camera lens charge level interval obtains the module for obtain camera lens charge level interval, and camera lens charge level interval obtains the module and includes:
the fuzzy charge level image acquisition unit is used for acquiring a fuzzy charge level image acquired by an industrial endoscope;
the charge level imaging area calculating unit is used for extracting a contour image of the fuzzy charge level image and calculating the charge level imaging area according to the contour image;
the charge level height acquisition unit is used for acquiring the charge level height according to the charge level imaging area;
the distance acquisition unit is used for acquiring the lens charge level distance according to the charge level height;
the view field range self-adjusting module is used for adjusting the distance between the material level and the industrial endoscope according to the distance between the lens material level, and comprises a motor, a gear arranged on a rotating shaft of the motor, a first thread vertically meshed with the gear and a second thread matched with the first thread, wherein the first thread is arranged on the mirror rod, and the second thread is arranged on the enamel.
Furthermore, the high-temperature industrial endoscope field range self-adjusting device further comprises a cooling module, and the cooling module comprises a water inlet and a water outlet of a circulation cold water loop arranged on the outer layer unit and a gas inlet for accessing air cooling gas.
The invention provides a high-temperature industrial endoscope field range self-adjusting system, which comprises:
the device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the steps of the high-temperature industrial endoscope visual field range self-adjusting method provided by the invention when executing the computer program.
Compared with the prior art, the invention has the advantages that:
the invention provides a method, a device and a system for self-adjusting a field range of a high-temperature industrial endoscope, which are used for acquiring a fuzzy charge level image acquired by the industrial endoscope, extracting a profile image of the fuzzy charge level image, calculating a charge level imaging area according to the profile image, acquiring a charge level height according to the charge level imaging area, acquiring a lens charge level distance according to the charge level height and adjusting the distance between the charge level and the industrial endoscope according to the lens charge level distance, solving the technical problem that the field range of the existing high-temperature industrial endoscope cannot be accurately self-adjusted.
The purpose of the invention is as follows:
the invention aims to provide a video fuzzy detection algorithm, which comprises the steps of constructing a key frame classifier to extract a video key frame image, carrying out gray processing on the image, and finally evaluating the definition of the image by using a Tenengrad function to judge whether the video image is fuzzy.
The invention aims to provide a charge level imaging area calculation algorithm, which utilizes a fractional order mask operator to extract the edge profile of a fuzzy charge level image so as to calculate the imaging area of the charge level of an industrial kiln.
The invention aims to establish an industrial kiln charge level height model, construct an industrial kiln charge level view angle image capture elliptic equation, calculate the charge level height through the charge level imaging area, obtain the distance between a lens and the charge level, compare the distance with the preset distance of the lens charge level, and further judge whether the distance between the lens and the charge level is proper.
The invention aims to develop a high-temperature industrial endoscope visual field range self-adjusting device, which determines the forward rotation or the reverse rotation of a motor by judging the distance between a lens and a charge level after detecting the fuzzy video image, a gear on the motor is vertically meshed with a thread on a rod of an industrial endoscope, the rod and an enamel are internally provided with mutually matched threads, and the gear drives the lens to rotate and move, so that the distance between the lens and the charge level is adjusted.
The key points of the embodiment of the invention comprise:
(1) in the aspect of a mechanical structure, a gear is arranged on a rotating shaft of a motor, the gear is vertically meshed with threads on a mirror rod, matched threads are arranged in an enamel shell, and the rotating shaft is driven by the motor to rotate so as to drive a lens to move back and forth;
(2) in the aspect of a video fuzzy detection algorithm, firstly, a key frame classifier is constructed, the accuracy of a test set evaluation classifier is formed, video key frames are automatically extracted, video information is converted into images, the key frame images are subjected to graying processing, and the definition of the images is evaluated by a Tenengrad function after the processing;
(3) in the aspect of a charge level imaging area calculation algorithm, a fractional order mask operator is adopted to extract the charge level profile of a fuzzy image, so that the imaging area of the charge level is calculated;
(4) in the aspect of judging the distance between the lens and the charge level, establishing a charge level height model, constructing a charge level view angle image-capturing elliptic equation, calculating the charge level height through an imaging area, obtaining the distance between the lens and the charge level and comparing the distance with a preset distance so as to judge whether the distance between the lens and the charge level is too far or too close;
(5) in the aspect of judging the distance between the lens and the charge level, establishing a charge level height model, constructing a charge level view angle image-capturing elliptic equation, calculating the charge level height through an imaging area, obtaining the distance between the lens and the charge level and comparing the distance with a preset distance so as to judge whether the distance between the lens and the charge level is too far or too close;
(6) in the aspect of general design thought, in order to solve the problem that the distance between a lens and a charge level of an industrial endoscope is improper, so that the video image is blurred and the imaging area is large, whether the video is blurred is detected by using a video blurring algorithm, the charge level imaging area of the blurred image is obtained by using a charge level imaging area calculation algorithm, the distance between the lens and the charge level is calculated by using a charge level height model, the lens and the charge level are judged to be too far or too close, the motor is controlled to rotate to change the distance between the lens and the charge level, and finally the focal length of the lens is adjusted by using a self-focusing algorithm, so that the video image is clear and the imaging area is proper.
