CN114972166A - Aggregate grading data statistical method based on visual inspection image - Google Patents
Aggregate grading data statistical method based on visual inspection image Download PDFInfo
- Publication number
- CN114972166A CN114972166A CN202210297303.9A CN202210297303A CN114972166A CN 114972166 A CN114972166 A CN 114972166A CN 202210297303 A CN202210297303 A CN 202210297303A CN 114972166 A CN114972166 A CN 114972166A
- Authority
- CN
- China
- Prior art keywords
- aggregate
- image
- equivalent
- interval
- calculating
- 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.)
- Pending
Links
- 238000011179 visual inspection Methods 0.000 title claims abstract description 20
- 238000007619 statistical method Methods 0.000 title claims abstract description 14
- 239000002245 particle Substances 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000003709 image segmentation Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000005192 partition Methods 0.000 claims abstract description 7
- 230000000007 visual effect Effects 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 19
- 238000005303 weighing Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06T7/0002—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
- G06T7/12—Edge-based segmentation
-
- 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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an aggregate grading data statistical method based on visual inspection images, which comprises the following steps: a camera collects visual inspection image data of aggregate on line and inputs the data into edge equipment; an image processing system of the edge device preprocesses an input visual detection image, divides the preprocessed image and outputs an image division result; based on the image segmentation result, obtaining a contour map of each aggregate, calculating the Feret diameter of the contour map of each aggregate, and calculating to obtain an equivalent ellipse and an equivalent ellipsoid of the contour map of each aggregate; calculating the equivalent volume of each aggregate, carrying out grading statistics according to the interval j to obtain the partition screen residue percentage of the interval j, and then calculating to obtain the accumulated screen residue percentage of all the aggregates. The invention provides an acquisition and calculation method for an equivalent ellipse and an equivalent ellipsoid of an aggregate, which can efficiently acquire the particle size and volume information of the detected aggregate and improve the accuracy of data through calibration of a correction coefficient.
Description
Technical Field
The invention belongs to the technical field of image data processing, and particularly relates to an aggregate gradation data statistical method based on visual inspection images.
Background
And a plurality of information of each aggregate in the sand aggregate particle size section image can be obtained by utilizing a digital image processing technology. Such as: the particle size, perimeter, area, equivalent diameter, shape factor, squareness, circularity, centroid position coordinates and the like of the aggregate.
In the existing aggregate grading data generation method, for aggregate volume calculation, volume information is obtained through data of a 3D camera in an integral mode, and the requirement on equipment is high; in addition, data such as length, width and the like are obtained by performing rectangular fitting on the two-dimensional image profile of the aggregate, and the accuracy of the obtained particle size data of the aggregate is poor.
Disclosure of Invention
The invention aims to provide an aggregate grading data statistical method based on visual detection images to improve the accuracy of aggregate grading data statistics.
The invention is realized in such a way, and provides an aggregate gradation data statistical method based on visual inspection images, which comprises the following steps:
the method comprises the following steps that a camera collects visual inspection image data of aggregate on line and inputs the visual inspection image data into edge equipment;
an image processing system of the edge device preprocesses an input visual detection image, divides the preprocessed image and outputs an image division result;
based on the image segmentation result, obtaining a contour map of each aggregate, calculating the Feret diameter of the contour map of each aggregate, and calculating to obtain an equivalent ellipse and an equivalent ellipsoid of the contour map of each aggregate;
dividing an interval j according to the particle size of aggregate particles, wherein j is 1, 2, … … and 9, and calibrating a correction coefficient k of grading statistics according to the interval j j ；
Calculating the equivalent volume of each aggregate, carrying out grading statistics according to the interval j to obtain the partition screen residue percentage of the interval j, and then calculating to obtain the accumulated screen residue percentage of all the aggregates.
Further, the maximum Feret diameter of the Feret diameters is d f max Minimum Feret diameter of d f min The major axis a ═ d of the equivalent ellipse of the aggregate contour map f max Minor axis
And S is the aggregate projection area, and the number of pixel points occupied by the aggregates in the binary image of the image segmentation result is used as the aggregate projection area.
Further, the correction coefficient k j The calculation method of (2) is as follows:
randomly extracting equal aggregate samples, and calculating the total volume V of all aggregates in each interval j by using a weighing method and a density method cj ，j＝1， 2，……，9；
Obtaining the major axis a of the equivalent ellipse for each aggregate sample ji And a minor axis b ji Calculating a correction coefficient k for each interval j j ，
In the formula, each boneThe volume of the equivalent ellipsoid of the material is
n j Is the total particle number of the aggregate sample in the jth interval.
Further, the equivalent volume V of a single aggregate j,i The calculation is as follows:
the partition percent screen residue is calculated by the following formula:
in the formula M j,i Is the mass of the ith aggregate in the jth interval.
