CN115343228A - Method, device and equipment for determining sand and stone mud content - Google Patents
Method, device and equipment for determining sand and stone mud content Download PDFInfo
- Publication number
- CN115343228A CN115343228A CN202210866378.4A CN202210866378A CN115343228A CN 115343228 A CN115343228 A CN 115343228A CN 202210866378 A CN202210866378 A CN 202210866378A CN 115343228 A CN115343228 A CN 115343228A
- Authority
- CN
- China
- Prior art keywords
- mud content
- turbidity
- sand
- pool
- determining
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/251—Colorimeters; Construction thereof
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application is applicable to the technical field of building material testing, and provides a method, a device and equipment for determining sand and stone mud content, wherein the method comprises the steps of obtaining an image of a muddy water pond at the time t and an image of a sand and stone pond at the time t; determining a first turbidity value in the image of the turbid water pool based on the trained turbid water turbidity identification model; determining the initial mud content in the sand pool image based on the trained sand mud content recognition model; determining a second turbidity value of the turbid water pool at the time t based on the turbidity detection device; and determining the target mud content in the sand pool at the time t according to the first turbidity value, the second turbidity value and the initial mud content. The method provided by the application can be used for quickly and accurately obtaining the sand and stone mud content.
Description
Technical Field
The application belongs to the technical field of building material testing, and particularly relates to a method, a device and equipment for determining sand and stone mud content.
Background
In the screening process of recycling the muck, in order to ensure the quality of the sandstone, the mud content is an important technical index of the sandstone, and the mud content in the sand has different degrees of influence on the fluidity, the water retention property, the strength, the deformation, the durability and the like of the concrete. In order to ensure the quality of concrete, especially when preparing high-strength concrete, clean sand should be selected.
In the related technology, the mud content in the sandstone is mainly detected and controlled by manual operation, so the measurement steps are complicated, the consumed time is long, and the method is generally used for laboratory inspection and is not suitable for detection at any time in a production field.
Disclosure of Invention
The embodiment of the application provides a method, a device and equipment for determining sand and stone mud content, and can solve the problems that the sand and stone mud content detection step is complex and the time consumption is long in the prior art.
In a first aspect, an embodiment of the application provides a method for determining sand and gravel mud content, which includes acquiring a muddy water pond image at time t and a sand and gravel pond image at time t; determining a first turbidity value in the image of the turbid water pool based on the trained turbid water turbidity identification model; determining the initial mud content in the sand pool image based on the trained sand mud content recognition model; determining a second turbidity value of the turbid water pool at the time t based on the turbidity detection device; and determining the target mud content in the sand-gravel pool at the time t according to the first turbidity value, the second turbidity value and the initial mud content.
Illustratively, the turbidity detecting means comprises at least one of a turbidity sensor, a colorimeter or a spectrophotometer.
According to the determining method for the sand and stone mud content, the trained muddy water turbidity identification model is used for obtaining the first turbidity value, the trained sand and stone mud content identification model is used for obtaining the initial mud content, the method for image identification can be used for realizing the rapid real-time detection of the sand and stone mud content, the turbidity detection device is used for obtaining the second turbidity value, the final calculated mud content result can be more accurate by combining the first turbidity value, the second turbidity value and the initial mud content, and the calculating speed is also greatly improved.
In one possible implementation manner of the first aspect, the target mud content in the sand pool at the time t is determined according to the first turbidity value, the second turbidity value and the first mud content, and the method comprises the following steps:
determining the target mud content in the sand pool at the time t by using the following calculation formula:
y＝K 1 x 1 +K 2 x 2 +K 3 x 3
wherein y represents the target mud content in the sand pond; k 1 、K 2 、K 3 Representing a parameter value; x is the number of 1 Representing the first turbidity value, x 2 Representing said second turbidity value, x 3 Representing the initial mud content. In the implementation mode, the target mud content can be quickly and accurately obtained by utilizing a computational mathematical calculation formula.
In a possible implementation manner of the first aspect, the method further includes: obtaining a plurality of sands with known mud content; respectively determining first turbidity values in a plurality of muddy water pool images with known mud content based on a muddy water turbidity identification model; respectively determining the initial mud content in a plurality of sand pool images with known mud content based on the sand mud content identification model; respectively determining second turbidity values of a plurality of sand with known mud content based on the turbidity detection device; determining K based on the first turbidity value, the second turbidity value and the initial sludge content 1 、K 2 、K 3 . In the implementation mode, the sand with known mud content is tested, test data is obtained, calculation is carried out to determine the parameter values, and a first turbidity value, a second turbidity value and a first mud content are providedThe mathematical expression of (1).
In a possible implementation manner of the first aspect, the method further includes: obtaining a training sample, wherein the sample comprises a turbid pool image with known turbidity; generating a predicted turbidity value by using the training sample and an initial AlexNet network model; calculating a network error based on the known turbidity value and the predicted turbidity value; and carrying out iterative training on the initial Alexnet network model based on the network error to obtain the trained turbidity water pool turbidity identification model.
