CN114708137B - 360 image processing device of monitoring in pit - Google Patents
360 image processing device of monitoring in pit Download PDFInfo
- Publication number
- CN114708137B CN114708137B CN202210436111.1A CN202210436111A CN114708137B CN 114708137 B CN114708137 B CN 114708137B CN 202210436111 A CN202210436111 A CN 202210436111A CN 114708137 B CN114708137 B CN 114708137B
- Authority
- CN
- China
- Prior art keywords
- image processing
- area
- processing unit
- screening
- image
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 169
- 238000012544 monitoring process Methods 0.000 title claims abstract description 17
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 102
- 230000007797 corrosion Effects 0.000 claims description 63
- 238000005260 corrosion Methods 0.000 claims description 63
- 230000003628 erosive effect Effects 0.000 claims description 10
- 239000013307 optical fiber Substances 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000003287 optical effect Effects 0.000 description 7
- 239000000523 sample Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003518 caustics Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/44—Morphing
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a 360-degree image processing device for underground monitoring, in particular to the technical field of image processing, wherein the device comprises a wide-angle camera which is arranged at the front end of a shell and can rotate by 360 degrees, a plurality of high-brightness LED light sources are circumferentially arranged on the periphery of the wide-angle camera, one end of each high-brightness LED light source is connected with an image processing unit, and the image processing unit is used for carrying out regional division on an obtained video frame image according to a gray value during image processing; one end of the image processing unit is connected with the logging cable network image transmission unit, one end of the logging cable network image transmission unit is connected with a battery for supplying power to the wide-angle camera, the high-brightness LED light source, the image processing unit and the logging cable network image transmission unit, and the other end of the battery is provided with a roller centralizer. The invention effectively improves the accuracy of image recognition and analysis and improves the detection efficiency of the integrity of the shaft.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a 360-degree image processing device for underground monitoring.
Background
Due to long-term water injection development, a series of problems can occur to the oil-water well casing, such as casing leakage, casing damage and even casing dislocation; in addition, due to long-term development, corrosive substances in formation fluid can corrode a casing, so that the integrity of a well bore is damaged, and the normal production of an oil-water well is seriously influenced by the problems.
Chinese patent CN201010115676.7 discloses a gas storage well shaft wall thickness and corrosion detection system, which comprises an overground part, a long-distance signal transmission part, an underground ultrasonic signal transmitting and receiving part and an annular water immersion probe array arrangement and righting part; converting the detected electric signal into an optical signal through a photoelectric converter, transmitting the optical signal through an optical fiber, and converting the optical signal into an electric signal through the photoelectric converter on the well to send to a computer; starting a computer, placing the underwater part into the well, adjusting the centralizer part, and ensuring that the probe array is coaxially parallel to the gas storage well; starting detection software, exciting and receiving ultrasonic signals between probe array layers staggered by a certain angle between the layers, performing operation processing on the obtained signals, converting the signals into optical signals by a photoelectric converter, then entering optical fibers, converting the optical signals by the photoelectric converter at the other end of the optical fibers, and then entering a computer network port; the real-time data image is displayed in the corresponding screen display area, so that the stability and the accuracy of detection are improved. However, the technical idea lies in that the ultrasonic probe emits ultrasonic waves for detection, and the technology is easily interfered by factors such as surrounding noise and the like, influences the detection result, and cannot visually, accurately and real-timely detect through images.
Disclosure of Invention
Therefore, the invention provides a 360-degree image processing device for underground monitoring, which is used for overcoming the problem of low detection efficiency of the integrity of a shaft caused by the fact that accurate image recognition and analysis cannot be carried out in the prior art.
In order to achieve the above objects, the present invention provides a 360 ° image processing apparatus for downhole monitoring, comprising,
the wide-angle camera is arranged at the front end of the shell and can rotate by 360 degrees and used for collecting images of the inner wall of the shaft, a plurality of high-brightness LED light sources used for illuminating the inner wall of the shaft are circumferentially arranged on the periphery of the wide-angle camera, and one end of each high-brightness LED light source is connected with an image processing unit used for carrying out image processing on the collected images of the inner wall of the shaft;
the image processing unit is used for carrying out region division on an obtained video frame image according to a gray value during image processing, dividing the video frame image into a plurality of preselected regions, determining a screening region according to a gray difference value delta Q of the connected preselected regions, judging a shaft deformation state according to a region sideline shape of the screening region after the region division is finished, calculating a curvature difference value delta A according to an average curvature of the sideline of the screening region to carry out secondary judgment on the shaft deformation state, judging a shaft corrosion state after the shaft deformation state is determined, carrying out primary judgment on a corrosion region of the video frame image according to each circumferential screening region area S in the obtained video frame image and obtaining a target region, carrying out secondary judgment on the corrosion region of the video frame image according to a graphic texture complexity P of the target region, and carrying out different corrosion region marking modes on the shaft deformation region and the video frame image in the image processing unit when the primary judgment is carried out;
one end of the image processing unit is connected with a logging cable network image transmission unit used for transmitting images processed by the image processing unit to ground processing equipment in real time through a cable or an optical fiber, one end of the logging cable network image transmission unit is connected with a battery used for supplying power to the wide-angle camera, the high-brightness LED light source, the image processing unit and the logging cable network image transmission unit, and the other end of the battery is provided with a roller centralizer used for centralizing when the device is placed down and inclined when encountering obstacles.