Drawings
FIG. 1 is a flowchart of a video blur detection algorithm according to a second embodiment of the present invention;
FIG. 2 is a schematic view of a cone of view of an endoscope in accordance with a second embodiment of the present invention;
FIG. 3 is a schematic view of an imaging area of an industrial endoscope according to a second embodiment of the present invention;
FIG. 4 is a flowchart of a high temperature industrial endoscope field of view self-adjusting method according to a second embodiment of the present invention;
FIG. 5 is a main body diagram of a high-temperature industrial endoscope field range self-adjusting device according to a third embodiment of the invention;
fig. 6 is a schematic structural diagram of a field range self-adjusting module according to a third embodiment of the present invention;
fig. 7 is a mechanical structure operation flow chart of a visual field range self-adjusting module according to a third embodiment of the present invention;
FIG. 8 is a block diagram of a high temperature industrial endoscope field of view self-adjusting system according to an embodiment of the present invention.
Reference numerals:
10. a memory; 20. a processor; m1, housing; m2, optical lens; m3, air inlet; m4, a water outlet; m5, a water inlet; m6, enamel shell; m7, mirror bar; m8, second thread; m9, first thread; m10, gear; m11, motor.
Detailed Description
In order to facilitate an understanding of the invention, the invention will be described more fully and in detail below with reference to the accompanying drawings and preferred embodiments, but the scope of the invention is not limited to the specific embodiments below.
Embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
Example one
The embodiment of the invention provides a self-adjusting method for the field range of a high-temperature industrial endoscope, which comprises the following steps:
s101, acquiring a fuzzy charge level image acquired by an industrial endoscope;
step S102, extracting a contour image of the fuzzy charge level image, and calculating the charge level imaging area according to the contour image;
step S103, acquiring the height of the charge level according to the charge level imaging area;
step S104, acquiring the distance between the lens charge levels according to the charge level height;
and step S105, adjusting the distance between the charge level and the industrial endoscope according to the distance between the lens charge level.
The method for self-adjusting the field range of the high-temperature industrial endoscope comprises the steps of acquiring a fuzzy charge level image acquired by the industrial endoscope, extracting a profile image of the fuzzy charge level image, calculating a charge level imaging area according to the profile image, acquiring a charge level height according to the charge level imaging area, acquiring a lens charge level distance according to the charge level height and adjusting the distance between the charge level and the industrial endoscope according to the lens charge level distance, so that the technical problem that the field range of the existing high-temperature industrial endoscope cannot be accurately self-adjusted is solved, and the distance between the industrial endoscope and the charge level in a furnace is intelligently adjusted by accurately measuring the lens charge level distance, so that the industrial endoscope shoots a charge level video image with a proper field size and clear image.
Example two
The self-adjusting method for the field range of the high-temperature industrial endoscope provided by the embodiment of the invention comprises the following steps:
step S201, acquiring a fuzzy charge level image acquired by an industrial endoscope.
Specifically, the embodiment of the invention firstly judges whether the video acquired by the industrial endoscope is fuzzy or not through a video fuzzy detection algorithm.
Referring to fig. 1, in the video blur detection algorithm according to the embodiment of the present invention, a video key frame image is extracted first, then a graying process is performed on the video key frame image, and finally image quality is evaluated. The method comprises the following specific steps:
step 1: video key frame extraction algorithm U0
If the quality of the whole monitoring video is evaluated, the calculated amount is large, and the real-time performance is poor, so that the key frame image in the video is extracted and the image is analyzed. The key frame extraction main thought is as follows: firstly, candidate key frames are selected, a candidate key frame data set is formed by judging feature extraction, a training set and a testing set are further generated, a key frame classifier is established, and finally, the key frames are accurately output. The key frame classifier is constructed as follows:
the classifier for constructing the image key frame is used for screening out good-quality and useful images, so that a corresponding data set is needed for training the classifier, and in order to construct the data set, a characteristic selection quantitative evaluation image is needed to construct a data set needed by training the classifier; the embodiment further provides an algorithm of the classifier, so that a high-precision classifier algorithm is realized, and key frames are quickly extracted from a large number of video frames.
a) Feature selection
The target feature represents the nature of the image, and an important task in image analysis is to derive a quantified value of the target feature from the image. Regarding the gray level characteristics of the image, regarding the gray level characteristics of the color, the edge intensity, the normalized brightness value and the noise amount are taken as the image definition characteristics. The edge strength can reflect the image definition, the image definition is defined as follows based on a Laplacian gradient function, the numerical value is larger and clearer:
D(f)＝∑y∑x|G(x,y)| (1)
where G (x, y) is the convolution of the Laplacian at the pixel point (x, y).
And normalizing the brightness value, namely defining the uniform brightness of the image as the sum of the number of pixels exceeding a high brightness threshold and a low brightness threshold, and superposing to obtain the uniform brightness distribution of the image, wherein the high brightness threshold value of the embodiment is 180, and the low brightness threshold value is 50.
b) Classifier algorithm
The random forest is a classifier which comprises a plurality of decision trees and adopts a random sampling mode. When the samples are input into the random forest classifier, the samples need to be input into each tree for classification, an output result is determined by adopting a multi-decision tree voting mechanism, and classification results of a plurality of weak classifiers can be selected, so that a strong classifier is formed. N observed values exist in the dependent variable y in the random forest, and j independent variables are related to the n observed values; when constructing the classification tree, the random forest can randomly select n observation values from the original data, wherein some observation values are selected for multiple times, and other observation values are not selected, namely, bootstrap resampling. Meanwhile, the random forest randomly selects k independent variable partial variables to determine tree nodes, and n training sets are generated. And the final result is obtained by adopting a majority voting mechanism.