In a possible implementation manner of the first aspect, the method further includes: obtaining a training sample, wherein the sample comprises a sand pool image with known mud content; generating a predicted mud content by using the training sample and an initial AlexNet network model; calculating a network error based on the known mud content and the predicted mud content; and performing iterative training on the initial Alexnet network model based on the network error to obtain the trained sandstone pool mud content identification model.
In a second aspect, there is provided a communication device comprising means for performing the steps of the above first aspect or any possible implementation manner of the first aspect.
In a third aspect, a communication device is provided, which comprises at least one processor and a memory, the at least one processor being configured to perform the method of the first aspect above or any possible implementation manner of the first aspect.
In a fourth aspect, a communication device is provided, which comprises at least one processor configured to perform the method of the first aspect above or any possible implementation manner of the first aspect, and an interface circuit.
In a fifth aspect, there is provided an apparatus for data packet transmission, the apparatus comprising at least one processor coupled with at least one memory: the at least one processor is configured to execute the computer program or instructions stored in the at least one memory to cause the data packet sending apparatus to perform the method of the above first aspect or any possible implementation manner of the first aspect.
A sixth aspect provides a computer program product comprising a computer program for performing the method of the first aspect or any possible implementation form of the first aspect when executed by a processor.
In a seventh aspect, a computer-readable storage medium is provided, in which a computer program is stored, which, when executed, is adapted to perform the method of the first aspect or any possible implementation manner of the first aspect.
In an eighth aspect, there is provided a chip or an integrated circuit, the chip or the integrated circuit comprising: a processor configured to invoke and execute the computer program from the memory, so that the device on which the chip or the integrated circuit is installed performs the method of the first aspect or any possible implementation manner of the first aspect.
It is to be understood that, for the beneficial effects of the second aspect to the eighth aspect, reference may be made to the relevant description in the first aspect, and details are not described herein again.
Compared with the prior art, the embodiment of the application has the advantages that:
this application embodiment acquires first turbidity value through utilizing the muddy water turbidity recognition model that trains, utilizes the grit mud content recognition model that trains to acquire initial mud content, and this kind of method that utilizes image recognition can realize the quick real-time detection of grit mud content, utilizes turbidity detection device to acquire the second turbidity value, combines first turbidity value, second turbidity value and initial mud content can make the mud content result that final calculation obtained more accurate, and the computational rate has also obtained improving by a wide margin.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments or the prior art description will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings may be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram illustrating a sand and mud content detection scenario provided by an embodiment of the present application;
FIG. 2 is a schematic diagram of a sand and mud content detection system provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart of a sand-mud content determination method provided by an embodiment of the present application;
FIG. 4 is a schematic flow chart diagram illustrating a training process of a turbidity water turbidity identification model provided by an embodiment of the application;
FIG. 5 is a schematic view showing a sand and mud content determining apparatus according to an embodiment of the present application;
fig. 6 shows a schematic view of the sand and mud content determination apparatus provided in the embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
First, before describing the methods and systems provided herein, some of the terms that will be referred to immediately below will need to be described. When the present application refers to the terms "first" or "second" etc. ordinal, it should be understood that they are used for distinguishing purposes only, unless they do express an order in accordance with the context.
The terms "exemplary" or "such as" are used herein to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
Unless otherwise indicated, "/" herein generally indicates that the preceding and following associated objects are in an "or" relationship, e.g., a/B may represent a or B. The term "and/or" is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the present application, "a plurality" means two or more.
Nowadays, the grit that adopts during engineering construction mostly excavates the collection from river course or massif, consequently can sieve the grit of gathering through the shale shaker usually to the grit of sieving out can reach service standard. But the grit can produce more tiny dust at the screening in-process, and grit self also can carry partial silt particle simultaneously, leads to the mud content of the mechanism sand of producing to be higher relatively, and then influences the normal use of grit.
At present, the standard detection method specified in GB/T2684-2009 is mainly adopted for detecting the mud content of the raw sand, and the method is also the most common method for measuring the mud content of the raw sand at present. The method comprises the steps of firstly, forming layers of mud and sand grains in water according to the principle that the diameters of raw sand and mud suspended in water are different and the descending speeds of the raw sand and the mud are also different, and then sucking out partial water and suspended mud on a sand washing cup by using a siphon. And repeatedly settling and siphoning for many times until the mud in the sand sample is cleaned. And finally, drying, weighing and calculating the residual sand sample to obtain the mud content of the sand sample. The main time consumption is long, the interval is long, and the obtained parameters have serious lag with the actually used materials; secondly, the detection steps of the mud content detection equipment in the current market are as follows: automatic weighing, washing and drying, wherein the drying time is long, the materials are difficult to ensure complete drying, and the measurement error is large; moreover, after the water washing of the current mud content detection equipment is finished, whether mud is washed cleanly or not is not judged, so the detection accuracy of the equipment is questioned.
How to rapidly and accurately obtain the mud content in the sand is a problem to be solved urgently in the field of sand screening and cleaning at present.
