CN112613531A - Soil and rock classification method and device based on image processing - Google Patents
Soil and rock classification method and device based on image processing Download PDFInfo
- Publication number
- CN112613531A CN112613531A CN202011336766.9A CN202011336766A CN112613531A CN 112613531 A CN112613531 A CN 112613531A CN 202011336766 A CN202011336766 A CN 202011336766A CN 112613531 A CN112613531 A CN 112613531A
- Authority
- CN
- China
- Prior art keywords
- soil
- image
- gradient
- rock
- circuit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000002689 soil Substances 0.000 title claims abstract description 114
- 239000011435 rock Substances 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012545 processing Methods 0.000 title claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 42
- 238000005070 sampling Methods 0.000 claims abstract description 39
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 38
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 15
- 230000003321 amplification Effects 0.000 claims description 8
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 239000004927 clay Substances 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 16
- 239000004575 stone Substances 0.000 description 15
- 238000010586 diagram Methods 0.000 description 13
- 238000000605 extraction Methods 0.000 description 8
- 239000002245 particle Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000011120 plywood Substances 0.000 description 5
- 230000010355 oscillation Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000003990 capacitor Substances 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004061 bleaching Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000006056 electrooxidation reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/02—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance
- G01N27/04—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance by investigating resistance
- G01N27/048—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance by investigating resistance for determining moisture content of the material
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Electrochemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a soil and rock classification method and device based on image processing, and belongs to the technical field of image processing. In the design of the automatic soil and rock classification method, the image is subjected to unsupervised clustering secondary classification based on the gradient sampling duty ratio of the image, and primary classification is completed. In soil subdivision, a soil water content detection circuit is combined, and the soil water content is utilized to distinguish silty clay from plain filling soil. In the rock subdivision, a quantitative profile feature set is provided to represent the texture complexity of the rock images, and unsupervised clustering secondary classification is carried out through the texture complexity to realize secondary classification of rocks; and further, a profile estimation feature set is provided to represent the similarity between the shape of the object and the circle, and unsupervised clustering and secondary classification are carried out to realize tertiary classification of the rock. The invention can automatically complete the fine classification identification of soil and rock according to the sampling image, and has the advantages of rapid and efficient classification and low requirement on hardware.
Description
Technical Field
The invention relates to an image processing technology, in particular to a scheme for classifying soil and rocks by utilizing the image processing technology.
Background
For a construction scene, different construction modes exist for different geological landforms, so that the construction environment needs to be detected and evaluated first.
The detection and evaluation is firstly distinguished by manually excavating and sampling, and the categories of the environmental soil and the rock are identified, but the method is time-consuming, labor-consuming and low in accuracy.
With the continuous update of the image processing technology, soil or rock of the sample can be more accurately identified and classified by means of the image processing. However, most existing classification solutions complete the identification of soil or rock by machine learning/deep learning, for example, CN110261330A discloses a rock classification constraint inheritance loss method for a rock identification deep learning model. The method needs to collect a huge sample set, and needs to accurately define the category of the sample, otherwise, the classifier is affected, and in addition, the calculation amount of the method is large. Moreover, most of the existing methods can only realize the identification and classification of one of soil or rock.
Disclosure of Invention
The invention aims to: in view of the existing problems, a soil and rock classification method based on image processing is provided to provide a solution capable of automatically performing fine classification on soil/rock in an image.
The technical scheme adopted by the invention is as follows:
a soil and rock classification method comprises the following steps: A. respectively executing the following processing to each collected original image: carrying out first preprocessing on the collected original image to obtain a corresponding first binarized image; calculating the transverse and longitudinal gradients of the first binarized image, and calculating the gradient sampling duty ratio corresponding to the original image according to the transverse and longitudinal gradients; B. carrying out unsupervised clustering secondary classification on the gradient sampling duty ratio corresponding to each original image, and classifying the environment corresponding to each original image into a soil class and a rock class at one time; c, performing secondary classification on the soil class, and D, performing secondary classification on the rock class; C. classifying the soil corresponding to the original image according to the water content of the soil corresponding to the original image; D. carrying out unsupervised clustering secondary classification on the texture complexity of the original image, and secondarily classifying rocks corresponding to the original image into first-class rocks and second-class rocks; for the first type of rocks, performing step E to perform three times of classification; E. and carrying out second preprocessing on the original image to obtain a corresponding second binary image, and carrying out unsupervised clustering secondary classification on the rock corresponding to the original image by taking the connected domain ratio and the centroid boundary distance chaos of the second binary image as characteristics.
Further, the method for calculating the gradient sampling duty ratio comprises the following steps: equidistant sampling of rows/columns of the horizontal/vertical gradient; respectively calculating the ratio of gradient information points of sampling rows/columns to the number of information points in the rows/columns; and carrying out unsupervised clustering secondary classification on the ratio of the sampling rows/columns, and taking the class with a large number of clusters as the gradient sampling duty ratio corresponding to the original image.
Furthermore, step C utilizes soil water content detection circuit to detect the water content of soil, soil water content detection circuit includes square wave signal generating circuit, sensing circuit, rectifier circuit, filter circuit, correction circuit, amplifier circuit and display circuit, square wave signal generating circuit, sensing circuit, rectifier circuit and filter circuit connect gradually, soil water content detection circuit's power is connected to correction circuit's input, filter circuit with correction circuit's output is connected respectively amplifier circuit's two inputs, amplifier circuit's output is connected display circuit.
Further, the texture complexity comprises three characteristics of contour complexity, a transverse curvature coefficient and a longitudinal curvature coefficient; the method for calculating the complexity of the contour comprises the following steps: combining the transverse gradient and the longitudinal gradient of the original image into a gradient map, traversing the gradient map, counting the total number of points with pixel values not being zero, and representing the contour complexity by the proportion of the total number of the points with pixel values not being zero to the total pixel points of the gradient map; the transverse curvature coefficient is obtained by calculating the curvature of the transverse gradient of the original image; the longitudinal curvature coefficient is obtained by calculating the curvature of the longitudinal gradient of the original image.