The present invention contemplates the use of gini coefficients to judge the selection of split branches, which is a measure of the purity of a sample set, represented by equation (3).
Wherein, PiIs the ratio of the factors in the total required sample purity of the samples that each sample needs to occupy in sample class i. If the coefficient of the gini class of samples at a leaf node is much greater than the value δ of the current set sample threshold, then a sample split set at the current leaf node cannot achieve all of the necessary sample purities simultaneously, or is considered to be a potentially confusing sample split set, and it may be necessary to continue sample splitting for the current leaf node.
The threshold δ is determined by the mixed sample ratio α, which is the largest number of samples in the leaf node, as expressed by equation (4). The samples stored on a leaf node are of k types relative to the samples stored on an alpha leaf node, wherein the number of one sample is maximum LmThe ratio of the total number of samples is pmThe rest of sample PiN is not LmThe relative proportion of the labeled samples is α, and the leaf node splitting threshold parameter is:
the basic steps of single tree construction are as follows:
step1, beginning, regarding all records as a node;
step2, traversing all the segmentation modes, searching an optimal segmentation point, and dividing the optimal segmentation point into two nodes N1And N2；
Step3, for N1And N2And respectively continuing to execute the steps 2-3 until the purity of each node exceeds the threshold delta.
d) General algorithm flow
The overall flow of key frame extraction is as follows:
step1, acquiring a video frame of a charge level image;
step2, evaluating the edge strength of each frame of image, and recording a corresponding evaluation value;
step3, evaluating the normalized brightness value of each frame image, and recording a corresponding evaluation value;
step 4, marking the generated image and data, namely marking out the key frame to generate a training set and a test set;
step 6, evaluating the accuracy of the trained classifier by using the test set;
step 7, changing the setting parameters of the random forest classifier algorithm, and circulating the step 6 and the step 7 until the accuracy of the classifier meets the requirement;
and 8, finishing the construction of the key frame classifier, and automatically extracting the key frames from the video.
Step 2: image graying processing U1
The image is composed of a matrix of pixel points of three components of RGB, namely three primary colors of red, green and blue to represent that the true color range is generally from 0 to 255, white is 255 and black is 0. The gray level is the degree of color shading, and the obtained key frame image is grayed, i.e. RGB is equalized to obtain the gray level, and here, the weighted average method is adopted to perform weighted average on the three components with different weights. Because human eyes have highest sensitivity to green and lowest sensitivity to blue, a reasonable gray image can be obtained by carrying out weighted average on RGB three components according to the following formula.
Gray(i,j)＝0.299×R(i,j)+0.578×G(i,j)+0.114×B(i,j) (5)
Step 3: image sharpness evaluation U2
The Tenengrad function is a gradient-based image sharpness evaluation function. In image processing, it is generally believed that the in-focus image has sharper edges and therefore larger gradient function values. The Tenengrad function extracts the gradient values in the horizontal and vertical directions using Sobel operators. The larger the average gray value of the image processed by the Sobel operator is, the clearer the image is represented.
The specific process is as follows:
let Sobel convolution kernel be Gx，GyThen the gradient of image I at point (x, y):
the Tenengrad value for this image is defined as:
where n is the total number of pixels in the image.
The Sobel operator used here is:
and then setting a threshold, judging that the image is fuzzy when the calculated image Ten value is smaller than the threshold, judging that the lens is far away from or close to the charge level according to a subsequent algorithm, starting a motor, performing forward rotation or reverse rotation once, and adjusting the distance between the lens and the charge level.
And S202, extracting a contour image of the fuzzy charge level image, and calculating the charge level imaging area according to the contour image.
Specifically, according to the algorithm of the charge level imaging area, the charge level profile is extracted by adopting a fractional operator, so that the charge level imaging area is obtained through calculation. The differential expression of the fractional order differential operator in the x direction is as follows:
the differential expression in the y-direction is:
and further constructing a 3 × 3 mask operator acting on each direction of the image:
the specific process is as follows:
(1) performing wavelet decomposition and single-branch reconstruction on the image to obtain a high-frequency image and a low-frequency image;
(2) the edges of the high and low frequency images are detected using two mask operators of different orders, respectively. Obtaining the complete and continuous edge of the high-frequency image, and reserving the texture details of the low-frequency image;
(3) carrying out weighted fusion on the two edge images to obtain the profile of the charge level;
(4) and finally, calculating the area contained by the contour through the contour of the charge level, namely the imaging area of the charge level in the video image.
And S203, acquiring the charge level height according to the charge level imaging area, and acquiring the lens charge level distance according to the charge level height.
Specifically, the distance between the lens of the industrial endoscope and the charge level of the industrial kiln is closely related to the imaging area of the charge level. The imaging area is finally determined by the imaging ellipse of the endoscope, so that the cone equation of the field of view of the endoscope needs to be calculated first, and then the imaging ellipse equation of the field angle needs to be calculated.