In view of this, the embodiment of the present application provides a method for determining a sand and gravel mud content, the method includes first obtaining an image of a muddy water pool at a time t and an image of a sand and gravel pool at the time t, then determining a first turbidity value in the image of the muddy water pool at the time t by using a trained muddy water turbidity recognition model and determining an initial mud content in the image of the sand and gravel pool at the time t by using a trained sand and gravel mud content recognition model, then determining a second turbidity value of the sand and gravel pool at the time t by using a turbidity detection device, and finally determining a target mud content in the sand and gravel pool at the time t based on the first turbidity value, the second turbidity value and the initial mud content.
In a possible application scenario, when the sand and stone mud content in the sand and stone pool is dynamically measured, the method for determining the mud content in the sand and stone provided by the application can be adopted.
Before describing the method for determining the mud content in the sandstone provided by the application, a description is given to a scene to which the method for determining the mud content in the sandstone provided by the application is applicable.
Fig. 1 shows a schematic view of a sand and mud content detection scene provided by the embodiment of the application, as shown in fig. 1, a is a sand pool, and B is a muddy water pool. After silt in the residue soil resource is separated, screening and cleaning are carried out through a residue soil resource system, sand and stone which are screened after cleaning are sent to a sand and stone pool A, the sand and stone in the sand and stone pool A are sent to a sand and stone field through transportation to prepare for subsequent resource utilization, turbid liquid generated after washing flows into a muddy water pool B through a screening filter screen, and therefore dynamic cleaning of the sand and stone is achieved, the muddy liquid in the muddy water pool B is recycled through treatment, the sand and stone in the sand and stone pool A and the muddy liquid in the muddy water pool B dynamically change in real time and are not accumulated all the time. The scheme determines the dynamic variation of the mud content of the sandstone in the sandstone pool in the washing process according to the mud content of the sandstone in the sandstone pool and the turbidity of the muddy water pool.
The sand and gravel mud content detection system provided by the embodiment of the application is specifically introduced below. Fig. 2 shows a schematic diagram of the sand and mud content detection system provided by the embodiment of the present application, and as shown in fig. 2, the system mainly includes an image acquisition module, an image recognition module, a turbidity detection module, and a data processing module.
The image acquisition module is used for acquiring images of the muddy water pool and the sand pool at any moment. For example, cameras can be respectively arranged on the muddy water pool and the sandstone pool, and images of the muddy water pool and the sandstone pool at any time can be acquired through the cameras.
The image identification module is used for identifying the turbidity in the collected muddy water pool image and the mud content in the sand pool image.
The turbidity detection module is used for detecting turbidity in the muddy water pool by using the detection device. For example, turbidity detection can be performed by a turbidity sensor or the like.
The data processing module is used for determining the target mud content in the sand pool by utilizing the identified turbidity in the muddy water pool image, the mud content in the sand pool image and the detection result of the turbidity detection module.
Next, a method for determining the mud content in the sandstone provided by the embodiment of the present application is specifically described with reference to fig. 1 and fig. 2, and fig. 3 shows a schematic flow chart of the method for determining the mud content in the sandstone provided by the embodiment of the present application, and the method may be applied to the above-mentioned scenario, and may of course be applied to other scenarios of detecting the mud content in the sandstone, which is not limited in the embodiment of the present application.
It should be understood that, an execution subject of the sand and gravel mud content determination method in the embodiment of the present application is sand and gravel mud content determination equipment, and the equipment includes, but is not limited to, a mobile terminal such as a smartphone, a tablet computer, a wearable device, and the like, and may also be a desktop computer, a robot, a server, or the like.
As shown in fig. 3, the method may include S310 to S350.
S310, obtaining the images of the sand pool at the time t and the images of the muddy water pool at the time t.
In this application embodiment, in order to carry out intelligent detection to the mud content in the grit pond, need obtain the image in grit pond and the image in muddy water pond at first.
In some embodiments, images of the sand pool can be acquired through a camera mounted on the sand pool, and images of the muddy water pool at any time can be acquired through a camera mounted on the muddy water pool in the same way.
In other embodiments, any equipment with the photographing function is used for photographing, so that the image of the sand pool at the time t and the image of the muddy water pool at the time t are obtained.
Therefore, the method for acquiring the images of the sand pool and the muddy water pool is not limited by the application.
It should be noted that the time t may be a specific time, or may be a specific time period, which may be set according to specific situations, and this is not limited in this embodiment of the application.
S320, determining a first turbidity value in the image of the turbid water tank at the time t based on the turbid water tank turbidity identification model.
In order to obtain an accurate turbidity value of the turbid water tank, in the embodiment of the application, the first turbidity value in the turbid water tank image at the time t can be accurately identified based on the trained turbid water turbidity identification network model.
In some embodiments, the initial AlexNet model may be trained based on a large number of pool images of known turbidity to yield a trained turbidity identification model.
Next, on the basis of step S320, a training process of the turbidity water turbidity identification model provided in the embodiment of the present application is specifically described, and fig. 4 shows a schematic flowchart of the training process of the turbidity water turbidity identification model provided in the embodiment of the present application, and as shown in fig. 4, the method includes S321-S325:
s321, acquiring and expanding an image data set, and constructing a training set and a testing set of turbidity images of the turbid water pool.
