CN113344955B - System and method for accurately detecting slope by fuzzy edge - Google Patents
System and method for accurately detecting slope by fuzzy edge Download PDFInfo
- Publication number
- CN113344955B CN113344955B CN202110572155.2A CN202110572155A CN113344955B CN 113344955 B CN113344955 B CN 113344955B CN 202110572155 A CN202110572155 A CN 202110572155A CN 113344955 B CN113344955 B CN 113344955B
- Authority
- CN
- China
- Prior art keywords
- edge
- image
- contour
- slope
- filtering
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000001914 filtration Methods 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000003708 edge detection Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 230000009977 dual effect Effects 0.000 claims description 6
- 230000001629 suppression Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012163 sequencing technique Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
Images
Classifications
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a system for accurately detecting a side slope by fuzzy edges, which comprises: the detection piece is used for being installed on a side slope; the shooting module is used for shooting the detection piece; the median filtering processing module is used for carrying out image binarization and median filtering processing; the contour extraction module is used for extracting contours of the images; the contour primary processing module is used for generating a plurality of positive rectangles at the contour edge of the image, and generating a circle by taking the center of the positive rectangle as the center of the circle and the side length of the positive rectangle as the diameter; the contour middle-level processing module is used for connecting the edge detection key point and the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S; and the contour final-stage processing module is used for filtering the set S, identifying each S in the filtered set S and then finding the center point again. The invention also discloses a method for accurately detecting the side slope by the fuzzy edge.
Description
Technical Field
The invention relates to the field, in particular to a system and a method for accurately detecting a side slope by a fuzzy edge.
Background
TD side slope monitoring system is a side slope automation monitoring early warning system based on shallow surface subsides and slope deformation height precision measurement, this system can carry out remote automation monitoring to the side slope, and can carry out real-time analysis to the monitoring data, in time make early warning response, fixed point installation ultralong burnt digital camera monitoring system under the massif is as the observation point, install the detection piece on the side slope on the massif, judge the position of detection piece according to the camera and judge whether the phenomenon that the landslide appears in the side slope, however current shooting equipment is when shooing the photo of detection piece, because the photo profile is comparatively fuzzy, the inconvenient position of judging the detection piece on the photo, thereby whether the landslide appears in the influence judgement side slope.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a system and a method for accurately detecting a side slope by using a fuzzy edge.
The technical scheme adopted by the invention is as follows:
a system for accurately detecting a slope with blurred edges, comprising:
the detection piece is arranged on the side slope and used for shooting by the shooting module;
the shooting module is used for shooting an image of a detection piece arranged on a side slope;
the median filtering processing module is used for adjusting the image saturation, then carrying out image binarization and carrying out median filtering processing;
the contour extraction module is used for carrying out contour extraction after carrying out edge detection and expansion processing on the image;
the contour primary processing module is used for generating a plurality of positive rectangles at the contour edge of the image, and generating a circle by taking the center of the positive rectangle as the center of the circle and the side length of the positive rectangle as the diameter;
the contour middle-level processing module is used for calculating the superposition number of the circles generated in the contour primary processing module and the edge detection key points, connecting the edge detection key points and the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S;
and the contour final-stage processing module is used for filtering the set S, identifying each S in the filtered set S and then finding the center point again.
Preferably, the median filtering process in the median filtering process module specifically includes:
generating a filtering template, and sequencing pixel values in the template to generate a two-dimensional data sequence which monotonically rises or falls, wherein the two-dimensional median filtering output is g (x, y) ═ medf { f (x-k, y-1), (k, l ∈ w) }, wherein f (x, y) and g (x, y) are an original image and an image after image saturation adjustment respectively, and w is an input two-dimensional template;
odd numbers of data are fetched from a two-dimensional template in the image for sorting, and the sorted median value is used for replacing the data to be processed.
Preferably, the edge detection in the contour extraction module specifically includes:
applying gaussian filtering to smooth the image to remove noise;
finding an intensity gradient of the image;
applying non-maximum suppression to eliminate edge false detection;
applying a dual threshold to determine possible boundaries;
the boundaries are tracked using hysteresis.
Preferably, the filtering of the set S in the contour last stage processing module is specifically:
calculating the average value S1 of S in the set S, filtering out S which is larger than the average value S1 in the set S, and filtering out S with the least frequency of occurrence in the set S.
Preferably, the identification of each S in the set S in the contour final processing module is specifically:
a ═ avg (abs (s)), where avg denotes the average value and abs denotes the absolute value.