The endoscope view cone equation can be regarded as that the generatrix AB of the view cone a-BO' C rotates once around the rotation axis DA, as shown in fig. 2, a spatial rectangular coordinate system is established with OX as an x-axis, OY as a y-axis, and OZ as a z-axis. Wherein OZ is the central line of the industrial kiln, WOYX is the standard stockline stock level, DA is the rotating shaft, the end point A in the rotating shaft DA is the end point of the industrial endoscope, D is the intersection point of the industrial endoscope and the industrial kiln, and the view cone A-BO 'C is the specific range of the angle of view of the DA of the industrial endoscope, wherein D, A, O' three points are collinear; and the points C and Y are actually one point, and in fig. 2, for the sake of distinction, no overlapping processing is performed, and the straight line DAO' intersects with the diameter WY of the surface WOYX standard strand level, that is, the industrial endoscope moves only on the surface ZWOY in the vertical direction.
In this embodiment, a field-of-view conic equation is obtained by using a parallel latitude circle method, which specifically includes:
let M1(x1,y1,z1) At a point on the bus AB, then pass M1(x1,y1,z1) The weft circle equation of (a) is:
due to M1On the bus AB, the AB equation is satisfied:
eliminating x by a series of calculations1,y1,z1Obtaining a view field conic equation:
(x-xA)2+(y-yA)2+(z-zA)2＝C0g2(x,y,z)g-2(xB,yB,zB) (16)
wherein:
g(x,y,z)＝([xA,yA,zA]T-[x,y,z]T)T([xA,yA,zA]T-[xD,yD,zD]T),
C0＝|AB|2＝(xA-xB)2+(yA-yB)2+(zA-zB)2,
the height q of the charge level is the distance from the charge level of the industrial kiln to the charge level of the standard charge line, and q belongs to [0,2] m. The charge level plane equation is:
z＝q (17)
then, the final field angle imaging ellipse equation obtained from equations (16) and (17) is:
(x-xA)2+(y-yA)2+(q-zA)2＝C0g2(x,y,q)g-2(xB,yB,zB) (18)
therefore, the field angle imaging ellipse equation obtained from equation (18) is only related to A (x)A,yA,yA)、B(xB,yB,yB)、D(xD,yD,yD) The coordinates of the points are related, and the imaging area of the industrial endoscope is the middle part of a section circle formed by an image-taking ellipse and the wall of the blast furnace on a two-dimensional plane, as shown in figure 3.
Formula (18) can be solved as:
wherein:
since the equation for the cross-sectional circle is:
x2+y2＝R2 (20)
according to the formulas (19) and (20), the imaging area is integrated to obtain an equation of the imaging area S and the charge level height q:
wherein R is1、R2、R3、R4Is the intersection point of the ellipse and the cross-sectional circle, R1And R2Abscissa of equal, R3And R4The abscissa is equal, S is the charge level imaging area, xR1And xR3Coordinate value in x direction of intersection point of imaging ellipse and cross-section circle corresponding to view angle imaging ellipse equation, yR1And yR3Is a coordinate value of the intersection point in the y direction, R is the radius of the cross-sectional circle, (x)B,yB,zB) Is the spatial coordinate of end point B of the bus AB, and C1、C2、C3、C4、C5And C6Is the height coefficient of the charge level, g (x)B,yB,zB)＝([xA,yA,zA]T-[xB,yB,zB]T)T([xA,yA,zA]T-[xD,yD,zD]T)。
And substituting the imaging area S to obtain the charge level height q, wherein the charge level height gradually increases along with the reduction of the imaging area, and the distance between the charge level of the industrial kiln and the industrial endoscope is closer and closer. The lens charge level distance s can be obtained through the charge level height q and the lens mounting data, and the specific calculation formula is as follows:
s＝zA-q (22)
after the distance between the lens charge level is obtained, the present embodiment compares the distance between the lens charge level and the preset lens charge level, and thus can determine whether the distance between the charge level and the industrial endoscope is too far or too close.
It is easy to see that the embodiment of the invention firstly proposes that a view field conical equation is established by adopting a latitude circular equation, so that a view field angle image-taking elliptic equation which accurately represents a charge level image is obtained, and an accurate charge level height model is established according to the view field angle image-taking elliptic equation and a cross section circular equation corresponding to the furnace wall of a blast furnace, so that the accurate charge level height is obtained, the lens charge level distance is obtained, and a foundation is laid for realizing accurate self-adjustment of the subsequent high-temperature industrial endoscope view field range.
And step S204, adjusting the distance between the material level and the industrial endoscope according to the distance between the lens material level.
Specifically, the embodiment of the invention calculates the deviation between the lens material surface distance and the preset distance threshold value, and controls the industrial endoscope to move to the preset distance threshold value according to the deviation.
The method for self-adjusting the field range of the high-temperature industrial endoscope comprises the steps of acquiring a fuzzy charge level image acquired by the industrial endoscope, extracting a profile image of the fuzzy charge level image, calculating a charge level imaging area according to the profile image, acquiring a charge level height according to the charge level imaging area, acquiring a lens charge level distance according to the charge level height and adjusting the distance between the charge level and the industrial endoscope according to the lens charge level distance, so that the technical problem that the field range of the existing high-temperature industrial endoscope cannot be accurately self-adjusted is solved, and the distance between the industrial endoscope and the charge level in a furnace is intelligently adjusted by accurately measuring the lens charge level distance, so that the industrial endoscope shoots a charge level video image with a proper field size and clear image.