And acquiring the image of the existing muddy water pool, and labeling the turbidity in the image of the muddy water pool. In order to extract the characteristics related to turbidity in the turbid water pool image, the acquired existing turbid water pool image can be subjected to data enhancement and expansion. For example, the orientation of the image content can be changed by rotating the image randomly by a certain angle; turning the image along the horizontal or vertical direction; and then, randomly selecting the labeled data sets to construct a training set and a testing set for all the data sets according to the proportion of 4:1, wherein the training set and the training set are used for training the network model, and the testing set are used for testing the performance of the trained network model.
And S322, constructing an initial AlexNet network model.
The AlexNet network model is divided into eight layers in total, wherein the first five layers are convolutional layers and the last three layers are fully-connected layers, and each convolutional layer comprises an excitation function ReLU and a Local Response Normalization (LRN) process, and then a down-sampling (pool process) is performed. Compared with other deep learning network models, the Alexnet network model is more suitable for turbidity identification of turbid water pool images, and has the characteristics of fewer convolution layers, relatively fewer parameter quantities and capability of carrying out quick and accurate identification. Since the muddy water pool image is generally small in size, mostly between 16 pixels and 200 pixels, and is a characteristic of a gray image, the input layer of the Alexnet network needs a color picture with a size of 227 x 227.
The input layer of the AlexNet network model is 171X 1, which makes it more suitable for muddy water pool image data sets. The first convolutional layer adopts 96 filters with the step size of 3, namely 9 multiplied by 9 filters, so that the feature map obtained by the convolutional operation is more suitable for the feature information of the input image, and the training parameters of the network model are reduced. Then passes through the largest pooling layer, which uses a convolution kernel of 3 x 3 with a step size of 2, and passes the computation output to the next layer. The model is combined by five convolutional layers and three pooling layers, then three full-connection layers are arranged, the number of nodes of the third full-connection layer is 10, the nodes respectively correspond to the turbidity contents in a plurality of turbidity water tanks, finally, the identification of different turbidity images is completed through a softmax classifier, and the identification result of the turbidity contents in the images is output at an output layer.
And S323, setting training parameters of the initial AlexNet network model.
An input image is a gray image of 171 × 171 × 1, training is performed on a single Graphics Processing Unit (GPU), the number of batch input images is 64, and an initial learning rate is 0.001;
s324, training a turbidity pool turbidity identification model based on the Alexnet network model;
and (5) training the turbid pool turbidity identification network based on the Alexnet network model by using the image training set and the training set labels obtained in the step (S221) and combining the training parameters set in the step (S223).
When the model is trained, a back propagation learning algorithm and a random gradient descent method are adopted, the network weight is updated in a back iteration mode by minimizing the magnitude of the loss function value of forward propagation, and the network training is stopped until the loss function value of the model is converged.
Specifically, the muddy water pond sample images in the training set are input into an initial Alexnet network model to obtain an initial network error, training parameters of the initial Alexnet network model are adjusted based on the initial network error, and the network error is continuously obtained based on the sample images in the training set and the adjusted initial Alexnet network model. And when the network error is judged to be larger than the error threshold value, readjusting the parameters of the Alexnet network model, acquiring the network error again, repeating the process until the network error acquired again is not larger than the error threshold value, and acquiring the turbidity identification model of the basically trained muddy water pool.
And S325, determining a trained turbidity water pool turbidity identification model based on the turbidity water pool image test set.
And (4) testing the Alexnet model obtained in the step (324) by using the testing set of the image of the muddy water pool obtained in the step (321), so as to obtain the turbidity identification result and the overall accuracy of the muddy water pool in each image of the testing set.
And judging whether the training of the model is finished according to the turbidity identification result and the overall accuracy of the turbid water pool. The accuracy can be set according to specific conditions, and therefore, the turbidity pool turbidity identification network model training is completed.
And finally, inputting the muddy water pond image obtained at the time t in the step S310 into a muddy water pond turbidity identification network model to obtain a first turbidity value in the muddy water pond image.
It can be understood that the muddy water pool turbidity identification model can be trained by the sand pool mud content identification device in advance, and also can be trained by other devices in advance to transplant the file corresponding to the muddy water pool turbidity identification model into the sand pool mud content identification device. That is, the execution subject who trains the turbidity pool turbidity recognition model may be the same as or different from the execution subject who performs image recognition using the turbidity pool turbidity recognition model. For example, when the initial turbidity pool turbidity identification model is trained by other equipment, after the initial turbidity pool turbidity identification model is trained by other equipment, the model parameters of the initial turbidity pool turbidity identification model are fixed to obtain a file corresponding to the turbidity pool turbidity identification model, and then the file is transplanted to the sand pool mud content identification equipment.
S330, determining the initial mud content in the sand pool image based on the sand pool mud content identification model.