Further, the calculating the curvature of the transverse gradient of the original image includes: binarizing the transverse gradient of the original image to obtain a transverse gradient image; filtering the transverse gradient image to filter out a connected region with an area smaller than a first threshold value; calculating the curvature of the filtered transverse gradient image to obtain a transverse curvature map; and taking the variance value of the points of which the pixel points are not zero in the transverse curvature map as a transverse curvature coefficient.
Further, the calculating the curvature of the longitudinal gradient of the original image includes: binarizing the longitudinal gradient of the original image to obtain a longitudinal gradient image; filtering the longitudinal gradient image to filter out a connected region with an area smaller than a second threshold value; calculating the curvature of the filtered longitudinal gradient image to obtain a longitudinal curvature map; and taking the variance value of the points of which the pixel points are not zero in the longitudinal curvature map as a longitudinal curvature coefficient.
Further, the second preprocessing is performed on the original image to obtain a corresponding second binary image, including: carrying out first preprocessing on an original image to obtain a corresponding first binarized image; and calculating a connected region in the first binarized image, filtering the connected region with the area smaller than a third threshold value in the first binarized image, and opening the rest part to obtain a second binarized image.
Further, the connected domain proportion is the area ratio of each connected domain area to the corresponding minimum frame selection rectangle in the second binarized image.
Further, the method for calculating the centroid boundary distance chaos comprises the following steps: extracting the outline of a connected domain in each minimum framing rectangle in the second binary image; and calculating Euclidean distances from each point on the outline of each connected domain to the centroid, and taking the variance value of each Euclidean distance as the confusion degree of the centroid boundary distance.
The invention also provides a soil and rock classification device based on image processing, which comprises a processor, a computer readable storage medium and a soil water content detection circuit, wherein the processor is respectively connected with the computer readable storage medium and the soil water content detection circuit; the soil water content detection circuit is used for detecting the water content of soil, and a computer program is stored in the computer readable storage medium; the soil water content detection circuit transmits the detection result to the processor, and the processor runs the computer program to execute the soil and rock classification method.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. the invention can automatically complete the fine classification identification of the soil and the rock according to the sampling image.
2. The scheme of the invention completely accords with the natural properties of soil and rock, and has high classification accuracy.
3. The invention does not need sampling and training in the previous period, can be directly used, has simpler configuration, small calculated amount, quick classification and low requirement on hardware.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
fig. 1 shows an example of a process flow of a soil and rock classification method.
Fig. 2 is a process of first preprocessing an image.
Fig. 3 is a transverse/longitudinal gradient diagram of a soil-like picture and a rock-like picture.
Fig. 4 is a lateral/longitudinal gradient sampling diagram of a soil-type picture and a rock-type picture.
Fig. 5 is one embodiment of a soil moisture content sensing circuit.
FIG. 6 is one embodiment of a soil pressure sensing circuit.
Fig. 7 is a structural view of a soil environment detection system.
FIG. 8 is one embodiment of a display circuit.
Fig. 9 is an overall gradient diagram of a rock class picture.
Fig. 10 is a transverse curvature diagram of a rock class picture.
Fig. 11 is a longitudinal curvature diagram of a rock class picture.
Fig. 12 is a process of second preprocessing of an image.
Fig. 13 is a connected information extraction diagram.
Figure 14 is a schematic of 6 soils/rocks.
Detailed Description
All of the features disclosed in this specification, or all of the steps in any method or process so disclosed, may be combined in any combination, except combinations of features and/or steps that are mutually exclusive.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
The figures in the drawings illustrate:
in fig. 2, (1) an original color image; (2) a grayscale image; (3) a first binary image.
In fig. 3, (1) a lateral gradient map of a soil-like picture; (2) a longitudinal gradient map of the soil class picture; (3) a transverse gradient map of the rock class picture; (4) longitudinal gradient map of rock class image.
In fig. 4, (1) a lateral gradient sampling diagram of a soil-like picture; (2) a transverse gradient sampling diagram of the rock pictures; (3) a transverse gradient sampling graph of the soil class picture; (4) longitudinal gradient sampling diagram of the rock class image.
In fig. 9, (1) a gradient map of the pebble image; (2) gradient map of cobble stone image; (3) a gradient map of a mud, egg and gravel image; (4) gradient map of sandstone inclusion rock image.
In fig. 10, (1) a transverse curvature map of the pebble image; (2) a transverse curvature map of the pebble bleaching stone image; (3) a transverse curvature map of the mud, gravel and stone image; (4) a transverse curvature map of a sandstone clamp rock image.
In fig. 11, (1) a longitudinal curvature map of the pebble image; (2) a longitudinal curvature map of the pebble image; (3) a longitudinal curvature map of the mud, gravel and stone image; (4) longitudinal curvature map of sandstone inclusion rock image.
In fig. 12, (1) a pebble image original color map; (2) a pebble image binary image; (3) filtering an area threshold value of the pebble image; (4) and opening the operation back graph by the pebble image.
In fig. 13, (1) a pebble image connected information extraction map; (2) and (4) extracting the image of the cobble stone image communication information, wherein the blue asterisk is the mass center of each communication area, and the red dotted line rectangular frame is the minimum frame selection rectangle.
The invention discloses a soil and rock classification method based on image processing, which takes two major classes of pebbles, cobble stones, mud-cobble stones and sandstone plywood rocks as two major classes of secondary classification of rocks, takes pebbles and cobble stones as two minor classes of tertiary classification of rocks, and takes silty clay and plain filling soil as a major class of secondary classification of soil for example, and the process is shown in figure 1, and the classification method comprises the following steps:
A. respectively executing the following processing to each collected original image:
A1. and carrying out first preprocessing on the acquired original image to obtain a corresponding first binarized image.