Further, the image processing unit acquires a video frame image from the acquired video image and performs area division on the video frame image when performing image processing, the image processing unit performs area division on the video frame image according to the gray scale value when performing area division, takes the areas which are connected and have the same gray scale value as preselected areas, acquires the gray scale value Q of each preselected area, calculates the gray scale difference value Δ Q of the connected preselected areas, sets Δ Q = | Qk-Qk1 |, qk is the gray scale value of the kth preselected area in the video frame image, and Qk1 is the gray scale value of the area connected with the kth preselected area, the image processing unit compares the gray scale difference value Δ Q of the connected preselected areas with the preset gray scale difference value Δ Q0, if Δ Q ≦ Q0, the image processing unit takes the connected preselected areas as the same screening area, and if Δ Q ≦ Q0, the image processing unit takes the connected preselected areas as different screening areas.
Further, when the image processing unit determines each regional side line by regional division, each regional side line is determined by tracking the regional boundary, when each regional boundary is tracked, a planar rectangular coordinate system is established by taking a central point of a video frame image as a coordinate origin, a horizontal direction as an x axis and a vertical direction as a y axis, a current edge point coordinate is set as (x, y), a position of the current edge point in 8 adjacent regions of an upper edge point is coded as m, a position of the current edge point (x, y) coded as m is clockwise moved by 2 pixels as an initial position of a next edge point search, 8 pixels are sequentially checked from the initial position in a counterclockwise direction, when a gray value of a pixel appearing for the first time is equal to a preset gray value, the pixel point serves as a next edge point, the image processing unit records the searched boundary point coordinates, forms each boundary point coordinate into a neighborhood array of one point, and takes a neighborhood array of the point as the regional side line.
Further, the image processing unit obtains the shape of the area boundary of the screening area when judging the deformation area of each screening area in the video frame image, and judges whether the shaft is deformed according to the shape of the area boundary, wherein,
when the shape of the area boundary line is circular, the image processing unit judges that the screening area is not deformed;
and when the shape of the area sideline is non-circular, the image processing unit carries out secondary judgment on whether the shaft is deformed or not according to the average curvature of the screening area sideline.
Further, the image processing unit obtains an average curvature a of the boundary line of the screening area when performing secondary determination on whether deformation occurs in the shaft, calculates a curvature difference value Δ a, sets Δ a = | a-A0 | where A0 is a preset standard curvature, compares the calculated curvature difference value Δ a with a preset curvature difference value Δ A0, determines that deformation does not occur in the screening area if Δ a is less than or equal to Δ A0, and determines that deformation has occurred in the screening area if Δ a is greater than Δ A0.
Furthermore, the image processing unit judges the corrosion area of the inner wall of the shaft after finishing the deformation judgment of the shaft, the image processing unit acquires the circumferential screening areas in the video frame image and acquires the area S of each circumferential screening area, the image processing unit compares the area S of the circumferential screening areas with the area S0 of a preset screening area and carries out the primary judgment of the corrosion area according to the comparison result, wherein,
when S is less than or equal to S0, the image processing unit judges that the screening area has corrosion risk;
and when S is larger than S0, the image processing unit judges that the screened area has no corrosion risk.
Further, when the image processing unit sets the area S0 of the preset screening area, the preset gray level difference value Delta Q0 is compared with each standard gray level difference value, and the corresponding adjusting coefficient is selected according to the comparison result to adjust the area S0 of the preset screening area, wherein,
when the delta Q0 is less than the delta Q1, the image processing unit selects a first adjusting coefficient g1 to adjust the area of the screening area, the adjusted area of the screening area is S1, S1= S0 Xg 1, and 1 < g1 < 1.2 is set;
when the delta Q1 is less than or equal to the delta Q0 is less than or equal to the delta Q2, the image processing unit does not adjust the area of the screening area;
when the delta Q2 is less than the delta Q0, the image processing unit selects a second adjusting coefficient g2 to adjust the area of the screening area, the adjusted area of the screening area is S2, S2= S0 Xg 2, and 0.8 < g2 < 1;
wherein, the delta Q1 is the minimum standard gray level difference value, the delta Q2 is the maximum standard gray level difference value, and the delta Q1 is smaller than the delta Q2.