The flow chart of the method for realizing the self-adjustment of the field range of the high-temperature industrial endoscope in the embodiment of the invention can be specifically referred to fig. 4, and the method specifically comprises the following steps:
(1) water and gas are respectively introduced into the water inlet M5 and the gas inlet M3 and circularly flow, so that the normal work of the whole equipment in the industrial kiln is ensured;
(2) s0: constructing a key frame classifier by a video fuzzy detection algorithm, extracting a key frame image, performing graying processing on the key frame image, calculating an image parameter by using a Tenengrad function, and judging video fuzziness if the image parameter is smaller than a threshold value;
(3) s1: after the image is judged to be fuzzy, extracting the charge level profile of the fuzzy image by using a charge level imaging area calculation algorithm, and calculating the charge level imaging area;
(4) s2: establishing a charge level height model, constructing an ellipse equation of the field angle of the charge level of the industrial kiln, calculating the charge level height through an imaging area, acquiring the distance between a lens and the charge level, comparing the distance with a preset distance, and judging whether the distance between the lens and the charge level is short or long;
(5) s3: if the distance is too far, the motor M11 rotates forwards, the lens moves forwards, the distance between the lens and the charge level is equal to the preset distance, and if the distance is too far, the motor rotates backwards;
(6) s4: adjusting the focal length of the lens by using a lens self-focusing algorithm to enable the image to be clear;
(7) the steps S0 to S4 are repeated after the video blur is detected again.
EXAMPLE III
Referring to fig. 5, the high-temperature industrial endoscope viewing field range self-adjusting device according to the embodiment of the present invention is composed of a housing module, a lens level distance acquiring module, a viewing field range self-adjusting module, and a cooling module, wherein the lens level distance acquiring module includes a blurred level image acquiring unit, a level imaging area calculating unit, a level height acquiring unit, and a distance acquiring unit. The specific working process is as follows: firstly, detecting that the video shot by an industrial endoscope is fuzzy through a video fuzzy detection algorithm; extracting a fuzzy image contour by using a charge level imaging area calculation algorithm, and calculating the charge level imaging area; then constructing a material level height model of the industrial kiln, constructing a view field imaging cone equation, obtaining the material level height through an imaging area, calculating the distance between a lens and the material level of the industrial kiln, comparing the distance with the preset distance between the lens and the material level, and further judging whether the lens is too far away from the material level or too close to the material level; the operation of a motor is controlled, a gear on the motor rotates, the gear is vertically meshed with a thread on a rod of an industrial endoscope, the rod and the enamel are internally provided with mutually matched threads, and the gear drives the industrial endoscope to rotate and move back and forth to a preset distance; and adjusting the focal length of the lens by using a lens self-focusing algorithm to shoot a clear image with proper size. Hereinafter, each of the components constituting the apparatus will be specifically described
The outer shell module of the embodiment of the invention adopts high-temperature resistant steel as a main material, and comprises a two-layer structure, wherein an inner layer unit comprises an enamel shell M6 sleeved on an industrial endoscope and a mirror rod M7 arranged in the enamel. The outer shell M1 of the outer layer unit is provided with an air inlet M3, and a water-cooled water inlet M5 and a water outlet M4. The front end of the shell is an imaging probe of the device and is used for imaging of the device.
The lens module is composed of different types of optical lenses M2, images of the material distribution process are collected in the industrial kiln, and then the images are transmitted to a computer through optical equipment, so that field workers can conveniently confirm the conditions of each device and material distribution in the industrial kiln.
The device adopts two devices of water cooling and air cooling, and ensures that the equipment can well run in the high-temperature dusty environment in the industrial kiln. Water enters the channel from a water inlet M5 shown in figure 5, flows in a spiral pipeline inside the shell, and flows out from a water outlet M4, so that the equipment is protected from being cooled. The air-cooled gas is blown into the shell from the air inlet M3 to generate strong air pressure, so that dust is prevented from entering the shell, and the lens of the endoscope is protected.
The lens charge level distance acquisition module comprises a fuzzy charge level image acquisition unit, a charge level imaging area calculation unit, a charge level height acquisition unit and a distance acquisition unit. The specific process and principle of the lens charge level distance obtaining module for obtaining the lens charge level distance can refer to the specific steps and method for obtaining the lens charge level distance in the high-temperature industrial endoscope view field range self-adjusting method in the second embodiment.
The self-adjusting module of the field of view range of the embodiment of the invention is a core component, and as shown in fig. 6, a mirror rod M7 of the industrial endoscope of the device is provided with a first thread M8, and an enamel shell M6 is internally provided with a second thread M9 which is matched. A gear M10 is fixed on the rotating shaft of the rear motor M11 and is vertically meshed with the first thread. Referring to fig. 7, when the lens is detected to be too far away from the material surface, the motor rotates positively, the gear rotates to drive the mirror rod to rotate to enter the enamel shell, and the industrial endoscope moves forwards to enable the distance between the lens material surfaces to be equal to the preset distance; when the lens is detected to be too close, the motor rotates reversely to move the lens backwards. Finally, the focal length of the lens is adjusted through a general lens self-focusing algorithm, so that the lens can clearly image.