Generally speaking, for an image shot in an environment as a color image (a black-and-white image may lose information), as shown in fig. 2, in a first preprocessing process, an acquired color original image is converted into a gray image, a threshold value for maximizing a gray value difference between two parts of the gray image is found according to an Otsu global threshold determination method, and the gray image is divided into a binary image by applying the threshold value, where the binary image is a first binary image.
A2. And calculating the transverse and longitudinal gradients of the first binarized image, and calculating the gradient sampling duty ratio corresponding to the original image according to the transverse and longitudinal gradients.
The horizontal and vertical gradients of the image represent the difference of the two-dimensional matrix of the image in the horizontal and vertical directions respectively, and can reflect the density degree of the texture of the object in the picture. The image horizontal and longitudinal gradient calculation formula is as formula (1) and (2).
Wherein G isx、GyIs the calculated transverse and longitudinal gradients of the image,f (x, y) represents a pixel value at the image (x, y) position. Fig. 3 shows a transverse and longitudinal gradient diagram of a soil-type picture and a rock-type picture.
The random sampling observation is carried out on the transverse and longitudinal gradients, the transverse (longitudinal) gradients of the soil pictures and the rock pictures are collected in the middle row (column) and compared, and the result is shown in fig. 4. As can be seen from fig. 4, for the soil type picture, the overall density is higher, the edge information calculated by the gradient is more, and the proportion is larger than that of the background (the point where the gradient is 0); and the overall density of the rock images is low, the edge information calculated by the gradient is less, and the occupation ratio of the gradient calculated edge information to the background is small, so that the soil images and the rock images can be distinguished by adopting the gradient sampling duty ratio as a characteristic parameter.
The method for calculating the gradient sampling duty ratio comprises the following steps:
the rows/columns of the transverse gradient are sampled equidistantly. The sampling distance may be set according to the size of the gradient sample map, and in some embodiments, the sampling distance is set to 5.
Respectively calculating the ratio of the gradient information points of the sampling rows/columns to the number of information points in the sampling rows/columns: and calculating the ratio of gradient information points (points with the gradient of 1) to the total number of the points in each row (column) for the sampling row (column), namely the duty ratio, wherein the calculation formulas are shown in formulas (3) and (4).
Wherein, F1i、F2jRespectively representing the duty cycle values of the sampled rows and columns, Fx、FyThe horizontal and vertical images of the image are respectively represented, and m and n respectively represent the row and column numbers of the gradient image.
Carrying out unsupervised clustering secondary classification on the ratio of the sampling rows/columns, and taking the class with a large number of clusters as the gradient sampling duty ratio corresponding to the original image: and carrying out unsupervised clustering with the category of 2 on the sampled row (column) duty ratio values, removing the category with a small number to reduce interference terms caused by image noise or other factors, and taking the category with a large number as the final gradient sampling duty ratio of the image.
B. Carrying out unsupervised clustering secondary classification on the gradient sampling duty ratio corresponding to each original image, and classifying the environment corresponding to each original image into a soil class and a rock class at one time; and C, performing the step C to perform secondary classification on the soil class, and performing the step D to perform secondary classification on the rock class.
The gradient sampling duty ratio of each image is taken as a characteristic of classification. The gradient sampling duty ratio characteristics of 1 image are randomly selected from the soil class and the rock class to serve as initial clustering centers, then the distance between the characteristics of each image and each clustering center is calculated, and the characteristics participating in the current calculation are distributed to the clustering center closest to the characteristics. The cluster centers and the features assigned to them represent a cluster. When a sample (feature) is distributed, the clustering center of the cluster is recalculated according to the existing object in the cluster until the clustering center is not changed any more and the sum of the squares of errors is minimum, and then one-time clustering is completed. And finally, the pictures participating in calculation are gathered into two types (soil type/rock type), so that the two types of soil/rock are classified.
C. And classifying the soil corresponding to the original image according to the water content of the soil corresponding to the original image.
The water content of the soil is detected by using a soil water content detection circuit.
As shown in fig. 7, the soil water content detection circuit includes a square wave signal generation circuit, a sensing circuit, a rectification circuit, a filter circuit, a correction circuit, an amplification circuit and a display circuit, the square wave signal generation circuit, the sensing circuit, the rectification circuit and the filter circuit are connected in sequence, the input end of the correction circuit is connected with the power supply of the soil water content detection circuit, the output ends of the filter circuit and the correction circuit are respectively connected with the two input ends of the amplification circuit, and the output end of the amplification circuit is connected with the display circuit.
The principle of the detection circuit is as follows: the soil moisture content and the soil resistivity are in a linear relation, the oscillation signal is applied to the sensing circuit, the sensing circuit can output a corresponding voltage signal (namely, detection voltage which is reduced along with the increase of the soil moisture content) under the action of the soil resistivity, and the voltage signal is subjected to the action of a subsequent circuit and then is displayed on the display circuit except for a corresponding numerical value. The square wave signal generating circuit of the detection circuit applies an oscillation signal to the sensing circuit, the sensing circuit acts on the soil to be detected, generally speaking, the sensing circuit adopts paired probe circuits, and the two probes are respectively connected with the sensor probe. Under the action of an oscillation signal, an output detection voltage of the sensing circuit sequentially passes through the rectifying circuit and the filter circuit and then is input into the amplifying circuit, the divided voltage is sent to the amplifying circuit by the correcting circuit, the amplifying circuit usually adopts an operational amplifier, the filter circuit is connected to the inverting end of the operational amplifier, the correcting circuit is connected to the non-inverting end of the operational amplifier, and the amplifying circuit outputs an amplified signal to the display circuit for numerical value display. The display circuit is formed by connecting a digital voltmeter and a nixie tube circuit.