Further, calculating to obtain the equivalent maximum length-diameter ratio of the single aggregate
Further, the interval j is [0, 9.5], [9.5, 16], [16, 19], [19, 26.5], [26.5, 31.5], [31.5, 37.5], [37.5, 63], [63, 75], [75, + ∞ ] in the order of mm.
Compared with the prior art, the aggregate grading data statistical method based on the visual detection image is based on the two-dimensional visual detection image, provides an acquisition and calculation method for the equivalent ellipse and the equivalent ellipsoid of the aggregate, can efficiently acquire the particle size and volume information of the detected aggregate, and improves the accuracy of the data through calibration of the correction coefficient.
Drawings
FIG. 1 is a schematic flow chart of an aggregate grading data statistical method based on visual inspection images according to the present invention;
FIG. 2 is a schematic diagram of a Feret diameter calculation method of an equivalent ellipse in the process of FIG. 1;
FIG. 3 is a schematic diagram of the calculation of the major and minor axes of the equivalent ellipse of FIG. 2;
FIG. 4 is a schematic diagram of the formation of an equivalent ellipsoid in FIG. 1;
FIG. 5 is the standard regulation of particle size distribution of pebbles and crushed stones in the national Standard GB/T14685-2011 construction pebbles and crushed stones.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Referring to fig. 1 to 4, the present invention discloses an aggregate gradation data statistical method based on visual inspection images, which includes the following steps:
the method comprises the following steps that a camera collects visual inspection image data of aggregate on line and inputs the visual inspection image data into edge equipment;
an image processing system of the edge device preprocesses an input visual detection image, divides the preprocessed image and outputs an image division result;
based on the image segmentation result, obtaining a contour map of each aggregate, calculating the Feret diameter of the contour map of each aggregate, and calculating to obtain an equivalent ellipse and an equivalent ellipsoid of the contour map of each aggregate;
dividing an interval j according to the particle size of aggregate particles, wherein j is 1, 2, … … and 9, and calibrating a correction coefficient k of grading statistics according to the interval j j ；
And calculating the equivalent volume of each aggregate, carrying out grading statistics according to the interval j to obtain the partition screen residue percentage of the interval j, and calculating to obtain the accumulated screen residue percentage of all the aggregates.
Specifically, the aggregate grading data statistical method based on the visual inspection image comprises the following steps:
(1) image acquisition and input
When the aggregate conveying belt is used, the computer program sends out an instruction, and the camera is instructed to collect the aggregate images on the aggregate conveying belt at regular time and input the aggregate images into a designated area of the computer.
(2) Image data pre-processing
And the edge equipment performs histogram equalization processing on the collected aggregate image. The histogram equalization processing is a method for enhancing the contrast of an image, and the main idea is to make the histogram distribution of the image more uniform, so that the obtained image is clearer compared with the original image.
Histogram equalization is a transformation based on a probability density function of a random variable, and widens the number of gray levels having a large number of pixels in an image, and reduces the number of gray levels having a small number of pixels. Firstly, the gray level r in the image is counted k Probability of occurrence:
where L is the gray level of the image, the transform function is:
the gray level in the image being r k Is mapped to s k In (1).
After histogram equalization processing is carried out on the aggregate image, min-max standardization processing is carried out on pixel values in the image to be processed, and the principle is that linear transformation is carried out on the pixel values in the image, and the values are mapped to the positions between [0 and 1 ]. The formula is as follows: new pixel value ═ original pixel value-minimum pixel value)/(maximum pixel value-minimum pixel value).
Such as: for sequence x 1 ，x 2 ，......，x n And (3) carrying out transformation:
then the new sequence y 1 ，y 2 ，......，y n ∈[0，1]And is dimensionless.
(3) Image segmentation processing
And obtaining an image segmentation result of each aggregate in the image based on a trained improved Cascade Mask R-CNN image segmentation algorithm.
(4) Calculation of particle size and shape
And carrying out contour recognition based on the binary image of the image segmentation result to obtain a contour image of each aggregate. Polygonal fitting is carried out on the aggregate contour map, and the distance between two parallel lines tangent to the aggregate image is taken every 10 degrees of rotation of the parallel lines (by d) f Expressed), the maximum distance between parallel lines is taken as the maximum Feret diameter (in d) f,max Expressed), the minimum distance is recorded as the minimum Feret diameter (in d) f,min Representation).