According to the high-temperature industrial endoscope visual field range self-adjusting device provided by the embodiment of the invention, the fuzzy charge level image acquired by the industrial endoscope is acquired, the profile image of the fuzzy charge level image is extracted, the charge level imaging area is calculated according to the profile image, the charge level height is acquired according to the charge level imaging area, the lens charge level distance is acquired according to the charge level height, and the distance between the charge level and the industrial endoscope is adjusted according to the lens charge level distance, so that the technical problem that the visual field range of the existing high-temperature industrial endoscope cannot be accurately self-adjusted is solved.
Referring to fig. 8, the high temperature industrial endoscope field range self-adjusting system according to the embodiment of the present invention includes:
a memory 10, a processor 20 and a computer program stored on the memory 10 and executable on the processor 20, wherein the processor 20 when executing the computer program realizes the steps of the high temperature industrial endoscope field of view range self-adjusting method proposed by the present embodiment.
The specific working process and working principle of the high-temperature industrial endoscope viewing field range self-adjusting system in this embodiment can refer to the working process and working principle of the high-temperature industrial endoscope viewing field range self-adjusting method in this embodiment.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A self-adjusting method for the field range of a high-temperature industrial endoscope is characterized by comprising the following steps:
acquiring a fuzzy charge level image acquired by an industrial endoscope;
extracting a contour image of the fuzzy charge level image, and calculating the charge level imaging area according to the contour image;
acquiring the height of the charge level according to the charge level imaging area;
acquiring the distance between the lens charge levels according to the charge level height;
and adjusting the distance between the material level and the industrial endoscope according to the distance between the lens material level.
2. The high temperature industrial endoscope field of view range self-adjusting method of claim 1, wherein acquiring the blurred level image captured by the industrial endoscope comprises:
extracting a video key frame of a charge level image acquired by an industrial endoscope;
carrying out gray level processing on the video key frame to obtain a charge level gray level image;
calculating the definition evaluation value of the material surface gray level image by adopting a Tenengrad evaluation function;
and acquiring a fuzzy charge level image according to the definition evaluation value and a preset definition evaluation threshold value.
3. The high temperature industrial endoscope field of view range self-adjusting method of claim 2, wherein extracting video key frames of the level image captured by the industrial endoscope comprises:
extracting image definition characteristics, wherein the image definition characteristics comprise edge intensity, normalized brightness value and noise quantity;
and training a classifier according to the image definition characteristics, and classifying the charge level image acquired by the industrial endoscope according to the trained classifier so as to obtain a video key frame of the charge level image.
4. The high temperature industrial endoscope field of view range self-adjusting method of claim 1, wherein calculating a charge level imaging area from the profile image comprises:
performing wavelet decomposition and single-branch reconstruction on the contour image to obtain a high-frequency image and a low-frequency image;
using two mask operators of different orders to respectively detect the edges of the high-frequency image and the low-frequency image to obtain a high-frequency edge image and a low-frequency edge image;
carrying out weighted fusion on the high-frequency edge image and the low-frequency edge image to obtain a fused charge level profile;
and calculating the charge level imaging area according to the fused charge level profile.
5. A high temperature industrial endoscope field of view range self-adjusting method according to any of claims 1-4 and characterized in that obtaining level height based on level imaging area comprises:
establishing an endoscope view field conical equation by using a parallel latitude circle method;
acquiring an angle of view imaging ellipse equation corresponding to the height of the charge level based on an endoscope field cone equation;
establishing a charge level height model according to the view angle image-taking elliptic equation and a cross section circular equation corresponding to the furnace wall of the blast furnace;
and obtaining the height of the charge level according to the charge level imaging area and the charge level height model.
6. The high temperature industrial endoscope field of view range self-adjusting method of claim 5, wherein establishing the endoscope field of view cone equation using parallel latitude circle method comprises:
selecting a bus AB of an industrial endoscope view field cone to rotate around a rotating shaft DA for a circle, wherein an end point A in the rotating shaft DA is an end point of the industrial endoscope, a D is an intersection point of the industrial endoscope and an industrial kiln, and obtaining a view field cone equation by using a parallel latitude circle method, wherein the specific calculation formula is as follows:
wherein (x, y, z) is the space coordinate of any point in the industrial endoscope view field cone, (x)A,yA,zA) And (x)B,yB,zB) The spatial coordinates of the end points A and B of the bus AB, respectively, (x)D,yD,zD) Is the spatial coordinate of the end point D of the rotation axis DA, | AB | is the length of the bus AB [ ·]TRepresenting a transpose operation.
7. The high temperature industrial endoscope viewing field range self-adjusting method according to claim 6, characterized in that the specific calculation formula of the level height model is:
wherein S is the charge level imaging area, xR1And xR3The coordinate value in the x direction of the intersection point of the imaging ellipse corresponding to the view angle imaging ellipse equation and the cross-section circle,
and
is a coordinate value of the intersection point in the y direction, R is the radius of the cross-sectional circle, (x)B,yB,zB) Is the spatial coordinate of endpoint B of bus AB, and:
g(xB,yB,zB)＝([xA,yA,zA]T-[xB,yB,zB]T)T([xA,yA,zA]T-[xD,yD,zD]T)，C1、C2、C3、C4、C5and C6The specific calculation formula is as follows:
wherein (x)A,yA,zA) And (x)B,yB,zB) The spatial coordinates of the end points A and B of the bus AB, respectively, (x)D,yD,zD) Is the spatial coordinate of the end point D of the rotating shaft DA, and q is the level height.