In one embodiment, in order to prevent the electrochemical corrosion phenomenon of the probes and reduce the influence of the distributed capacitance between the two probes, the working voltage of the soil water content detection circuit adopts a low-medium frequency oscillation signal, so that the soil water content is mainly proportional to the resistivity of the soil. As shown in FIG. 5, U1 and R are designed2、R3、D1、D2、C2、C3A square wave signal generator with the frequency of 1kHz and formed by the same elements as the working voltage of the detection circuit. The square wave signal passes through a coupling capacitor C4And an adjustable resistance R4Is applied to the detection probe. Current limiting resistor R5And a diode D3、D4The rectifying circuit is configured to reduce the output voltage with an increase in soil moisture. The output voltage is passed through R6And C5The filter circuit is connected to the inverting terminal of U2C through a voltage follower U2A. Resistance R8Potentiometer R9And a voltage follower U2B for performing zero setting and correction on the amplifier circuit, and connected to the output terminal of the amplifier circuitWhen the soil probe is not attached to the in-phase end of the U2C, the voltage of the in-phase input end of the U2B is adjusted, so that the output voltage of the U2C is zero, and the zero setting function is realized. U2C is a differential amplifier whose gain is given by resistor R12/R7And (6) determining. And finally, the output signal of the measuring circuit is transmitted to a digital voltmeter through a voltage follower U2D, and the final output voltage value is displayed, so that the numerical value of the soil moisture content can be directly read. The display circuit is formed by connecting a digital voltmeter and a nixie tube circuit, as shown in fig. 8, the digital voltmeter adopts an ICL7107 to collect analog voltage, the ICL7107 is a double-integration analog-digital converter, and the ICL7107 is a very widely applied integrated circuit and comprises an 31/2-bit digital analog converter, so that the LED nixie tube can be directly driven without a driving circuit. The ICL7107 is internally provided with functions of reference voltage, an independent analog switch, a logic switch, display driving, automatic zero setting and the like. The digital voltmeter can realize the measurement of 0-20V direct current voltage. The nixie tube circuit adopts a MAN6710 nixie tube, the eight-segment type nixie tube MAN6710 adopts a common anode connection method, the nixie tube can display 19.9V voltage at most, and automatic polarity display can be realized by inputting negative voltage.
As shown in fig. 7, this embodiment also discloses a soil environment detecting system, including soil water content detection circuit, soil pressure detection circuit and display circuit, soil water content detection circuit includes square wave signal generating circuit, sensing circuit, rectifier circuit, filter circuit, correction circuit and amplifier circuit, and square wave signal generating circuit, sensing circuit, rectifier circuit and filter circuit connect gradually, soil water content detection circuit's power is connected to correction circuit's input, filter circuit with correction circuit's output is connected respectively amplifier circuit's two input ends, amplifier circuit's output is connected display circuit. The soil pressure detection circuit comprises a bridge circuit and an operational amplifier, two arms of the bridge circuit are respectively connected to two ends of the operational amplifier, and the output end of the operational amplifier is connected with the display circuit.
As shown in FIG. 5, the soil water content detection circuit is designed by U1 and R2、R3、D1、D2、C2、C3A square wave signal generator with the frequency of 1kHz and formed by the same elements as the working voltage of the detection circuit. The square wave signal passes through a coupling capacitor C4And an adjustable resistance R4Is applied to the detection probe. Current limiting resistor R5And a diode D3、D4The rectifying circuit is configured to reduce the output voltage with an increase in soil moisture. The output voltage is passed through R6And C5The filter circuit is connected to the inverting terminal of U2C through a voltage follower U2A. Resistance R8Potentiometer R9And the voltage follower U2B forms a correction circuit, the amplification circuit is subjected to zero setting and correction, the output of the amplification circuit is connected to the in-phase end of U2C, and when the soil probe is not attached, the voltage of the in-phase input end of U2B is adjusted, so that the output voltage of U2C is zero, and the zero setting function is realized. U2C is a differential amplifier whose gain is given by resistor R12/R7And (6) determining. Finally, the output signal of the measuring circuit is supplied to the display circuit via a voltage follower U2D. As shown in fig. 6, the soil pressure detection circuit is a bridge circuit formed by 4 ceramic piezoresistors, two arms of the bridge circuit are respectively connected with two input ends of an operational amplifier LM2904, and an output end of the operational amplifier is connected to a display circuit. The display circuit is formed by connecting a digital voltmeter and a nixie tube circuit, the digital voltmeter adopts ICL7107 to collect analog voltage, the ICL7107 is a double-integral analog-digital converter, the ICL7107 is a very widely applied integrated circuit, the ICL7107 comprises an 31/2-bit digital analog converter, and the LED nixie tube can be directly driven without a driving circuit. The ICL7107 is internally provided with functions of reference voltage, an independent analog switch, a logic switch, display driving, automatic zero setting and the like. The digital voltmeter can realize the measurement of 0-20V direct current voltage. The nixie tube circuit adopts a MAN6710 nixie tube, the eight-segment type nixie tube MAN6710 adopts a common anode connection method, the nixie tube can display 19.9V voltage at most, and automatic polarity display can be realized by inputting negative voltage.
D. Carrying out unsupervised clustering secondary classification on the texture complexity of the original image, and secondarily classifying rocks corresponding to the original image into first-class rocks and second-class rocks; and E, performing step E to classify the first rock three times.
In the embodiment, pebbles, gravels and sandstone plywood rocks are used as objects of the second classification. The contour edge textures of pebbles and cobble stones are smooth and regular, and the complexity is small; the mud-gravel and sandstone splint rock profile has disordered edge textures and high complexity, so that the rocks can be divided into two categories, namely pebbles, pebble-drift rocks, mud-gravel and sandstone splint rocks according to the texture complexity.
In the embodiment, the texture complexity of the rock image is represented by a quantitative profile feature set consisting of three features of profile complexity, a transverse curvature coefficient and a longitudinal curvature coefficient, and the texture complexity is taken as a feature of object classification. And (3) calculating the gradient of the image in the horizontal and vertical directions according to the formulas (1) and (2) to obtain edge texture information of the original image, and representing the contour complexity of the image by using the proportion of edge information points (points with non-zero pixel values) in total pixel points.