Furthermore, the image processing unit takes the connected screening areas with corrosion risk as target areas and obtains the graph texture complexity P of each target area, the image processing unit compares the graph texture complexity P of the target areas with the preset graph texture complexity P0 and carries out secondary judgment on the corrosion areas according to the comparison result, wherein,
when P > P0, the image processing unit judges that the target region is a corrosion region;
when P is less than or equal to P0, the image processing unit judges that the target area is a non-erosion area.
Further, the image processing unit marks the deformation area and the erosion area in different ways after the judgment of shaft deformation and erosion is completed on the video frame image, wherein,
when the image processing unit marks the deformation area, acquiring an area side line inflection point in the deformation area, marking the inflection point position, uniformly marking the connected inflection points among the deformation areas when a plurality of deformation areas exist, and marking different inflection points of the same deformation area;
when the image processing unit marks the corrosion regions, the image processing unit marks the corrosion regions one by one.
Further, the surface treatment apparatus comprises: coiled tubing and corollary equipment, ground receiving equipment, signal converter, wireless signal transmitter, wireless signal receiver, signal processor, display panel.
Compared with the prior art, the device has the advantages that the device is applied to image acquisition of the shaft, when the image acquisition is carried out, the device is placed to the preset position for image acquisition, the wide-angle camera which is arranged at the front end and can rotate 360 degrees is used for acquiring images of the inner wall of the shaft without complete dead angles, and the wide-angle camera is circumferentially provided with a plurality of high-brightness LED light sources for illumination, so that the wide-angle camera can acquire the images more clearly. The device is applied to image acquisition of the inner wall of the shaft, and the clear integrity of the image acquisition of the inner wall of the shaft is improved by acquiring the image of the inner wall of the shaft at 360 degrees without dead angles, so that a basis is provided for subsequent image processing and analysis.
Particularly, when the image processing unit divides the video frame image into regions according to the gray values, the regions which are connected with each other and have the same gray value are used as preselected regions, the gray value Q of each preselected region is obtained, the gray difference value delta Q of each connected preselected region is calculated, and the image processing unit compares the gray difference value delta Q of each connected preselected region with the preset gray difference value delta Q0, so that the same screening region and different screening regions are divided from each other, and the accuracy of image identification is improved.
Particularly, when the image processing unit performs region division to determine the side lines of each region, the side lines of each region are determined by tracking the region boundary, and when the boundary of each region is tracked, the edge of the image can be quickly and accurately tracked by performing edge tracking through an 8-neighborhood search algorithm, so that the efficiency and the accuracy of image identification are improved.
Particularly, when the image processing unit processes the images, the image processing unit divides the acquired video frame images to form a plurality of screening areas, acquires a plurality of side lines of the screening areas in the images, and judges whether the screening areas deform or not according to the shapes of the side lines of the screening areas, so that the accuracy of shaft deformation judgment is improved.
Particularly, when the image processing unit judges whether the shaft is deformed for the second time, the shaft deformation is judged for the second time by obtaining the average curvature A of the side line of the screening area and calculating the curvature difference value delta A, the accuracy of judging the shaft deformation is improved by the second time judgment, the shaft deformation is judged to be larger when the curvature difference value delta A is larger, and the accuracy of judging the shaft deformation is further improved by judging the shaft deformation according to the curvature difference value delta A.
Particularly, when the image processing unit judges the corrosion area of the inner wall of the shaft, whether the screening area has corrosion risk is judged by comparing the area S of the circumferential screening area with the area S0 of the preset screening area, so that the accuracy of judging whether the shaft has corrosion risk is improved.
Particularly, when the image processing unit sets the area of the preset screening area, the preset gray difference value delta Q0 is compared with each standard gray difference value, and the corresponding adjusting coefficient is selected according to the comparison result to adjust the area of the preset screening area, so that the accuracy of the area of the screening area is improved, and the processing efficiency of judging the corrosion area of the inner wall of the shaft is further improved.
Particularly, the image processing unit compares the graph texture complexity P of the target area with the preset graph texture complexity P0 to judge whether the target area is corroded, so that the accuracy of judging whether the shaft is corroded is further improved.
Particularly, the image processing unit marks each deformation area and each corrosion area in different modes, and improves accurate positioning and identification of deformation positions by acquiring area side line inflection points in the deformation areas and marking inflection point positions; when a plurality of deformation areas exist, uniformly marking the connected inflection points among the deformation areas, performing different marking on different inflection points of the same deformation area, and improving the accurate positioning and identification of the deformation positions of the different areas through uniform marking and different marking modes; when the corrosion areas are marked, the corrosion areas are marked one by one, so that accurate positioning and identification of the corrosion areas are improved.
Drawings
Fig. 1 is a schematic structural diagram of a 360 ° image processing apparatus for downhole monitoring according to the present embodiment.