A method for accurately detecting a slope by fuzzy edges comprises the following steps:
s1, installing a detection piece on the slope to be detected;
s2, shooting an image of a detection piece on the side slope;
s3, adjusting the image saturation, then carrying out image binarization and carrying out median filtering processing;
s4, carrying out edge detection and expansion processing on the image and then carrying out contour extraction;
s5, generating a plurality of positive rectangles at the edge of the outline of the image, and generating a circle by taking the center of the positive rectangle as the center of a circle and the side length of the positive rectangle as the diameter;
s6, calculating the number of coincided circles and edge detection key points, connecting the edge detection key points with the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S;
and S7, filtering the set S, identifying each S in the filtered set S, and then finding the center point again.
Preferably, the median filtering is specifically:
generating a filtering template, and sequencing pixel values in the template to generate a two-dimensional data sequence which monotonically rises or falls, wherein the two-dimensional median filtering output is g (x, y) ═ medf { f (x-k, y-1), (k, l ∈ w) }, wherein f (x, y) and g (x, y) are an original image and an image after image saturation adjustment respectively, and w is an input two-dimensional template;
odd numbers of data are fetched from a two-dimensional template in the image for sorting, and the sorted median value is used for replacing the data to be processed.
Preferably, the edge detection of the image is specifically as follows:
applying gaussian filtering to smooth the image to remove noise;
finding an intensity gradient of the image;
applying non-maximum suppression to eliminate edge false detection;
applying a dual threshold to determine possible boundaries;
the boundaries are tracked using hysteresis.
Preferably, the filtering set S specifically includes:
calculating the average value S1 of S in the set S, filtering out S which is larger than the average value S1 in the set S, and filtering out S with the least frequency of occurrence in the set S.
Preferably, the identification of each S in the set S specifically includes:
a ═ avg (abs (s)), where avg denotes the average value and abs denotes the absolute value.
The invention has the beneficial effects that: according to the invention, the detection piece installed on the slope is shot by the shooting equipment, and when the picture of the detection piece shot by the shooting equipment is fuzzy, the edge on the picture is processed by the method to obtain a clear edge profile, so that the position of the detection piece on the picture is convenient to judge, whether the position of the detection piece on the slope is changed or not can be observed by the picture, and when the position of the detection piece shot on the picture is changed, the slope is indicated to have landslide and other phenomena.
Drawings
FIG. 1 is a schematic structural view of example 1 of the present invention;
FIG. 2 is a schematic flow chart of example 2 of the present invention;
reference numerals: 1. the device comprises a detection piece, 2, a shooting module, 3, a median filtering processing module, 4, a contour extraction module, 5, a contour primary processing module, 6, a contour middle-stage processing module, 7 and a contour final-stage processing module.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1, a system for accurately detecting a slope by a blurred edge includes:
the detection piece 1 is arranged on a side slope and used for shooting by the shooting module 2;
the shooting module 2 is used for shooting images of the detection piece 1 arranged on the side slope;
the median filtering processing module 3 is used for adjusting the image saturation, then carrying out image binarization and carrying out median filtering processing;
the contour extraction module 4 is used for carrying out contour extraction after carrying out edge detection and expansion processing on the image;
the outline primary processing module 5 is used for generating a plurality of regular rectangles at the outline edge of the image, and generating a circle by taking the center of the regular rectangle as the center of the circle and the side length of the regular rectangle as the diameter;
the contour middle-level processing module 6 is used for calculating the number of coincidences of the circles generated in the contour primary processing module 5 and the edge detection key points, connecting the edge detection key points and the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S;
and the contour final-stage processing module 7 is used for filtering the set S, identifying each S in the filtered set S and then finding the center point again.
The median filtering process in the median filtering process module 3 specifically includes:
generating a filtering template, and sequencing pixel values in the template to generate a two-dimensional data sequence which monotonically rises or falls, wherein the two-dimensional median filtering output is g (x, y) ═ medf { f (x-k, y-1), (k, l ∈ w) }, wherein f (x, y) and g (x, y) are an original image and an image after image saturation adjustment respectively, and w is an input two-dimensional template;
odd numbers of data are fetched from a two-dimensional template in the image for sorting, and the sorted median value is used for replacing the data to be processed.
The edge detection in the contour extraction module 4 is specifically:
applying gaussian filtering to smooth the image to remove noise;
finding an intensity gradient of the image;
applying non-maximum suppression to eliminate edge false detection;
applying a dual threshold to determine possible boundaries;
the boundaries are tracked using hysteresis.
The filtering of the set S in the contour final processing module 7 specifically includes:
calculating the average value S1 of S in the set S, filtering out S which is larger than the average value S1 in the set S, and filtering out S with the least frequency of occurrence in the set S.
The identification of each S in the set S in the contour final processing module 7 is specifically:
a ═ avg (abs (s)), where avg denotes the average value and abs denotes the absolute value.