And obtaining all pixel points of each aggregate based on the contour correction graph. In the binary image, the number of pixel points occupied by the aggregates is directly calculated to be used as the projection area S of the aggregates. Calculating the equivalent ellipse Feret minor diameter b based on the following formula:
calculating the equivalent maximum length-diameter ratio of the aggregate:
(5) grading statistics
According to the relevant standards, as shown in fig. 5, the aggregate can be divided into the following 9 intervals according to the particle size: [0, 9.5], [9.5, 16], [16, 19], [19, 26.5], [26.5, 31.5], [31.5, 37.5], [37.5, 63], [63, 75], [75, + ∞ ], in mm.
(5.1) calibration of correction factor
In the gradation statistics, the correction coefficient k needs to be calibrated at fixed time j . Correction coefficient k j The equivalent ellipse of the aggregate is converted into an equivalent ellipsoid, and the equivalent ellipsoid is corrected according to 9 intervals of the particle size. The method comprises the following specific steps:
based on a two-dimensional image method, the aggregate is equivalent to an ellipse, and a major axis a and a minor axis b of the equivalent ellipse are obtained, as shown in fig. 3, and an equivalent ellipsoid of the aggregate is further obtained based on the equivalent ellipse, as shown in fig. 4.
Suppose that
c＝κ·b
Where κ is a correction coefficient. Correction coefficient κ for segment j (j being 1, 2, … …, 9) j The calibration test and calculation method of (2) is as follows:
1) sampling from a belt conveyor, and randomly extracting 8 parts of stones with approximately equal quantity from the full section by using a container with the same width as the belt at the discharge position of the head of the belt conveyor through a material receiver to form a group of aggregate samples. Based on a weighing method and combined with a density method (the density can be calculated by adopting the volume of discharged water), obtaining all the volumes of 9 intervals, and calculating the total volume V of all the aggregates in each interval j cj (j＝1，2，……，9)。
2) For the aggregate sample in the step 1), obtaining the long axis a of the equivalent ellipse of the aggregate based on a two-dimensional image method ji And a minor axis b ji (j is the jth interval, j is 1, 2, … …, 9; i is the ith aggregate of the jth interval, i is 1, 2, … …, n j ) And the correction coefficient for each interval j is calculated,
wherein the volume of the equivalent ellipsoid of each aggregate is
n j Is the total particle number of the aggregate sample in the jth interval.
(5.2) equivalent volume V j,i Computing and grading statistics
Based on a two-dimensional image method and a correction method, the equivalent volume V of a single aggregate can be calculated j,i The calculation is as follows:
further, the percent rejects of the particle grading zone may be calculated as the ratio of the weight of all aggregates i in the current interval j to the total weight of aggregates in all intervals j. The partition percent screen residue is calculated by the following formula:
in the formula, M j,i Is the mass of the ith aggregate in the jth interval.
From the fractional percent sift of the particle grading interval j, a cumulative percent sift, i.e., a cumulative value of percent sift for each interval, may be calculated.
(6) Statistical result display
And visually displaying the aggregate grading data statistical result on the cloud platform through a computer program.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. An aggregate grading data statistical method based on visual inspection images is characterized by comprising the following steps:
the method comprises the following steps that a camera collects visual inspection image data of aggregate on line and inputs the visual inspection image data into edge equipment;
an image processing system of the edge device preprocesses an input visual detection image, divides the preprocessed image and outputs an image division result;
based on the image segmentation result, obtaining a contour map of each aggregate, calculating the Feret diameter of the contour map of each aggregate, and calculating to obtain an equivalent ellipse and an equivalent ellipsoid of the contour map of each aggregate;
dividing the interval j into 1, 2, … …, 9 according to the particle size of aggregate particles, and marking the interval jCorrection coefficient k of grading statistics j ；
Calculating the equivalent volume of each aggregate, carrying out grading statistics according to the interval j to obtain the partition screen residue percentage of the interval j, and then calculating to obtain the accumulated screen residue percentage of all the aggregates.
2. The visual inspection image-based aggregate grading data statistical method of claim 1, wherein the maximum Feret diameter of the Feret diameters is d f max Minimum Feret diameter of d f min The major axis a ═ d of the equivalent ellipse of the aggregate contour map f max Minor axis
And S is the aggregate projection area, and the number of pixel points occupied by the aggregates in the binary image of the image segmentation result is used as the aggregate projection area.
3. The visual inspection image-based aggregate grading data statistical method of claim 2, wherein the correction coefficient k is j The calculation method of (2) is as follows:
randomly extracting equal amount of aggregate samples, and calculating the total volume V of all aggregates in each interval j by using a weighing method and a density method cj ，j＝1，2，……，9；
Obtaining the major axis a of the equivalent ellipse for each aggregate sample ji And a minor axis b ji Calculating a correction coefficient k for each section j j ，
Wherein the volume of the equivalent ellipsoid of each aggregate is
n j Is the total particle number of the aggregate sample in the jth interval.