In the figure: the device comprises a wide-angle lens 1, a high-brightness LED light source 2, an image processing unit 3, a logging cable network image transmission unit 4, a battery 5, a roller centralizer 6 and a shell 7.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described in conjunction with the following examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Fig. 1 is a schematic structural diagram of a 360 ° image processing apparatus for downhole monitoring according to the present embodiment, the apparatus includes:
locate 360 rotatory wide-angle camera 1 of casing 7 front end, wide-angle camera 1 is used for gathering pit shaft inner wall image, the peripheral circumference of wide-angle camera 1 is equipped with a plurality of high bright LED light sources 2, high bright LED light source 2 is used for the illumination to the pit shaft inner wall, high bright LED light source 2's one end is connected with image processing unit 3, image processing unit 3 is used for carrying out image processing to the pit shaft inner wall image of gathering, image processing unit 3's one end and logging cable network picture pass unit 4 are connected, logging cable network picture pass unit 4 be used for with image processing unit 3 handles the back image and transmits for ground processing equipment through cable or optic fibre in real time, logging cable network picture passes the one end of unit 4 and is connected with battery 5, battery 5 is used for right wide-angle camera 1 high bright LED light source 2 image processing unit 3 and logging cable network picture passes unit 4 and supplies power, the other end of battery is equipped with gyro wheel centralizer 6, centralizer 6 is used for setting up when the device is transferred the in-process and is met the obstacle and rights.
Specifically, the ground processing apparatus in this embodiment includes: coiled tubing and corollary equipment, ground receiving equipment, signal converter, wireless signal transmitter, wireless signal receiver, signal processor, display panel. The coiled tubing and the matched equipment convey the multimode optical fiber and the image processing device into the shaft, and image acquisition is carried out on each preset position in the shaft through the up-and-down movement of the coiled tubing; the ground receiving equipment is used for receiving the optical signal transmitted to the ground by the optical fiber; the signal converter is used for converting the optical signal in the ground receiving equipment into an electric pulse signal, so that signal transmission is facilitated; the wireless signal transmitter is used for transmitting electric pulse signals; the wireless signal receiving device is used for transmitting electric pulse signals; the signal processor is used for converting the electric pulse signals into video signals and playing videos on the display panel, so that monitoring by operators is facilitated. This embodiment the device is applied to the image acquisition to the pit shaft, when carrying out image acquisition, will the device is transferred to predetermineeing the position and is carried out image acquisition, through locating the front end can 360 rotatory wide-angle camera for to the complete collection image at no dead angle of pit shaft inner wall the peripheral circumference of wide-angle camera is equipped with under the illumination of a plurality of high bright LED light sources, so that the wide-angle camera can gather the image more clearly. The device is applied to image acquisition of the inner wall of the shaft, and through image acquisition of the inner wall of the shaft in 360 degrees without dead angles, the clear integrity of the image acquisition of the inner wall of the shaft is improved, and a basis is provided for subsequent image processing and analysis. In this embodiment, the ground processing device conveys the multimode optical fiber and the image processing device to the shaft through the coiled tubing and the matching equipment, and performs image acquisition on each preset position in the shaft through the up-and-down movement of the coiled tubing so as to improve the convenience of image acquisition on the inner wall of the shaft.
Specifically, the image processing unit acquires a video frame image from an acquired video image and performs area division on the video frame image when performing image processing, the image processing unit performs area division on the video frame image according to gray levels, takes areas which are connected and have the same gray value as preselected areas, acquires gray values Q of the preselected areas, calculates gray difference values Δ Q of the connected preselected areas, sets Δ Q = | Qk-Qk1, |, qk being a gray value of a kth preselected area in the video frame image, and Qk1 being a gray value of an area connected to the kth preselected area, compares the gray difference values Δ Q of the connected preselected areas with a preset gray difference value Δ Q0, and if Δ Q ≦ Q0, the image processing unit takes the connected preselected areas as the same screening area, and if Δ Q ≦ Q0, the image processing unit takes the connected preselected areas as different screening areas.
Specifically, in this embodiment, when the image processing unit divides the video frame image into regions according to the gray values, the regions that are connected to each other and have the same gray value are used as the preselection regions, the gray value Q of each preselection region is obtained, the gray difference Δ Q of the connected preselection regions is calculated, and the image processing unit compares the gray difference Δ Q of the connected preselection regions with the preset gray difference Δ Q0, so that the same screening region and different screening regions are divided from the connected preselection regions, thereby improving the accuracy of image recognition.
Specifically, when the image processing unit determines each regional side line by regional division, each regional side line is determined by tracking the regional boundary, when each regional boundary is tracked, a planar rectangular coordinate system is established by taking a central point of a video frame image as a coordinate origin, a horizontal direction as an x axis and a vertical direction as a y axis, a current edge point coordinate is set as (x, y), a position of the current edge point in 8 adjacent regions of the upper edge point is coded as m, 2 pixels are moved clockwise as a starting position of a next edge point search by taking the position of the current edge point (x, y) coded as m, the 8 adjacent pixels are sequentially checked from the starting position in a counterclockwise direction, when a gray value of a pixel appearing for the first time is equal to a preset gray value, the pixel is taken as a next edge point, the image processing unit records the searched boundary point coordinates, forms each boundary point coordinate into an array of points, and takes the array of the point as the regional side line.