In this application embodiment, for the mud content in confirming the grit pond, can discern the mud content in the grit pond at any moment based on the grit pond mud content recognition model who trains well.
In some embodiments, the initial AlexNet model may be trained based on a large number of known mud-laden sand pool images to yield a trained sand pool mud recognition model.
It should be noted that the process of the sand pool mud content identification model in step S330 is the same as the step of the turbid water pool turbidity identification model in step S320, and specific reference may be made to the description in step S321 to step S325, which is not described herein again.
And finally, inputting the sand pool image obtained at the time t in the step S310 into a sand pool mud content identification model to obtain the initial mud content in the sand pool image.
It should be noted that the initial Alexnet model is taken as an example for the training of the turbidity pool turbidity model and the sand pool mud content model in steps S320 to S330, and the initial model may be a VGG model, a google net model, or the like. Therefore, the embodiments of the present application are not limited.
It can be understood that the sand-gravel pool mud content identification model can be trained by sand-gravel pool mud content identification equipment in advance, and also can be trained by other equipment in advance to transplant the file corresponding to the sand-gravel pool mud content identification model into the sand-gravel pool mud content identification equipment. That is, the execution subject for training the sand pool mud content recognition model and the execution subject for performing image recognition by using the sand pool mud content recognition model may be the same or different. For example, when the initial sand pool mud content identification model is trained by other equipment, after the initial sand pool mud content identification model is trained by other equipment, the model parameters of the initial sand pool mud content identification model are fixed, a file corresponding to the sand pool mud content identification model is obtained, and then the file is transplanted into the sand pool mud content identification equipment.
S340, determining a second turbidity value of the turbid water tank at the time t based on the turbidity detection device;
in step S320, a first turbidity value of the turbid water pool is identified by using the model, and in order to obtain the turbidity value of the turbid water pool more accurately, the turbidity of the turbid water pool may be further measured by using a turbidity measuring device.
In some embodiments, a turbidity sensor may be used to detect the turbidity of the turbid water reservoir at time t to obtain a second turbidity value.
It should be understood that the turbidity sensor is an optical sensor, and is mainly applied to water quality detection, and the infrared geminate transistors are arranged in the turbidity sensor, and are arranged in parallel, the emitting ends of the infrared geminate transistors emit light, the transmission amount of the light depends on the amount of suspended particles in water, and the higher the turbidity of the water quality is, the more the suspended particles in the water are, and the less the light is. The receiving end of the infrared geminate transistor converts the transmitted light intensity into voltage, the water quality is clearer, the voltage value is higher, and the dirty degree of the muddy water tank can be calculated by measuring the voltage of the receiving end of the infrared geminate transistor.
In other embodiments, the second turbidity value can also be estimated by measuring the degree of transmitted light intensity attenuation due to the obstruction of particles in the turbid water pool using a colorimeter or spectrophotometer.
Of course, other methods may be used to measure the second turbidity value of the turbid water tank, such as a conventional turbidimetry method or a scattering light method, which is not limited in this application.
And S350, determining the target mud content in the sand-gravel pool at the time t according to the first turbidity value, the second turbidity value and the initial mud content.
In the embodiment of the application, in order to obtain a more accurate mud content result, the target mud content in the sand pool can be determined by combining the result of image recognition and the data obtained by detection of the turbidity detection equipment.
In some embodiments, the target mud content in the sand pool at the time t can be determined by a first turbidity value obtained by the turbidity water pool turbidity identification model, a second turbidity value obtained by the turbidity detection device and an initial mud content obtained by the sand pool mud content identification model.
For example, from the first turbidity value, the second turbidity value and the initial mud content, the target mud content in the sand pool at the time t can be determined by using the following calculation formula:
y＝K 1 x 1 +K 2 x 2 +K 3 x 3
wherein y represents the target mud content in the sand pond; k 1 、K 2 、K 3 Representing a fixed parameter value; x is the number of 1 Representing a first turbidity value, x 2 Representing a second turbidity value, x 3 Indicating the initial mud content.
K in the following formula 1 、K 2 、K 3 The determination method of (2) will be specifically explained:
the grit that obtains the different mud content of multiunit at first carries out the experiment, utilizes muddy water pond turbidity identification model to carry out image recognition to the grit that the multiunit actual measurement obtained known mud content and obtains a plurality of first turbidity values, utilizes grit pond mud content identification model to carry out image recognition and obtain a plurality of initial mud content to and utilize turbidity detection device to obtain a plurality of second turbidity values. Then, fitting is carried out according to the ternary one-time mode, and K is finally determined 1 、K 2 、K 3 Value of (A)。
Furthermore, in order to improve the stability of the system, the system can be a multi-redundancy system, and x can be fitted according to the data obtained by the experiment 2 The relation with the known mud content is fitted, namely the relation between the second turbidity value measured by the turbidity detection device and the known mud content is used, and a new parameter K is obtained 4 。
Then, when the image recognition device is out of order, only the reading of the turbidity sensor is read, using K 4 And finally determining the target mud content of the sand and stone according to the second turbidity value.