8. A high temperature industrial endoscope viewing field range self-adjusting device for implementing the high temperature industrial endoscope viewing field range self-adjusting method according to any one of claims 1-7, wherein the high temperature industrial endoscope viewing field range self-adjusting device comprises a housing module, a lens level distance acquisition module and a viewing field range self-adjusting module, wherein:
the outer shell module comprises an outer layer unit and an inner layer unit, and the inner layer unit comprises an enamel sleeved on the industrial endoscope and a mirror rod arranged in the enamel;
the lens module is arranged in the inner layer unit and used for collecting a charge level image;
the camera lens charge level interval obtains the module for obtain camera lens charge level interval, and camera lens charge level interval obtains the module and includes:
the fuzzy charge level image acquisition unit is used for acquiring a fuzzy charge level image acquired by an industrial endoscope;
the charge level imaging area calculating unit is used for extracting a contour image of the fuzzy charge level image and calculating the charge level imaging area according to the contour image;
the charge level height acquisition unit is used for acquiring the charge level height according to the charge level imaging area;
the distance acquisition unit is used for acquiring the lens charge level distance according to the charge level height;
the view field range self-adjusting module is used for adjusting the distance between the material level and the industrial endoscope according to the distance between the lens material level, and comprises a motor, a gear arranged on a rotating shaft of the motor, a first thread vertically meshed with the gear and a second thread matched with the first thread, wherein the first thread is arranged on the mirror rod, and the second thread is arranged on the enamel.
9. The high temperature industrial endoscope viewing field range self-adjusting device according to claim 8, characterized in that the high temperature industrial endoscope viewing field range self-adjusting device further comprises a cooling module, and the cooling module comprises a water inlet and a water outlet of a circulating cold water loop arranged on the outer layer unit and a gas inlet for accessing air-cooled gas.
10. A high temperature industrial endoscope field of view range self-adjusting system, the system comprising:
memory (10), processor (20) and a computer program stored on the memory (10) and executable on the processor (20), characterized in that the steps of the method of any of the preceding claims 1 to 7 are implemented when the computer program is executed by the processor (20).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210102508.7A CN114513607B (en) | 2022-01-27 | 2022-01-27 | Method, device and system for self-adjusting field range of high-temperature industrial endoscope |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210102508.7A CN114513607B (en) | 2022-01-27 | 2022-01-27 | Method, device and system for self-adjusting field range of high-temperature industrial endoscope |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114513607A true CN114513607A (en) | 2022-05-17 |
| CN114513607B CN114513607B (en) | 2022-11-11 |
Family
ID=81549401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210102508.7A Active CN114513607B (en) | 2022-01-27 | 2022-01-27 | Method, device and system for self-adjusting field range of high-temperature industrial endoscope |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114513607B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115314609A (en) * | 2022-06-21 | 2022-11-08 | 中南大学 | Automatic acquisition method and device for aluminum electrolysis cell fire hole video |
| CN115396570A (en) * | 2022-07-12 | 2022-11-25 | 中南大学 | High-temperature industrial endoscope with faint light |
| CN116614707A (en) * | 2023-07-17 | 2023-08-18 | 中国空气动力研究与发展中心高速空气动力研究所 | Rotating blurred image deblurring method in blade surface pressure measurement |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5777668A (en) * | 1994-08-25 | 1998-07-07 | Amano & Associates Incorporated | Furnace monitoring camera with pivoting zoom lens |
| CN1286395A (en) * | 2000-09-29 | 2001-03-07 | 上海交通大学 | Imaging measurement method for volume of large material stack |
| CN101840055A (en) * | 2010-05-28 | 2010-09-22 | 浙江工业大学 | Video auto-focusing system based on embedded media processor |
| CN103417176A (en) * | 2013-08-01 | 2013-12-04 | 深圳先进技术研究院 | Capsule endoscope and automatic focusing method thereof |
| CN108881716A (en) * | 2018-06-13 | 2018-11-23 | 顺丰科技有限公司 | A kind of acquisition device and method of material image |
| CN109493426A (en) * | 2018-07-24 | 2019-03-19 | 中南大学 | A kind of blast furnace charge level three-dimensional reconstruction method and system based on monocular imaging |
| CN112149495A (en) * | 2020-08-07 | 2020-12-29 | 中国矿业大学(北京) | Video key frame extraction method based on parallax tracking |
| CN112419393A (en) * | 2020-11-15 | 2021-02-26 | 浙江大学 | Real-time measuring and calculating device and method for volume of garbage in hopper of garbage incinerator |
| CN214702145U (en) * | 2021-05-19 | 2021-11-12 | 陕西龙门钢铁有限责任公司 | Laser charge level monitoring system for measuring height and shape of charge level in blast furnace |