Specifically, in this embodiment, when the image processing unit performs region division to determine each region edge, each region edge is determined by tracking the region boundary, and when each region boundary is tracked, the edge of the image can be quickly and accurately tracked by performing edge tracking through an 8-neighborhood search algorithm, so as to improve the efficiency and accuracy of image identification.
Specifically, the image processing unit obtains the shape of the area boundary of the screening area when judging the deformation area of each screening area in the video frame image, and judges whether the shaft is deformed according to the shape of the area boundary, wherein,
when the shape of the area boundary line is circular, the image processing unit judges that the screening area is not deformed;
and when the shape of the area sideline is non-circular, the image processing unit carries out secondary judgment on whether the shaft is deformed or not according to the average curvature of the screening area sideline.
Specifically, in the embodiment, when the image processing unit performs image processing, the image processing unit divides the acquired video frame image to form a plurality of screening areas, obtains a plurality of side lines of the screening areas in the image, and determines whether the screening areas deform according to the shapes of the side lines of the screening areas, so as to improve the accuracy of determining the deformation of the shaft.
Specifically, the image processing unit obtains an average curvature a of an edge line of a screening area when secondarily determining whether deformation occurs in a shaft, calculates a curvature difference value Δ a, sets Δ a = | a-A0 | where A0 is a preset standard curvature, compares the calculated curvature difference value Δ a with a preset curvature difference value Δ A0, determines that deformation does not occur in the screening area if Δ a is less than or equal to Δ A0, and determines that deformation has occurred in the screening area if Δ a is greater than or equal to Δ A0.
Specifically, in this embodiment, when performing secondary determination on whether a wellbore deforms, the image processing unit performs secondary determination on the wellbore deformation by obtaining an average curvature a of a sideline of the screening area and calculating a curvature difference value Δ a, so as to improve accuracy of determination on the wellbore deformation, and when the curvature difference value Δ a is larger, it is determined that the wellbore deformation is larger, and by performing the wellbore deformation determination according to the curvature difference value Δ a, accuracy of determination on the wellbore deformation is further improved. It can be understood that, in this embodiment, a determination method for performing secondary determination on deformation is not specifically limited, and a person skilled in the art can freely set the determination method, for example, by obtaining the radial diameter D of the wellbore in the video frame image and comparing the radial diameter D with the preset wellbore radial diameter D0, and when D > D0 or D < D0, determining that the wellbore deforms; and when D = D0, judging that the shaft is not deformed and the like. When the deformation is determined twice, those skilled in the art may set other determination manners, such as obtaining the number of inflection points of the side line of the screening area, and determining that the deformation occurs if the number of inflection points is greater than a threshold value.
Specifically, the image processing unit judges the corrosion area of the inner wall of the shaft after the deformation of the shaft is judged, the image processing unit acquires the circumferential screening areas in the video frame image and acquires the area S of each circumferential screening area, the image processing unit compares the area S of the circumferential screening areas with the area S0 of a preset screening area and carries out primary judgment on the corrosion area according to the comparison result, wherein,
when S is less than or equal to S0, the image processing unit judges that the screening area has corrosion risk;
and when S is larger than S0, the image processing unit judges that the screened area has no corrosion risk.
Specifically, in this embodiment, when the image processing unit determines the corrosion area of the inner wall of the wellbore, the image processing unit determines whether the screening area has a corrosion risk by comparing the area S of the circumferential screening area with the preset area S0 of the screening area, so as to improve the accuracy of determining whether the wellbore has the corrosion risk. It can be understood that, when determining whether the corrosion risk exists in the screening area, a person skilled in the art may also set other determination manners, such as presetting a corrosion image feature map, comparing the screening area image with the presetting corrosion image feature map, and determining whether the corrosion risk occurs according to the image feature similarity between the screening area image and the presetting corrosion image feature map.
Specifically, when the image processing unit sets the area S0 of the preset screening area, the preset gray level difference value Δ Q0 is compared with each standard gray level difference value, and the corresponding adjustment coefficient is selected according to the comparison result to adjust the area S0 of the preset screening area, wherein,
when the delta Q0 is less than the delta Q1, the image processing unit selects a first adjusting coefficient g1 to adjust the area of the screening area, the adjusted area of the screening area is S1, S1= S0 Xg 1, and 1 < g1 < 1.2 is set;
when the delta Q1 is less than or equal to the delta Q0 is less than or equal to the delta Q2, the image processing unit does not adjust the area of the screening area;
when the delta Q2 is less than the delta Q0, the image processing unit selects a second adjusting coefficient g2 to adjust the area of the screening area, the adjusted area of the screening area is S2, S2= S0 Xg 2, and 0.8 < g2 < 1;
wherein, the delta Q1 is the minimum standard gray difference value, the delta Q2 is the maximum standard gray difference value, and the delta Q1 is smaller than the delta Q2.