Specifically, the target sludge content may be determined using the following calculation formula:
y＝K 4 ×x 2 。
in some embodiments, x may also be fitted 1 And when the turbidity detection device or the sandstone pool mud content identification model has a fault, the target mud content of sandstone can be finally determined by only obtaining the first turbidity value obtained by the turbidity water pool turbidity identification model.
Illustratively, the relation between the first turbidity value obtained by using the turbidity identification model of the turbid water pool and the known mud content is fitted to obtain a new parameter K 5 . By K 5 And finally determining the target mud content of the sand and the first turbidity value.
Specifically, the target sludge content may be determined using the following calculation formula:
y＝K 5 ×x 1 。
in other embodiments, x may also be fitted 3 And when the turbidity detection device or the turbidity water pool turbidity identification model has a fault, the initial mud content obtained by only obtaining the sand pool mud content identification model can finally determine the target mud content of the sand.
Illustratively, the relationship between the initial mud content and the known mud content obtained by using the sand pool mud content identification model is fitted to obtain a new parameter K 6 。
By K 6 And finally determining the target mud content of the sand and the initial mud content.
Specifically, the target sludge content may be determined using the following calculation formula:
y＝K 6 ×x 3 。
the embodiment of the application provides a method for determining sand and gravel mud content, the method comprises the steps of firstly obtaining an image of a muddy water pool at the t moment and an image of a sand and gravel pool at the t moment, then determining a first turbidity value in the image of the muddy water pool at the t moment by using a trained turbidity water turbidity recognition model and determining an initial mud content in the image of the sand and gravel pool at the t moment by using a trained sand and gravel mud content recognition model, then determining a second turbidity value of the sand and gravel pool at the t moment by using a turbidity detection device, and finally determining a target mud content in the sand and gravel pool at the t moment based on the first turbidity value, the second turbidity value and the initial mud content.
The method for determining sand and gravel content provided by the embodiment of the present application is specifically described above with reference to fig. 1 to 4, and the device and apparatus for determining sand and gravel content provided by the embodiment of the present application are specifically described below.
Fig. 5 is a schematic view of a sand and mud content determination device provided in an embodiment of the present application. The sand and mud content determination apparatus 500 includes a processing unit 510.
The processing unit 510 is configured to obtain an image of the muddy water pool at the time t and an image of the sand pool at the time t; determining a first turbidity value in the image of the turbid water pool based on the trained turbid water turbidity identification model; determining the initial mud content in the sand pool image based on the trained sand mud content recognition model; determining a second turbidity value of the turbid water pool at the time t based on the turbidity detection device; and determining the target mud content in the sand-gravel pool at the time t according to the first turbidity value, the second turbidity value and the initial mud content.
The processing unit 510 is further configured to determine a target mud content in the sand pool at time t using the following calculation:
y＝K 1 x 1 +K 2 x 2 +K 3 x 3
wherein y represents the target mud content in the sand pond; k 1 、K 2 、K 3 Representing a parameter value; x is the number of 1 Representing a first turbidity value, x 2 Representing a second turbidity value, x 3 Indicating the initial mud content.
The processing unit 510 is also used to obtain a plurality of sands of known mud content; respectively determining first turbidity values in a plurality of muddy water pool images with known mud content based on a muddy water turbidity identification model; respectively determining the initial mud content in a plurality of sand pool images with known mud content based on the sand mud content identification model; respectively determining second turbidity values of a plurality of sand with known mud content based on the turbidity detection device; determining K based on the first turbidity value, the second turbidity value and the initial sludge content 1 、K 2 、K 3 。
The processing unit 510 is further configured to obtain a training sample, the sample comprising an image of the turbid water pool of known turbidity; generating a prediction turbidity value by using a training sample and an initial AlexNet network model; calculating a network error based on the known turbidity value and the predicted turbidity value; and carrying out iterative training on the initial Alexnet network model based on the network error to obtain a trained turbidity water pool turbidity identification model.
The processing unit 510 is further configured to obtain a training sample, where the sample includes an image of a sand pool with a known mud content; generating a predicted mud content by using a training sample and an initial AlexNet network model; calculating a network error based on the known mud content and the predicted mud content; and carrying out iterative training on the initial Alexnet network model based on the network errors to obtain a trained sandstone pool mud content identification model.
Fig. 6 is a schematic view of the sand and mud content determination apparatus according to the embodiment of the present application. As shown in fig. 6, the sand-mud content determination apparatus 600 according to this embodiment includes: a processor 610, a memory 620 and a computer program 630 stored in said memory 620 and executable on said processor 610. The processor 610, when executing the computer program 630, implements the steps in the various sand-mud-content-determining method embodiments described above, such as steps S46-S460 shown in fig. 4. Alternatively, the processor 610 implements the functions of the modules/units in the above-described device embodiments when executing the computer program 630.
Illustratively, the computer program 630 may be partitioned into one or more modules/units, which are stored in the memory 620 and executed by the processor 610 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions describing the execution of the computer program 630 in the sand mud content determination apparatus 600.