The method for calculating the complexity of the contour comprises the following steps:
D1. and combining the transverse gradient and the longitudinal gradient of the original image into a gradient map.
The horizontal and vertical gradients G of the picture are obtained by the formulas (1) and (2)XAnd GyCombining the two to obtain an overall gradient map G, wherein a calculation formula is shown as a formula (5):
G＝Gx+Gy (5)
wherein G is the overall gradient map of the image, Gx、GyThe horizontal and vertical gradients of the image obtained by the expressions (1) and (2), respectively. Fig. 9 shows an overall gradient diagram of a rock picture.
D2. And traversing the gradient map, and counting the total number of points with the pixel values not being zero.
The gradient map G is traversed to find points (edge information points) where the pixel value is not 0, and the total number N thereof is counted.
D3. And representing the complexity of the profile by the proportion of the total number of the points with the non-zero pixel points to the total pixel points of the gradient map.
And (3) calculating the proportion of the edge information points to the total pixel points, wherein the calculation formula is shown as the formula (6):
R＝N/(m*n) (6)
wherein, R is the ratio of the edge information points to the total pixel points, N is the total number of the edge information points, and m and N are the row number and the column number of the gradient image G respectively.
The transverse curvature coefficient is obtained by calculating the curvature of the transverse gradient of the original image. Reflecting the difference degree of the longitudinal texture of the image, the calculation process comprises the following steps:
binarizing the transverse gradient of the original image to obtain a transverse gradient image: obtaining the transverse gradient G of the image according to equation (1)xAnd binarizes it.
And filtering the transverse gradient image to filter out a connected region with the area smaller than a first threshold value so as to reduce the influence of the connected region of the non-rock part in the background on image processing. The method comprises the following steps:
a. and traversing the image and determining a connected region in the image.
b. The area of each connected region is calculated.
c. An area threshold (namely a first threshold) is set through multiple experiments, and a connected region with the area smaller than the threshold is filtered out, so that a filtering effect is achieved.
And calculating the curvature of the filtered transverse gradient image to obtain a transverse curvature map. The calculation formula is shown in formulas (7) to (15):
Gdown＝(Gx1 2+Gx2 2)1.5 (13)
Gup＝Gx2 2·Gx1x-2Gx1·Gx2x·Gx2+Gx1 2·Gx2y (14)
K1＝Gup/Gdown (15)
wherein G isx、GyThe horizontal and vertical gradients of the pictures are obtained according to the formulas (1) and (2); k1The calculated transverse curvature of the image is used. The transverse curvature diagram is shown in fig. 10.
And taking the variance value of the points of which the pixel points are not zero in the transverse curvature map as a transverse curvature coefficient. The invention takes the variance value of the effective information point (the point which is not 0) in the transverse curvature as the transverse curvature coefficient to represent the difference degree of the longitudinal edge texture of the image. The calculation process comprises the following steps:
a. traversing the transverse curvature graph, finding out effective information points therein, and counting the number N of the effective information points1。
b. Calculating the mean value of the effective information points, wherein the calculation formula is shown as formula (16):
wherein KmeanTo calculate the mean of the resulting significant points, K1For transverse curvature of the image, N1The number of the effective points is shown.
c. And circularly traversing effective information points of the transverse curvature graph, and calculating the variance of the effective information points, wherein the variance calculation formula is shown as formula (17):
Ks＝∑(K1x-Kmean)2/N1 (17)
wherein KsFor the calculated variance of the effective information points, K1xTo traverse K1All the available information points, K, are obtainedmeanIs the mean value of the effective information points, N1The number of the effective points is shown.
The longitudinal curvature coefficient is obtained by calculating the curvature of the longitudinal gradient of the original image. Reflecting the difference degree of the transverse texture of the image, the calculation process is basically the same as the extraction process of the transverse curvature coefficient, and only G in the formulas (7) to (17) is usedxIs changed to GyThus obtaining the product. Fig. 11 is a longitudinal curvature diagram of a rock-like picture.
Based on the above, the texture complexity of the original images is subjected to unsupervised clustering two-stage classification, the quantitative profile feature set of 1 image is randomly selected from pebble, gravel and sandstone laminated rock to serve as an initial clustering center, then the distance between the feature set of each image and each clustering center is calculated, and the feature set participating in the current calculation is allocated to the nearest clustering center. The cluster centers and the feature sets assigned to them represent a cluster. When a sample (feature set) is allocated, the clustering center of the cluster is recalculated according to the existing object in the cluster until the clustering center is not changed any more and the sum of the squared errors is minimum, and then one-time clustering is completed. And finally, the pictures participating in calculation can be gathered into two types (pebble, cobble stone, mud-gravel and sandstone plywood rock), so that secondary classification of the rock is realized.
E. And carrying out second preprocessing on the original image to obtain a corresponding second binary image, and carrying out unsupervised clustering secondary classification on the rock corresponding to the original image by taking the connected domain ratio and the centroid boundary distance chaos of the second binary image as characteristics.
After the classification steps, the rock images are further subdivided into two categories of pebbles, pebbles and mud pebbles, and sandstone plywood rocks, wherein the mud pebbles and the sandstone plywood rocks have large texture difference and are easy to distinguish, and the pebbles have small texture difference and are difficult to distinguish, so that the automatic classification method for the pebbles and the pebbles is further designed aiming at the difficulty.
According to the definition, pebbles refer to natural oval particles without edges and corners, the particle diameter of which is 60-200 mm, and the natural oval particles are formed by long-term transportation of weathered rocks through water flow; the cobble rock is rock with particle size greater than 200mm and with round and sub-round particles as main components, and the content of the particles exceeds 50% of the total weight; in addition, the pebble and the boulder are easy to obtain by comparing images of the pebble and the boulder, the shape of the pebble is closer to a circle, the corner feeling of the boulder is more obvious, and therefore the difference between the pebble and the boulder on the images is mainly expressed as the shape.