Specifically, in this embodiment, when the preset screening area is set, the image processing unit compares the preset grayscale difference Δ Q0 with each standard grayscale difference, and selects a corresponding adjustment coefficient according to the comparison result to adjust the preset screening area, so as to improve the accuracy of the screening area, and further improve the processing efficiency of determining the corrosion area of the inner wall of the wellbore.
Specifically, the image processing unit takes a connected screening area with corrosion risk as a target area, acquires the graph texture complexity P of each target area, compares the graph texture complexity P of the target area with a preset graph texture complexity P0, and performs secondary judgment of a corrosion area according to a comparison result, wherein,
when P > P0, the image processing unit judges that the target region is a corrosion region;
when P is less than or equal to P0, the image processing unit judges that the target area is a non-erosion area.
Specifically, in this embodiment, the image processing unit determines whether the target region is corroded by comparing the graph texture complexity P of the target region with a preset graph texture complexity P0, so as to further improve the accuracy of determining whether the shaft is corroded. It can be understood that, in this embodiment, the determination method of the corrosion area is not specifically limited, and a person skilled in the art can freely set the determination method, for example, the determination method can also determine the brightness of the target area, for example, the brightness L of the target area is compared with a preset standard degree L0, and when L is greater than or equal to L0, it is determined that the target area is not corroded; and when L is less than L0, judging that the target area is corroded. The person skilled in the art can also determine in other ways, as long as the determination requirement for the corrosion area is met.
Specifically, after the determination of deformation and corrosion of the shaft is completed, the image processing unit marks the deformation area and the corrosion area in different ways, wherein,
when the image processing unit marks the deformation area, acquiring an area side line inflection point in the deformation area, marking the inflection point position, uniformly marking the connected inflection points among the deformation areas when a plurality of deformation areas exist, and marking different inflection points of the same deformation area;
when the image processing unit marks the corrosion regions, the image processing unit marks the corrosion regions one by one.
Specifically, in this embodiment, the image processing unit marks each deformation region and each corrosion region in different manners, and improves accurate positioning and identification of the deformation position by obtaining a region edge inflection point in the deformation region and marking the inflection point position; when a plurality of deformation areas exist, uniformly marking the connected inflection points among the deformation areas, performing different marking on different inflection points of the same deformation area, and improving the accurate positioning and identification of the deformation positions of the different areas through uniform marking and different marking modes; when the corrosion areas are marked, the corrosion areas are marked one by one, so that accurate positioning and identification of the corrosion areas are improved. It can be understood that, in this embodiment, the marking mode is not specifically limited, and those skilled in the art can freely set the marking mode, for example, geometric shapes including circles, rectangles, polygons and the like are drawn for marking, and other marking modes can be set, which only needs to meet the marking requirements for the deformation region and the erosion region.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (9)
1. A360-degree image processing device for underground monitoring is characterized by comprising,
the wide-angle camera is arranged at the front end of the shell and can rotate 360 degrees and used for acquiring images of the inner wall of the shaft, a plurality of high-brightness LED light sources used for illuminating the inner wall of the shaft are circumferentially arranged on the periphery of the wide-angle camera, and one end of each high-brightness LED light source is connected with an image processing unit used for processing the acquired images of the inner wall of the shaft;
the image processing unit is used for carrying out region division on an obtained video frame image according to gray values when carrying out image processing, dividing the video frame image into a plurality of preselected regions, determining a screening region according to the gray difference value delta Q of the connected preselected regions, after the region division is finished, judging a shaft deformation state according to the region sideline shape of the screening region, calculating a curvature difference value delta A according to the average curvature of the sideline of the screening region, carrying out secondary judgment on the shaft deformation state, after the shaft deformation state is determined, judging the shaft corrosion state, carrying out primary judgment on a corrosion region of the video frame image according to the area S of each circumferential screening region in the obtained video frame image, and obtaining a target region, carrying out secondary judgment on the corrosion region of the video frame image according to the graphic texture complexity P of the target region, and carrying out primary judgment on the corrosion region S0 of the preset region according to the gray difference value delta Q0 when carrying out primary judgment on the corrosion region, and carrying out marking different corrosion region marking modes on the corrosion region in the shaft image processing unit when carrying out primary judgment on the corrosion region;
one end of the image processing unit is connected with a logging cable network image transmission unit which is used for transmitting the image processed by the image processing unit to ground processing equipment in real time through a cable or an optical fiber, one end of the logging cable network image transmission unit is connected with a battery which is used for supplying power to the wide-angle camera, the high-brightness LED light source, the image processing unit and the logging cable network image transmission unit, and the other end of the battery is provided with a roller centralizer which is used for centralizing when the device is inclined when encountering obstacles in the process of lowering;
the image processing unit compares the preset gray level difference value delta Q0 with each standard gray level difference value when setting the preset screening area S0, and selects a corresponding adjusting coefficient according to the comparison result to adjust the preset screening area S0, wherein,
when the delta Q0 is less than the delta Q1, the image processing unit selects a first adjusting coefficient g1 to adjust the area of the screening area, the adjusted area of the screening area is S1, S1= S0 Xg 1, and 1 < g1 < 1.2 is set;
when the delta Q1 is less than or equal to the delta Q0 is less than or equal to the delta Q2, the image processing unit does not adjust the area of the screening area;
when the delta Q2 is less than the delta Q0, the image processing unit selects a second adjusting coefficient g2 to adjust the area of the screening area, the adjusted area of the screening area is S2, S2= S0 Xg 2, and 0.8 < g2 < 1;
wherein, the delta Q1 is the minimum standard gray level difference value, the delta Q2 is the maximum standard gray level difference value, and the delta Q1 is smaller than the delta Q2.