The device 600 for determining the sand and gravel content may be a first terminal device or a second terminal device, or may be a desktop computer, a notebook computer, a palm computer, a cloud server, or an upper computer or other computing devices. The sand and mud content determination device may include, but is not limited to, a processor 610, a memory 620. It will be appreciated by those skilled in the art that fig. 6 is merely an example of a sand and mud content determination device and does not constitute a limitation of a sand and mud content determination device and may include more or fewer components than shown, or some components may be combined, or different components, for example, the sand and mud content determination device may also include input and output devices, network access devices, buses, etc.
The Processor 610 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 620 may be an internal storage unit of the sand and mud content determination apparatus 600, such as a hard disk or a memory of the sand and mud content determination apparatus 600. The memory 620 may also be an external storage device of the sand and mud content determination device 600, such as a plug-in hard disk, a memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the sand and mud content determination device 600. Further, the memory 620 may also include both an internal storage unit and an external storage device of the sand and mud content determination device 600. The memory 620 is used to store the computer program and other programs and data required by the equipment for sand and mud content determination. The memory 620 may also be used to temporarily store data that has been output or is to be output.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium, which stores a computer program, and the computer program can realize the sand and mud content determination method when being executed by a processor.
The embodiment of the application provides a computer program product, and when the computer program product runs on equipment with determined sand and mud content, the equipment with determined sand and mud content executes a method capable of realizing the determination of the sand and mud content.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and used by a processor to implement the steps of the embodiments of the methods described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A method of determining sand mud content, the method comprising:
acquiring a muddy water pool image at the time t and a sandstone pool image at the time t;
determining a first turbidity value in the image of the turbid water pool based on a trained turbidity identification model;
determining the initial mud content in the sand pool image based on the trained sand mud content recognition model;
determining a second turbidity value of the turbid water pool at the time t based on the turbidity detection device;
and determining the target mud content in the sand-gravel pool at the time t according to the first turbidity value, the second turbidity value and the initial mud content.
2. The method of claim 1, wherein determining a target mud content in the sand pond at time t from the first turbidity value, the second turbidity value, and the initial mud content comprises:
and determining the target mud content in the sand pool at the time t by using the following calculation formula:
y＝K 1 x 1 +K 2 x 2 +K 3 x 3
wherein y represents the target mud content in the sand pond; k 1 、K 2 、K 3 Representing a parameter value; x is the number of 1 Representing the first turbidity value, x 2 Representing said second turbidity value, x 3 Representing the initial mud content.
3. The method of claim 2, further comprising:
obtaining a plurality of sand with known mud content;
respectively determining first turbidity values in the plurality of muddy water pool images with known mud content based on the muddy water turbidity identification model;
respectively determining initial mud content in the sand pool images with known mud content based on the sand mud content identification model;
respectively determining second turbidity values of the plurality of sand with known mud content based on the turbidity detection device;
determining K based on the first turbidity value, the second turbidity value and an initial sludge content 1 、K 2 、K 3 。
4. The method of claim 3, further comprising:
obtaining a training sample, wherein the sample comprises a turbid pool image with known turbidity;
generating a predicted turbidity value by using the training sample and an initial AlexNet network model;
calculating a network error based on the known turbidity value and the predicted turbidity value;
and carrying out iterative training on the initial Alexnet network model based on the network error to obtain the trained turbidity water pool turbidity identification model.
5. The method of claim 1, further comprising:
obtaining a training sample, wherein the sample comprises a sandstone pool image with known mud content;
generating a predicted mud content by using the training sample and an initial AlexNet network model;
calculating a network error based on the known mud content and the predicted mud content;
and performing iterative training on the initial Alexnet network model based on the network error to obtain the trained sandstone pool mud content identification model.
6. The method of any one of claims 1-5, wherein the turbidity detecting means comprises at least one of a turbidity sensor, a colorimeter, or a spectrophotometer.
7. An apparatus for sand mud content determination, characterized in that the apparatus comprises means for performing the steps of the method according to any one of claims 1 to 6.
8. An apparatus for sand mud content determination, the apparatus comprising at least one processor coupled to at least one memory:
the at least one processor configured to execute computer programs or instructions stored in the at least one memory to cause the sand mud content determination apparatus to perform the method of any one of claims 1 to 6.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 6.