The process of performing the second preprocessing on the original image to obtain the corresponding second binary image includes: carrying out first preprocessing on an original image to obtain a corresponding first binarized image; and calculating a connected region in the first binarized image, filtering the connected region with the area smaller than a third threshold value in the first binarized image, and opening the rest part to obtain a second binarized image.
Specifically, the read color image is converted into a gray image, a threshold value which enables the gray value difference between two parts of the gray image to be maximum is found according to an Otsu global threshold value determination method, and the gray image is divided into a binary image by applying the threshold value. And carrying out image filtering on the binary image, wherein the filtering method comprises the following steps:
a. and traversing the image and determining a connected region in the image.
b. The area of each connected region is calculated.
c. And setting an area threshold (namely a third threshold) through multiple experiments, and filtering out a connected region with the area smaller than the threshold.
d. And opening the image to further eliminate noise and make the boundary of each connected region clearer.
The process of image filtering is shown in fig. 12. As can be seen from fig. 12, after the first area threshold filtering, some non-pebble interference regions are filtered, but there are still some noise points and some regions are stuck, and after the opening operation, the noise points are further filtered, and the boundaries of the connected regions are also clearer. As can be seen from fig. 12, each connected region of the pebble image is approximately circular or elliptical, has a high degree of fitting with the rectangular frame, and has a larger occupation ratio in the rectangular frame; and each communication area of the cobble stone image has a corner sense, the fitting degree with the rectangular frame is low, and the occupation ratio in the rectangular frame is small. Therefore, it is possible to use the connected component ratio as the classification element.
In some embodiments, the connected component area ratio is an area ratio of each connected component area to the corresponding minimum boxed rectangle in the second binarized image. The calculation process comprises the following steps:
a. and (3) extracting communication information: traversing the filtered image, determining each connected region in the image, and combining a regionprops function in an MATLAB image processing toolbox to obtain a centroid C and an area S of each connected regionAAnd the position information of the minimum framing box. Fig. 13 shows the result of the connected information extraction. In fig. 13, the centroids of the respective connected regions are marked by blue asterisks, and the minimum boxed rectangle is marked in the form of a red dashed rectangle box.
b. And (3) connected domain proportion extraction: calculating the length and width of the bounding box by using the position information of the bounding box obtained during the extraction of the communication information, and further calculating to obtain the area S of the bounding boxb. The connected domain proportion calculation formula is shown as formula (18).
SR＝SA/Sb (18)
Wherein S isRThe calculated ratio of the connected domain is obtained; sAFor the connected region area obtained at the time of connected information extraction, SbA rectangular area is selected for the corresponding minimum box.
Based on the principle that the more circular the outline of the object is, the closer the distances from the points of the outline to the centroid are, i.e., the smaller the variance is, in some embodiments, the method for calculating the confusion of the centroid boundary distance includes:
and extracting the outline of the connected domain in each minimum frame selection rectangle in the second binary image.
And calculating Euclidean distances from each point on the outline of each connected domain to the centroid, and taking the variance value of each Euclidean distance as the confusion degree of the centroid boundary distance.
Specifically, the method for calculating the centroid boundary distance confusion degree comprises the following steps:
a. extracting the connected domain contour from each bounding box by using a Sobel edge extraction method, wherein the calculation formula is as follows:
Gsx＝[Fb(x+1，y-1)+2Fb(x+1，y)+Fb(x+1，y+1)]-[Fb(x-1，y-1+2Fbx-1，y+Fbx-1，y+1] (19)
Gsy＝[Fb(x-1，y-1)+2Fb(x，y-1)+Fb(x+1，y-1)]-[Fb(x-1，y+1+2Fb(x，y+1)+Fb(x+1，y+1)] (20)
θs＝arctan(Gsx/Gsy) (22)
wherein, FbCorresponding image areas to each bounding box (the pixel value of the connected area is 1, and the rest is 0); gsIs the bounding box image gradient; thetasIs the gradient direction thereof; when gradient GsWhen a certain threshold is exceeded, the corresponding point is set as an edge point.
b. Calculating Euclidean distances from each point of the connected domain outline to the centroid, wherein the calculation formula is as follows:
wherein D (i) represents the Euclidean distance from the ith contour point to the centroid, (x)i，yi) Represents the ith contour point coordinate, (C)x，Cy) Representing the coordinates of the center of mass.
c. Calculating variance of each distance
Wherein D isvFor the calculated variance value, N, of the distances from each contour point to the centroidedgeThe number of contour points.
And (3) forming a profile estimation feature set by using the extracted two feature coefficients of the connected domain proportion and the centroid boundary distance chaos, and performing unsupervised clustering secondary classification on rocks corresponding to the secondarily classified original images by using the feature set as a classification feature: randomly selecting 1 image profile estimation feature set from each of pebble and cobble classes as an initial clustering center, then calculating the distance between the feature set of each image and each clustering center, and allocating the feature set participating in the current calculation to the nearest clustering center. The cluster centers and the feature sets assigned to them represent a cluster. When a sample (feature set) is allocated, the clustering center of the cluster is recalculated according to the existing object in the cluster until the clustering center is not changed any more and the sum of the squared errors is minimum, and then one-time clustering is completed. And finally, the pictures participating in the calculation are gathered into two types (an egg stone type and an egg floating stone type), so that the further subdivision of the rock stone type is realized.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and the computer program can be run to execute the soil and rock classification method.
The embodiment of the invention also provides a soil and rock classification device based on image processing, which comprises the computer readable storage medium, a processor and a soil water content detection circuit, wherein the processor is respectively connected with the computer readable storage medium and the soil water content detection circuit, the soil water content detection circuit detects the soil water content and transmits the detection result to the processor, and the processor runs a computer program in the computer readable storage medium to execute the soil and rock classification method.