2. The 360 ° image processing apparatus for downhole monitoring according to claim 1, wherein the image processing unit acquires a video frame image from the acquired video image and performs area division on the video frame image when performing the image processing, the image processing unit performs area division on the video frame image by gray scale values, takes areas which are connected and have the same gray scale value as preselected areas, and acquires a gray scale value Q of each preselected area, and calculates a gray scale difference Δ Q of the connected preselected areas, sets Δ Q = | Qk-Qk1 | Qk being a gray scale value of a kth preselected area in the video frame image, qk1 being a gray scale value of an area connected to the kth preselected area, the image processing unit compares the gray scale difference Δ Q of the connected preselected areas with a preset gray scale difference Q0, and if Δ Q ≦ Q0, the image processing unit screens the connected preselected areas as the same preselected areas, if Δ Q > Δ Q0, and the image processing unit selects the different preselected areas as the screened areas.
3. The 360 ° image processing apparatus for downhole monitoring according to claim 2, wherein the image processing unit determines each regional edge by tracking the regional boundary when determining each regional edge by regional division, establishes a rectangular plane coordinate system by tracking each regional edge by using a central point of a video frame image as a coordinate origin, using a horizontal direction as an x-axis and a vertical direction as a y-axis when tracking each regional boundary, sets a current edge point coordinate as (x, y), codes a position of the point in 8 neighborhoods of the upper edge point as m, and moves 2 pixels clockwise as a start position of a next edge point search by using a position of the current edge point (x, y) coded as m, and sequentially checks 8 neighborhoods in a counterclockwise direction starting from the start position, and when a gray value of a pixel appearing for the first time is equal to a preset gray value, the pixel serves as a next edge point, and records the searched coordinates of each boundary point and forms an array of the coordinates of each boundary point as the regional edge.
4. The 360 ° image processing apparatus for downhole monitoring according to claim 1, wherein the image processing unit obtains an area edge shape of the screening area when performing deformation area determination on each screening area in the video frame image, and determines whether the shaft is deformed according to the area edge shape, wherein,
when the shape of the area side line is circular, the image processing unit judges that the screening area is not deformed;
and when the shape of the area sideline is non-circular, the image processing unit secondarily judges whether the shaft is deformed or not according to the average curvature of the screening area sideline.
5. The downhole monitored 360 ° image processing apparatus according to claim 4, wherein the image processing unit obtains an average curvature a of edges of the screening region and calculates a curvature difference Δ a when a secondary determination is made as to whether deformation occurs in the wellbore, and sets Δ a = | a-A0 |, A0 being a preset standard curvature, the image processing unit compares the calculated curvature difference Δ a with a preset curvature difference Δ A0, and if Δ a is less than or equal to Δ A0, the image processing unit determines that the screening region is not deformed, and if Δ a > Δ A0, the image processing unit determines that the screening region is deformed.
6. The 360-degree image processing device for downhole monitoring according to claim 1, wherein the image processing unit judges the erosion area of the inner wall of the shaft after the deformation judgment of the shaft is completed, the image processing unit obtains the circumferential screening areas in the video frame image and obtains the area S of each circumferential screening area, the image processing unit compares the area S of each circumferential screening area with a preset screening area S0 and performs the primary judgment of the erosion area according to the comparison result, wherein,
when S is less than or equal to S0, the image processing unit judges that the screening area has corrosion risk;
and when S is larger than S0, the image processing unit judges that the screened area has no corrosion risk.
7. The 360-degree image processing device for downhole monitoring according to claim 6, wherein the image processing unit takes the connected screening regions with corrosion risk as target regions and obtains the graph texture complexity P of each target region, the image processing unit compares the graph texture complexity P of the target regions with a preset graph texture complexity P0 and performs secondary judgment of corrosion regions according to the comparison result, wherein,
when P > P0, the image processing unit judges that the target region is a corrosion region;
when P is less than or equal to P0, the image processing unit judges that the target area is a non-erosion area.