Example 2
As shown in fig. 2, a method for accurately detecting a slope by a blurred edge includes the following steps:
s1, installing a detection piece on the slope to be detected;
s2, shooting an image of a detection piece on the side slope;
s3, adjusting the image saturation, then carrying out image binarization and carrying out median filtering processing;
s4, carrying out edge detection and expansion processing on the image, and then carrying out contour extraction, wherein the purpose of the expansion processing is mainly to communicate the similar contour points and smooth the edges;
s5, generating a plurality of positive rectangles at the edge of the outline of the image, and generating a circle by taking the center of the positive rectangle as the center of a circle and the side length of the positive rectangle as the diameter;
s6, calculating the number of coincided circles and edge detection key points, connecting the edge detection key points with the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S;
and S7, filtering the set S, identifying each S in the filtered set S, and then finding the center point again.
The median filtering is specifically:
generating a filtering template, and sequencing pixel values in the template to generate a two-dimensional data sequence which monotonically rises or falls, wherein the two-dimensional median filtering output is g (x, y) ═ medf { f (x-k, y-1), (k, l ∈ w) }, wherein f (x, y) and g (x, y) are an original image and an image after image saturation adjustment respectively, and w is an input two-dimensional template;
odd numbers of data are fetched from a two-dimensional template in the image for sorting, and the sorted median value is used for replacing the data to be processed.
The edge detection of the image specifically comprises the following steps:
applying gaussian filtering to smooth the image to remove noise;
finding an intensity gradient of the image;
applying non-maximum suppression to eliminate edge false detection;
applying a dual threshold to determine possible boundaries;
the boundaries are tracked using hysteresis.
The filtering set S specifically includes:
calculating the average value S1 of S in the set S, filtering out S which is larger than the average value S1 in the set S, and filtering out S with the least frequency of occurrence in the set S.
The specific identification of each S in the set S is as follows:
a ═ avg (abs (s)), where avg denotes the average value and abs denotes the absolute value.
And generating a clear edge profile according to the center point found again in the step S7, so as to facilitate the determination of the position of the detecting element on the image, and observing whether the position of the detecting element on the image is changed compared with the original position, if the position of the detecting element on the image is changed, it indicates that the slope has landslide and the like.
The above-mentioned embodiments only express the specific embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (8)
1. A system for accurately detecting a side slope by blurred edges, comprising:
the detection piece (1) is arranged on a side slope and used for shooting by the shooting module (2);
the shooting module (2) is used for shooting an image of the detection piece (1) arranged on the side slope;
the median filtering processing module (3) is used for adjusting the image saturation, then carrying out image binarization and carrying out median filtering processing;
the contour extraction module (4) is used for carrying out contour extraction after carrying out edge detection and expansion processing on the image;
the outline primary processing module (5) is used for generating a plurality of positive rectangles at the outline edges of the image, and generating circles by taking the centers of the positive rectangles as the circle centers and the side lengths of the positive rectangles as the diameters;
the contour middle-level processing module (6) is used for calculating the number of coincided circles generated in the contour primary processing module (5) and edge detection key points, connecting the edge detection key points and the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S;
and the contour final-stage processing module (7) is used for filtering the set S, identifying each S in the filtered set S and then finding the center point again.
2. The system for accurately detecting a slope according to the blurred edge, as set forth in claim 1, wherein the edge detection in the contour extraction module (4) is specifically: applying gaussian filtering to smooth the image to remove noise; finding an intensity gradient of the image; applying non-maximum suppression to eliminate edge false detection; applying a dual threshold to determine possible boundaries; the boundaries are tracked using hysteresis.
3. The system for edge-obscuring accurate slope detection according to claim 1, wherein the contour final processing block (7) filters the set S by: calculating the average value S1 of S in the set S, filtering out S which is larger than the average value S1 in the set S, and filtering out S with the least frequency of occurrence in the set S.
4. The system for edge-obscuring accurate slope detection according to claim 1, wherein the contour final processing block (7) identifies each S in the set S by: a ═ avg (abs (s)), where avg denotes the average value and abs denotes the absolute value.
5. A method for accurately detecting a slope by fuzzy edges is characterized by comprising the following steps:
s1, installing a detection piece on the slope to be detected;
s2, shooting an image of a detection piece on the side slope;
s3, adjusting the image saturation, then carrying out image binarization and carrying out median filtering processing;
s4, carrying out edge detection and expansion processing on the image and then carrying out contour extraction;
s5, generating a plurality of positive rectangles at the edge of the outline of the image, and generating a circle by taking the center of the positive rectangle as the center of a circle and the side length of the positive rectangle as the diameter;
s6, calculating the number of coincided circles and edge detection key points, connecting the edge detection key points with the circle center to form a straight line, extending the straight line, recording the distance between the intersection point of the extension line and the circle edge as S, and obtaining a set S according to all S;
and S7, filtering the set S, identifying each S in the filtered set S, and then finding the center point again.