The scheme of the embodiment of the invention can be applied to the classification of various common soils and rocks, as shown in fig. 14, wherein (1) to (6) in the figure sequentially comprise silty clay, plain soil, pebbles, cobble stones, mud gravel and sandstone sandwich rock, and the scheme (method or device) of the invention can automatically classify the listed soils or rocks. The invention can also be applied to the classification of other types of soil and rock, the principle is the same, and the classification is not listed.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed.
Claims (10)
1. A soil and rock classification method is characterized by comprising the following steps:
A. respectively executing the following processing to each collected original image:
carrying out first preprocessing on the collected original image to obtain a corresponding first binarized image;
calculating the transverse and longitudinal gradients of the first binarized image, and calculating the gradient sampling duty ratio corresponding to the original image according to the transverse and longitudinal gradients;
B. carrying out unsupervised clustering secondary classification on the gradient sampling duty ratio corresponding to each original image, and classifying the environment corresponding to each original image into a soil class and a rock class at one time; c, performing secondary classification on the soil class, and D, performing secondary classification on the rock class;
C. classifying the soil corresponding to the original image according to the water content of the soil corresponding to the original image;
D. carrying out unsupervised clustering secondary classification on the texture complexity of the original image, and secondarily classifying rocks corresponding to the original image into first-class rocks and second-class rocks; for the first type of rocks, performing step E to perform three times of classification;
E. and carrying out second preprocessing on the original image to obtain a corresponding second binary image, and carrying out unsupervised clustering secondary classification on the rock corresponding to the original image by taking the connected domain ratio and the centroid boundary distance chaos of the second binary image as characteristics.
2. The soil and rock classification method according to claim 1, wherein the gradient sampling duty cycle calculation method comprises the following steps:
equidistant sampling of rows/columns of the horizontal/vertical gradient, respectively;
respectively calculating the ratio of gradient information points of sampling rows/columns to the number of information points in the rows/columns;
and carrying out unsupervised clustering secondary classification on the ratio of the sampling rows/columns, and taking the class with a large number of clusters as the gradient sampling duty ratio corresponding to the original image.
3. The soil and rock classification method according to claim 1, wherein the soil water content detection circuit is used to detect the water content of the soil in step C, the soil water content detection circuit comprises a square wave signal generation circuit, a sensing circuit, a rectification circuit, a filter circuit, a correction circuit, an amplification circuit and a display circuit, the square wave signal generation circuit, the sensing circuit, the rectification circuit and the filter circuit are sequentially connected, the input end of the correction circuit is connected with the power supply of the soil water content detection circuit, the output ends of the filter circuit and the correction circuit are respectively connected with the two input ends of the amplification circuit, and the output end of the amplification circuit is connected with the display circuit.
4. The soil and rock classification method of claim 1, wherein the texture complexity comprises three features of contour complexity, transverse curvature coefficient and longitudinal curvature coefficient;
the method for calculating the complexity of the contour comprises the following steps:
the transverse and longitudinal gradients of the original image are merged into a gradient map,
traversing the gradient map, counting the total number of points whose pixel values are not zero,
representing the complexity of the profile by the proportion of the total number of the points with the non-zero pixel points to the total pixel points of the gradient map;
the transverse curvature coefficient is obtained by calculating the curvature of the transverse gradient of the original image;
the longitudinal curvature coefficient is obtained by calculating the curvature of the longitudinal gradient of the original image.
5. The soil and rock classification method of claim 4, wherein said calculating the curvature of the transverse gradient of the original image comprises:
binarizing the transverse gradient of the original image to obtain a transverse gradient image;
filtering the transverse gradient image to filter out a connected region with an area smaller than a first threshold value;
calculating the curvature of the filtered transverse gradient image to obtain a transverse curvature map;
and taking the variance value of the points of which the pixel points are not zero in the transverse curvature map as a transverse curvature coefficient.
6. The soil and rock classification method of claim 4, wherein said calculating the curvature of the longitudinal gradient of the original image comprises:
binarizing the longitudinal gradient of the original image to obtain a longitudinal gradient image;
filtering the longitudinal gradient image to filter out a connected region with an area smaller than a second threshold value;
calculating the curvature of the filtered longitudinal gradient image to obtain a longitudinal curvature map;
and taking the variance value of the points of which the pixel points are not zero in the longitudinal curvature map as a longitudinal curvature coefficient.
7. The soil and rock classification method according to claim 1, wherein the second preprocessing is performed on the original image to obtain a corresponding second binary image, and comprises:
carrying out first preprocessing on an original image to obtain a corresponding first binarized image;
and calculating a connected region in the first binarized image, filtering the connected region with the area smaller than a third threshold value in the first binarized image, and opening the rest part to obtain a second binarized image.
8. The soil and rock classification method according to claim 1, wherein the connected component area ratio is an area ratio of each connected component area to a corresponding minimum boxed rectangle in the second binarized image.
9. The soil and rock classification method according to claim 1, wherein the method for calculating the centroid boundary distance chaos comprises:
extracting the outline of a connected domain in each minimum framing rectangle in the second binary image;
and calculating Euclidean distances from each point on the outline of each connected domain to the centroid, and taking the variance value of each Euclidean distance as the confusion degree of the centroid boundary distance.