10. A chip, comprising: a processor for calling and running a computer program from a memory so that a device on which the chip is installed performs the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210866378.4A CN115343228B (en) | 2022-07-22 | 2022-07-22 | Method, device and equipment for determining sand and stone mud content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210866378.4A CN115343228B (en) | 2022-07-22 | 2022-07-22 | Method, device and equipment for determining sand and stone mud content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115343228A true CN115343228A (en) | 2022-11-15 |
| CN115343228B CN115343228B (en) | 2023-05-23 |
Family
ID=83950004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210866378.4A Active CN115343228B (en) | 2022-07-22 | 2022-07-22 | Method, device and equipment for determining sand and stone mud content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115343228B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292197A (en) * | 2023-10-10 | 2023-12-26 | 山东能源集团西北矿业有限公司 | TBM contact interface identification method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE59310235D1 (en) * | 1993-07-14 | 2001-12-20 | Lange Gmbh Dr Bruno | Method and device for optically determining solid concentrations in water |
| CN110782455A (en) * | 2019-11-19 | 2020-02-11 | 哈尔滨理工大学 | Novel method for determining mud content of raw sand based on image processing method |
| CN112712519A (en) * | 2021-01-15 | 2021-04-27 | 清华大学 | Non-contact type machine-made sandstone powder content intelligent real-time detection method and device |
| CN112712136A (en) * | 2021-01-15 | 2021-04-27 | 清华大学 | Method and device for intelligently manufacturing sand surface image-mud content relation data set |
| CN112748037A (en) * | 2020-12-24 | 2021-05-04 | 中山艾尚智同信息科技有限公司 | Method for rapidly measuring sand and stone mud content |
| CN112816475A (en) * | 2021-01-13 | 2021-05-18 | 太原市玉磊预拌混凝土有限公司 | Natural sand mud content detection device based on image scanning |
-
2022
- 2022-07-22 CN CN202210866378.4A patent/CN115343228B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE59310235D1 (en) * | 1993-07-14 | 2001-12-20 | Lange Gmbh Dr Bruno | Method and device for optically determining solid concentrations in water |
| CN110782455A (en) * | 2019-11-19 | 2020-02-11 | 哈尔滨理工大学 | Novel method for determining mud content of raw sand based on image processing method |
| CN112748037A (en) * | 2020-12-24 | 2021-05-04 | 中山艾尚智同信息科技有限公司 | Method for rapidly measuring sand and stone mud content |
| CN112816475A (en) * | 2021-01-13 | 2021-05-18 | 太原市玉磊预拌混凝土有限公司 | Natural sand mud content detection device based on image scanning |
| CN112712519A (en) * | 2021-01-15 | 2021-04-27 | 清华大学 | Non-contact type machine-made sandstone powder content intelligent real-time detection method and device |
| CN112712136A (en) * | 2021-01-15 | 2021-04-27 | 清华大学 | Method and device for intelligently manufacturing sand surface image-mud content relation data set |
Non-Patent Citations (2)
| Title |
|---|
| 耿方圆 等: "基于改进UNet 网络的机制砂石粉分割量化方法" * |
| 胡桂平 等: "基于图像识别的水质浊度测量技术研究" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292197A (en) * | 2023-10-10 | 2023-12-26 | 山东能源集团西北矿业有限公司 | TBM contact interface identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115343228B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | A deep learning approach for fast detection and classification of concrete damage | |
| Wang et al. | Convolutional neural network-based pavement crack segmentation using pyramid attention network | |
| CN110263706B (en) | Method for detecting and identifying dynamic target of vehicle-mounted video in haze weather | |
| CN109241967B (en) | Thyroid ultrasound image automatic identification system based on deep neural network, computer equipment and storage medium | |
| O’Byrne et al. | An underwater lighting and turbidity image repository for analysing the performance of image-based non-destructive techniques | |
| CN112330593A (en) | Building surface crack detection method based on deep learning network | |
| Dong et al. | Innovative method for pavement multiple damages segmentation and measurement by the Road-Seg-CapsNet of feature fusion | |
| CN110751644A (en) | Road surface crack detection method | |
| CN114723709A (en) | Tunnel disease detection method and device and electronic equipment | |
| Yu et al. | Intelligent Crack Detection and Quantification in the Concrete Bridge: A Deep Learning‐Assisted Image Processing Approach | |
| Guo et al. | A novel transformer-based network with attention mechanism for automatic pavement crack detection | |
| CN115343228A (en) | Method, device and equipment for determining sand and stone mud content | |
| CN115830004A (en) | Surface defect detection method, device, computer equipment and storage medium | |
| CN113469097A (en) | SSD (solid State disk) network-based real-time detection method for water surface floating object multiple cameras | |
| Zamani et al. | Deep semantic segmentation for visual scene understanding of soil types | |
| CN115205255A (en) | Stone automatic grading method and system based on deep learning | |
| Du Nguyen et al. | Crack segmentation of imbalanced data: The role of loss functions | |
| Li et al. | Real-time instance-level detection of asphalt pavement distress combining space-to-depth (SPD) YOLO and omni-scale network (OSNet) | |
| Yuan et al. | Automated pixel-level crack detection and quantification using deep convolutional neural networks for structural condition assessment | |
| Ye et al. | An advanced AI-based lightweight two-stage underwater structural damage detection model | |
| CN105303584B (en) | Moving target detecting method based on laser radar and device | |
| Mei et al. | A conditional wasserstein generative adversarial network for pixel-level crack detection using video extracted images | |
| CN110766662B (en) | Forging surface crack detection method based on multi-scale and multi-layer feature learning | |
| CN116861262A (en) | Perception model training method and device, electronic equipment and storage medium | |
| Gooda et al. | Automatic detection of road cracks using EfficientNet with residual U-net-based segmentation and YOLOv5-based detection |
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 |