8. A360 DEG image processing device for downhole monitoring according to any of claims 4-7, wherein the image processing unit marks the deformation area and the erosion area in different ways after the determination of deformation and erosion of the shaft is completed on the video frame image, wherein,
when the image processing unit marks the deformation area, acquiring an area side line inflection point in the deformation area, marking the inflection point position, uniformly marking the connected inflection points among the deformation areas when a plurality of deformation areas exist, and marking different inflection points of the same deformation area;
when the image processing unit marks the corrosion areas, the image processing unit marks the corrosion areas one by one.
9. A 360 ° image processing apparatus for downhole monitoring according to claim 1, wherein the surface processing means comprises: coiled tubing and corollary equipment, ground receiving equipment, signal converter, wireless signal transmitter, wireless signal receiver, signal processor, display panel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210436111.1A CN114708137B (en) | 2022-04-25 | 2022-04-25 | 360 image processing device of monitoring in pit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210436111.1A CN114708137B (en) | 2022-04-25 | 2022-04-25 | 360 image processing device of monitoring in pit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114708137A CN114708137A (en) | 2022-07-05 |
| CN114708137B true CN114708137B (en) | 2022-11-25 |
Family
ID=82174618
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210436111.1A Active CN114708137B (en) | 2022-04-25 | 2022-04-25 | 360 image processing device of monitoring in pit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114708137B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117745276B (en) * | 2024-02-19 | 2024-06-07 | 中铁四局集团有限公司 | Data sharing management method and system based on Internet of things |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255706A (en) * | 2021-07-16 | 2021-08-13 | 南京奕荣芯科技有限公司 | Target identification method and system based on convolutional neural network algorithm |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833217B (en) * | 2017-11-14 | 2021-08-10 | 安徽森力汽车电子有限公司 | Graph card detection method based on mathematical morphology |
| CN108805920A (en) * | 2018-06-01 | 2018-11-13 | 环境保护部卫星环境应用中心 | The recognition methods in soil pollution risk region and device on unused land |
| CN113837991A (en) * | 2021-06-18 | 2021-12-24 | 腾讯云计算（北京）有限责任公司 | Image processing method, device, equipment and storage medium |
-
2022
- 2022-04-25 CN CN202210436111.1A patent/CN114708137B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255706A (en) * | 2021-07-16 | 2021-08-13 | 南京奕荣芯科技有限公司 | Target identification method and system based on convolutional neural network algorithm |
Non-Patent Citations (2)
| Title |
|---|
| "基于内窥镜视频的工业管道图像展开研究";钱渠;《中国优秀硕士学位论文全文数据库 信息科技辑》;20210115(第1期);第9-15、41页 * |
| "煤矿立井井筒缺陷检测技术研究";薛芮;《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》;20220315(第3期);第31-32、56-57页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114708137A (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111255636B (en) | Method and device for determining tower clearance of wind generating set | |
| CN104568983B (en) | Pipeline Inner Defect Testing device and method based on active panoramic vision | |
| CN107229930B (en) | Intelligent identification method for numerical value of pointer instrument | |
| CN108844463A (en) | Underground piping dimensional orientation measuring system and method based on laser spot position | |
| CN112085003B (en) | Automatic recognition method and device for abnormal behaviors in public places and camera equipment | |
| CN108230344B (en) | Automatic identification method for tunnel water leakage diseases | |
| CN111895911B (en) | Method for monitoring hidden danger of ground collapse of shallow sand layer | |
| CN114708137B (en) | 360 image processing device of monitoring in pit | |
| CN110084842B (en) | Servo secondary alignment method and device for robot holder | |
| CN110189375B (en) | Image target identification method based on monocular vision measurement | |
| CN108693535A (en) | A kind of detection system for obstacle and detection method for underwater robot | |
| CN110130987B (en) | Tunnel convergence deformation monitoring method based on image analysis | |
| CN115308222B (en) | System and method for identifying poor chip appearance based on machine vision | |
| CN116379359B (en) | Natural gas leakage detection method and multi-mode natural gas leakage detection system | |
| CN115877400A (en) | Tunnel roof support steel belt drilling positioning method based on radar and vision fusion | |
| CN114812403A (en) | Large-span steel structure hoisting deformation monitoring method based on unmanned aerial vehicle and machine vision | |
| CN111829486A (en) | Shield construction ground settlement automatic monitoring method and system | |
| CN114119614A (en) | Method for remotely detecting cracks of building | |
| CN109164412A (en) | A kind of assisted location method based on beacon identification | |
| JP2007256280A (en) | Object recognition system and displacement measurement method of object using the same | |
| CN112964251A (en) | Positioning method of inspection robot | |
| CN115409691A (en) | Bimodal learning slope risk detection method integrating laser ranging and monitoring image | |
| CN113971699A (en) | Target object identification method and device, electronic equipment and storage medium | |
| CN114772467A (en) | System and method for monitoring verticality of tower crane in jacking process based on image recognition | |
| CN110738646A (en) | automatic identification method for pipeline breakage |
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 |