10. A soil and rock classification device comprises a processor, a computer readable storage medium and a soil water content detection circuit, wherein the processor is respectively connected with the computer readable storage medium and the soil water content detection circuit; the soil water content detection circuit is used for detecting the water content of soil, and the computer readable storage medium stores a computer program; the soil water content detection circuit transmits the detection result to the processor, and the processor runs the computer program to execute the soil and rock classification method according to any one of claims 1, 2, 4-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011336766.9A CN112613531B (en) | 2020-11-25 | 2020-11-25 | Soil and rock classification method and device based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011336766.9A CN112613531B (en) | 2020-11-25 | 2020-11-25 | Soil and rock classification method and device based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112613531A true CN112613531A (en) | 2021-04-06 |
| CN112613531B CN112613531B (en) | 2023-12-12 |
Family
ID=75225076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011336766.9A Active CN112613531B (en) | 2020-11-25 | 2020-11-25 | Soil and rock classification method and device based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613531B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116540316A (en) * | 2023-07-06 | 2023-08-04 | 华设检测科技有限公司 | Geological soil layer testing method based on SVM classification algorithm and clustering algorithm |
| CN117823232A (en) * | 2024-03-04 | 2024-04-05 | 邹城市宇光煤矿机械有限公司 | Coal mine production safety monitoring method and system and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160307073A1 (en) * | 2015-04-20 | 2016-10-20 | Los Alamos National Security, Llc | Change detection and change monitoring of natural and man-made features in multispectral and hyperspectral satellite imagery |
| CN106780485A (en) * | 2017-01-12 | 2017-05-31 | 西安电子科技大学 | SAR image change detection based on super-pixel segmentation and feature learning |
| CN110264459A (en) * | 2019-06-24 | 2019-09-20 | 江苏开放大学（江苏城市职业学院） | A kind of interstices of soil characteristics information extraction method |
| CN110427979A (en) * | 2019-07-10 | 2019-11-08 | 广东工业大学 | Road puddle recognition methods based on K-Means clustering algorithm |
| CN110866912A (en) * | 2019-11-15 | 2020-03-06 | 成都理工大学 | Shale streak layer heterogeneity data processing method based on imaging logging image texture |
| CN113838011A (en) * | 2021-09-13 | 2021-12-24 | 中南大学 | Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient |
-
2020
- 2020-11-25 CN CN202011336766.9A patent/CN112613531B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160307073A1 (en) * | 2015-04-20 | 2016-10-20 | Los Alamos National Security, Llc | Change detection and change monitoring of natural and man-made features in multispectral and hyperspectral satellite imagery |
| CN106780485A (en) * | 2017-01-12 | 2017-05-31 | 西安电子科技大学 | SAR image change detection based on super-pixel segmentation and feature learning |
| CN110264459A (en) * | 2019-06-24 | 2019-09-20 | 江苏开放大学（江苏城市职业学院） | A kind of interstices of soil characteristics information extraction method |
| CN110427979A (en) * | 2019-07-10 | 2019-11-08 | 广东工业大学 | Road puddle recognition methods based on K-Means clustering algorithm |
| CN110866912A (en) * | 2019-11-15 | 2020-03-06 | 成都理工大学 | Shale streak layer heterogeneity data processing method based on imaging logging image texture |
| CN113838011A (en) * | 2021-09-13 | 2021-12-24 | 中南大学 | Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient |
Non-Patent Citations (2)
| Title |
|---|
| 周磊;滕奇志;何海波;: "岩石颗粒图像中的斜长石识别", 现代计算机(专业版), no. 03 * |
| 范慧颖;董武;康宝生;张大奇;: "基于遥感图像的山地冰川识别方法对比", 水利水电技术, no. 05 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116540316A (en) * | 2023-07-06 | 2023-08-04 | 华设检测科技有限公司 | Geological soil layer testing method based on SVM classification algorithm and clustering algorithm |
| CN116540316B (en) * | 2023-07-06 | 2023-09-01 | 华设检测科技有限公司 | Geological Soil Layer Testing Method Based on SVM Classification Algorithm and Clustering Algorithm |
| CN117823232A (en) * | 2024-03-04 | 2024-04-05 | 邹城市宇光煤矿机械有限公司 | Coal mine production safety monitoring method and system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112613531B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106910186B (en) | Bridge crack detection and positioning method based on CNN deep learning | |
| CN106557764B (en) | A kind of water level recognition methods based on binary-coded character water gauge and image procossing | |
| Lu et al. | Land cover classification in a complex urban-rural landscape with QuickBird imagery | |
| CN101539629B (en) | Remote sensing image change detection method based on multi-feature evidence integration and structure similarity | |
| TWI281126B (en) | Image detection method based on region | |
| CN112613531B (en) | Soil and rock classification method and device based on image processing | |
| CN105335725A (en) | Gait identification identity authentication method based on feature fusion | |
| CN103778436B (en) | A kind of pedestrian's attitude detecting method based on image procossing | |
| CN106446894A (en) | Method for recognizing position of spherical object based on contour | |
| CN103048329A (en) | Pavement crack detecting method based on active contour model | |
| CN104123554B (en) | SIFT image characteristic extracting methods based on MMTD | |
| CN106407924A (en) | Binocular road identifying and detecting method based on pavement characteristics | |
| CN107392929A (en) | A kind of intelligent target detection and dimension measurement method based on human vision model | |
| CN101162503A (en) | Method for extracting and recognizing human ear characteristic by improved Hausdorff distance | |
| CN104778679A (en) | Gaofen-1 satellite data-based control point graphic element rapid-matching method | |
| Yuan et al. | Learning to count buildings in diverse aerial scenes | |
| CN106340010B (en) | A kind of angular-point detection method based on second order profile difference | |
| Gao et al. | A robust pointer meter reading recognition method for substation inspection robot | |
| CN103729649A (en) | Image rotating angle detection method and device | |
| CN104766096A (en) | Image classification method based on multi-scale global features and local features | |
| CN107341790A (en) | A kind of image processing method of environment cleanliness detection | |
| CN107085848A (en) | Method for detecting significance of RGB-D (Red, Green and blue-D) image | |
| CN106355596B (en) | A kind of edge detection method merging uniform color information and compound receptive field model | |
| Lambers et al. | Towards detection of archaeological objects in high-resolution remotely sensed images: the Silvretta case study | |
| CN111178193A (en) | Lane line detection method, lane line detection device and computer-readable storage medium |
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 |