4. The method of claim 3, wherein the aggregate grading data statistics based on visual inspection image,
equivalent volume V of single aggregate j,i The calculation is as follows:
the partition percent screen residue is calculated by the following formula:
in the formula M j,i Is the mass of the ith aggregate in the jth interval.
5. The aggregate gradation data statistical method based on visual inspection image as claimed in claim 2, wherein the equivalent maximum length to diameter ratio of single aggregate is calculated
6. The method of claim 1, wherein the interval j is [0, 9.5], [9.5, 16], [16, 19], [19, 26.5], [26.5, 31.5], [31.5, 37.5], [37.5, 63], [63, 75], [75, + ∞ ] in the order of mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297303.9A CN114972166A (en) | 2022-03-24 | 2022-03-24 | Aggregate grading data statistical method based on visual inspection image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297303.9A CN114972166A (en) | 2022-03-24 | 2022-03-24 | Aggregate grading data statistical method based on visual inspection image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114972166A true CN114972166A (en) | 2022-08-30 |
Family
ID=82976004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210297303.9A Pending CN114972166A (en) | 2022-03-24 | 2022-03-24 | Aggregate grading data statistical method based on visual inspection image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114972166A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN210136151U (en) * | 2019-05-10 | 2020-03-10 | 华侨大学 | Machine-made sand quality detection equipment |
| CN110969608A (en) * | 2019-11-29 | 2020-04-07 | 华侨大学 | Machine-made sand gradation correction system based on image method |
| CN112611690A (en) * | 2020-12-04 | 2021-04-06 | 华侨大学 | Coarse aggregate equivalent particle size grading method based on three-dimensional image |
| CN113987750A (en) * | 2021-09-27 | 2022-01-28 | 太原理工大学 | Three-dimensional microscopic model modeling method for full-graded concrete containing random defects |
-
2022
- 2022-03-24 CN CN202210297303.9A patent/CN114972166A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN210136151U (en) * | 2019-05-10 | 2020-03-10 | 华侨大学 | Machine-made sand quality detection equipment |
| CN110969608A (en) * | 2019-11-29 | 2020-04-07 | 华侨大学 | Machine-made sand gradation correction system based on image method |
| CN112611690A (en) * | 2020-12-04 | 2021-04-06 | 华侨大学 | Coarse aggregate equivalent particle size grading method based on three-dimensional image |
| CN113987750A (en) * | 2021-09-27 | 2022-01-28 | 太原理工大学 | Three-dimensional microscopic model modeling method for full-graded concrete containing random defects |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110118775B (en) | Method for rapidly detecting composition of plant-mixed cement stabilized macadam aggregate | |
| CN105510195B (en) | A kind of granularity particle shape online test method for stacking aggregate | |
| CN109978839B (en) | Method for detecting wafer low-texture defects | |
| Cox et al. | A practical approach to grain shape quantification | |
| CN116664559B (en) | Machine vision-based memory bank damage rapid detection method | |
| CN107437068B (en) | Pig individual identification method based on Gabor direction histogram and pig body hair mode | |
| CN114324078A (en) | Particle size identification method, device, equipment and medium | |
| CN108182674B (en) | Granularity detection analysis method based on U-Net deep learning network | |
| CN114694144B (en) | Intelligent identification and rating method for non-metallic inclusions in steel based on deep learning | |
| CN113706566B (en) | Edge detection-based perfuming and spraying performance detection method | |
| CN114596551A (en) | Vehicle-mounted forward-looking image crack detection method | |
| CN104978738A (en) | Method of detection of points of interest in digital image | |
| CN116246174B (en) | Sweet potato variety identification method based on image processing | |
| CN109410139A (en) | Inside a kind of historical relic and surface disease digital assay appraisal procedure | |
| CN110501268A (en) | A kind of micro dust detection method based on Micrograph image processing | |
| CN115115627A (en) | Soil saline-alkali soil monitoring method based on data processing | |
| CN117635615B (en) | Defect detection method and system for realizing punching die based on deep learning | |
| Chen et al. | Image analysis algorithm and verification for on-line molecular sieve size and shape inspection | |
| CN107369163B (en) | Rapid SAR image target detection method based on optimal entropy dual-threshold segmentation | |
| CN114972166A (en) | Aggregate grading data statistical method based on visual inspection image | |
| CN107024416A (en) | With reference to similitude and the quasi-circular particle mean size detection method of discontinuity | |
| CN108846839B (en) | Sagger crack detection method based on sector neighborhood difference histogram | |
| CN108805896B (en) | Distance image segmentation method applied to urban environment | |
| CN108615240B (en) | Non-parametric Bayesian over-segmentation method combining neighborhood information and distance weight | |
| CN114821165A (en) | Track detection image acquisition and analysis 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 |