6. The method for accurately detecting the slope by the blurred edge according to claim 5, wherein the edge detection of the image specifically comprises: applying gaussian filtering to smooth the image to remove noise; finding an intensity gradient of the image; applying non-maximum suppression to eliminate edge false detection; applying a dual threshold to determine possible boundaries; the boundaries are tracked using hysteresis.
7. The method for accurately detecting the slope by the blurred edge according to claim 5, wherein the filtering set S specifically comprises: calculating the average value S1 of S in the set S, filtering out S which is larger than the average value S1 in the set S, and filtering out S with the least frequency of occurrence in the set S.
8. The method for accurately detecting the slope by the blurred edge according to claim 5, wherein the step of identifying each S in the set S specifically comprises the steps of: a ═ avg (abs (s)), where avg denotes the average value and abs denotes the absolute value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110572155.2A CN113344955B (en) | 2021-05-25 | 2021-05-25 | System and method for accurately detecting slope by fuzzy edge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110572155.2A CN113344955B (en) | 2021-05-25 | 2021-05-25 | System and method for accurately detecting slope by fuzzy edge |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113344955A CN113344955A (en) | 2021-09-03 |
CN113344955B true CN113344955B (en) | 2022-03-18 |
Family
ID=77471330
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110572155.2A Active CN113344955B (en) | 2021-05-25 | 2021-05-25 | System and method for accurately detecting slope by fuzzy edge |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113344955B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361605A (en) * | 2014-12-10 | 2015-02-18 | 天津普达软件技术有限公司 | Method for detecting outer contour defects of blank bottle mouths |
CN110070557A (en) * | 2019-04-07 | 2019-07-30 | 西北工业大学 | A kind of target identification and localization method based on edge feature detection |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6463593B2 (en) * | 2015-11-02 | 2019-02-06 | コグネックス・コーポレイション | System and method for detecting lines in a vision system |
CN106169186A (en) * | 2016-07-01 | 2016-11-30 | 西安电子科技大学 | Based on the method obtaining initial profile in level set moving object detection |
CN107123146A (en) * | 2017-03-20 | 2017-09-01 | 深圳市华汉伟业科技有限公司 | The mark localization method and system of a kind of scaling board image |
CN110307790A (en) * | 2019-07-04 | 2019-10-08 | 深圳市富源信息技术有限公司 | Camera shooting machine detecting device and method applied to safety monitoring slope |
JP7341808B2 (en) * | 2019-09-11 | 2023-09-11 | キヤノン株式会社 | Image reading device and its control method |
CN112819845B (en) * | 2021-02-26 | 2023-10-27 | 华南理工大学 | Flexible package substrate contour, line width and line distance defect detection method, medium and equipment |
-
2021
- 2021-05-25 CN CN202110572155.2A patent/CN113344955B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361605A (en) * | 2014-12-10 | 2015-02-18 | 天津普达软件技术有限公司 | Method for detecting outer contour defects of blank bottle mouths |
CN110070557A (en) * | 2019-04-07 | 2019-07-30 | 西北工业大学 | A kind of target identification and localization method based on edge feature detection |
Also Published As
Publication number | Publication date |
---|---|
CN113344955A (en) | 2021-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109146860B (en) | Full-automatic mechanical equipment installation leakage detection method and device | |
CN111080582B (en) | Method for detecting defects of inner and outer surfaces of workpiece | |
JPH07302328A (en) | Method for extracting area of moving object based upon background difference | |
CN111489337B (en) | Automatic optical detection pseudo defect removal method and system | |
CN106645209B (en) | Detection method and system for key silk-screen printing | |
CN109781737B (en) | Detection method and detection system for surface defects of hose | |
CN108288274B (en) | Mold detection method and device and electronic equipment | |
CN108889635B (en) | Online visual inspection method for manufacturing defects of ring-pull cans | |
CN105957300B (en) | A kind of wisdom gold eyeball identification is suspicious to put up masking alarm method and device | |
CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
CN117455917B (en) | Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method | |
CN113344955B (en) | System and method for accurately detecting slope by fuzzy edge | |
JPH08189904A (en) | Surface defect detector | |
JP3635795B2 (en) | Method and apparatus for detecting fine line defects | |
KR102133330B1 (en) | Apparatus and method for recognizing crack in sturcutre | |
CN117036259A (en) | Metal plate surface defect detection method based on deep learning | |
JPH08171689A (en) | Changed area detector | |
CN115018829A (en) | Glass flaw positioning method and device | |
CN110634124A (en) | Method and equipment for area detection | |
JP2000003436A (en) | Device and method for recognizing isar picture | |
CN114862786A (en) | Retinex image enhancement and Ostu threshold segmentation based isolated zone detection method and system | |
CN112419296A (en) | Micro-nano optical element surface defect detection method and image segmentation method | |
JPH0217832B2 (en) | ||
JP2021190515A (en) | Workpiece left-over determination system | |
JP2711649B2 (en) | Surface scratch detection method for inspection object |
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 |