| CN113838114A (en) * | 2021-09-22 | 2021-12-24 | 中南大学 | Blast furnace charge level depth estimation method and system based on edge defocus tracking |
-
2022
- 2022-01-27 CN CN202210102508.7A patent/CN114513607B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5777668A (en) * | 1994-08-25 | 1998-07-07 | Amano & Associates Incorporated | Furnace monitoring camera with pivoting zoom lens |
| CN1286395A (en) * | 2000-09-29 | 2001-03-07 | 上海交通大学 | Imaging measurement method for volume of large material stack |
| CN101840055A (en) * | 2010-05-28 | 2010-09-22 | 浙江工业大学 | Video auto-focusing system based on embedded media processor |
| CN103417176A (en) * | 2013-08-01 | 2013-12-04 | 深圳先进技术研究院 | Capsule endoscope and automatic focusing method thereof |
| CN108881716A (en) * | 2018-06-13 | 2018-11-23 | 顺丰科技有限公司 | A kind of acquisition device and method of material image |
| CN109493426A (en) * | 2018-07-24 | 2019-03-19 | 中南大学 | A kind of blast furnace charge level three-dimensional reconstruction method and system based on monocular imaging |
| CN112149495A (en) * | 2020-08-07 | 2020-12-29 | 中国矿业大学(北京) | Video key frame extraction method based on parallax tracking |
| CN112419393A (en) * | 2020-11-15 | 2021-02-26 | 浙江大学 | Real-time measuring and calculating device and method for volume of garbage in hopper of garbage incinerator |
| CN214702145U (en) * | 2021-05-19 | 2021-11-12 | 陕西龙门钢铁有限责任公司 | Laser charge level monitoring system for measuring height and shape of charge level in blast furnace |
| CN113838114A (en) * | 2021-09-22 | 2021-12-24 | 中南大学 | Blast furnace charge level depth estimation method and system based on edge defocus tracking |
Non-Patent Citations (2)
| Title |
|---|
| JIANCAI HUANG ETC.: ""3D Topography Measurement and Completion Method of Blast Furnace Burden Surface Using High-Temperature Industrial Endoscope"", 《IEEE SENSORS JOURNAL》 * |
| 李超等: ""工业内窥镜调整方式优化"", 《科技展望》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115314609A (en) * | 2022-06-21 | 2022-11-08 | 中南大学 | Automatic acquisition method and device for aluminum electrolysis cell fire hole video |
| CN115314609B (en) * | 2022-06-21 | 2023-11-28 | 中南大学 | Automatic acquisition method and device for fire hole video of aluminum electrolysis cell |
| CN115396570A (en) * | 2022-07-12 | 2022-11-25 | 中南大学 | High-temperature industrial endoscope with faint light |
| CN115396570B (en) * | 2022-07-12 | 2023-12-12 | 中南大学 | Claustrophote high-temperature industrial endoscope |
| CN116614707A (en) * | 2023-07-17 | 2023-08-18 | 中国空气动力研究与发展中心高速空气动力研究所 | Rotating blurred image deblurring method in blade surface pressure measurement |
| CN116614707B (en) * | 2023-07-17 | 2023-09-19 | 中国空气动力研究与发展中心高速空气动力研究所 | Rotating blurred image deblurring method in blade surface pressure measurement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114513607B (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114513607B (en) | Method, device and system for self-adjusting field range of high-temperature industrial endoscope | |
| CN111047568B (en) | Method and system for detecting and identifying steam leakage defect | |
| US9338352B2 (en) | Image stabilization systems and methods | |
| CN106952225B (en) | Panoramic splicing method for forest fire prevention | |
| CN104519328A (en) | Image processing device, image capturing apparatus, and image processing method | |
| CN103902953B (en) | A kind of screen detecting system and method | |
| CN103185728A (en) | Image processing device and image processing method | |
| CN107255903A (en) | A kind of method that lens focus is measured based on Newton's ring | |
| CN116030055B (en) | Quality detection method for elevator-related accessories | |
| CN111179236A (en) | Raw ball granularity analysis method and device for pelletizer | |
| CN117579814B (en) | Quick lens detection method based on focusing detection | |
| JP7387261B2 (en) | Information processing device, information processing method and program | |
| CN113899698A (en) | Real-time focusing and centering adjustment method and device for in-situ test platform | |
| CN113375555A (en) | Power line clamp measuring method and system based on mobile phone image | |
| CN112461846A (en) | Workpiece defect detection method and device | |
| JP5050282B2 (en) | Focus detection device, focus detection method, and focus detection program | |
| CN116452976A (en) | Underground coal mine safety detection method | |
| CN206114545U (en) | Singly take photograph wide visual field of camera vision thread detection device | |
| CN112839168B (en) | Method for automatically adjusting camera imaging resolution in AOI detection system | |
| CN114529808A (en) | Pipeline detection panoramic shooting processing method | |
| CN109087278B (en) | Condom front and back recognition method based on improved Canny operator | |
| CN113705508A (en) | Flotation froth image acquisition and analysis method, system, medium and electronic terminal | |
| CN113596439A (en) | Camera module local analytic force failure detection method based on image fuzzy evaluation | |
| CN112640425A (en) | Focusing control method, device, equipment, movable platform and storage medium | |
| Désaulniers et al. | Performance evaluation of panoramic electro-optic imagers using the TOD 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 |