CN114332196A - Method, equipment and device for acquiring weight percentage of material part and storage medium - Google Patents
Method, equipment and device for acquiring weight percentage of material part and storage medium Download PDFInfo
- Publication number
- CN114332196A CN114332196A CN202111515772.5A CN202111515772A CN114332196A CN 114332196 A CN114332196 A CN 114332196A CN 202111515772 A CN202111515772 A CN 202111515772A CN 114332196 A CN114332196 A CN 114332196A
- Authority
- CN
- China
- Prior art keywords
- material part
- weight percentage
- information
- part set
- area
- 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
- 239000000463 material Substances 0.000 title claims abstract description 474
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 173
- 229910000831 Steel Inorganic materials 0.000 claims description 88
- 239000010959 steel Substances 0.000 claims description 88
- 238000013507 mapping Methods 0.000 claims description 49
- 230000011218 segmentation Effects 0.000 claims description 34
- 239000002699 waste material Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 239000002436 steel type Substances 0.000 description 11
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 241000252254 Catostomidae Species 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, equipment, a device and a storage medium for acquiring the weight percentage of a material, wherein the method comprises the following steps: acquiring an image data set of a material part set; obtaining area percentage information of the material part set based on the image data set of the material part set; and inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set. The invention belongs to the field of computer vision, and provides a method for acquiring the weight percentage of a material, which can automatically and accurately acquire the weight percentage of a material set based on the area percentage of the material set without depending on fuzzy prior knowledge, so that the acquired weight percentage of the material set is more accurate.
Description
Technical Field
The invention relates to the field of computer vision, in particular to a method, equipment, a device and a storage medium for acquiring weight percentage of a material.
Background
At present, in scenes such as scrap steel part recovery, building part batch shipment and the like, a part quality detection worker (quality inspector) is often relied on to judge and record a part set and weight percentage thereof, and the judgment of the current quality inspector on the weight percentage of the part is mainly realized by priori knowledge derivation.
However, the weight percentage of the material set deduced by fuzzy prior knowledge is limited by manual experience to a great extent, namely the problem of low accuracy exists.
Disclosure of Invention
The invention mainly aims to provide a method for acquiring the weight percentage of a material, and aims to solve the technical problem of low accuracy of the weight percentage of a material set inferred by fuzzy prior knowledge at present.
In order to achieve the above object, the present invention provides a method for obtaining weight percentage of a material, including:
acquiring an image data set of a material part set;
obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentages of different types of material parts in the material part set;
inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
and determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
Optionally, before the step of inputting the area percentage information of the material set into the preset weight percentage prediction model, the method includes:
acquiring a training data set, wherein each set of training data of the training data set corresponds to a material set, and the set of training data comprises weight percentage information and area percentage information of the material set corresponding to the set of training data;
determining the mapping model parameters based on the training data set;
and performing iterative training on the mapping model based on the training data set and the model parameters to obtain the weight percentage prediction model with the model parameters meeting the precision condition.
Optionally, the step of iteratively training the mapping model based on the training data set and the model parameters to obtain the weight percentage prediction model with model parameters satisfying a precision condition includes:
inputting area percentage information for each set of training data of the set of training data to the mapping model;
obtaining weight percentage information training prediction results of each group of training data of the training data set based on the area percentage information of each group of training data of the training data set and the model parameters by using the mapping model;
carrying out difference calculation on the weight percentage information training prediction result of each group of training data of the training data set and the weight percentage information of each group of training data of the training data set correspondingly to obtain a training error result;
judging whether the training error result meets an error standard meeting the preset error threshold range indication;
if the training error result does not meet the error standard indicated by the preset error threshold range, updating the current model parameters of the mapping model, and returning to the step of obtaining the weight percentage information training prediction result of each group of training data of the training data set by using the mapping model based on the area percentage information of each group of training data of the training data set and the model parameters, and stopping training until the training error result meets the error standard indicated by the preset error threshold range;
taking the mapping model that has stopped training as the weight percentage prediction model with model parameters that satisfy a precision condition.
Optionally, the training error result includes a mean square error result, the preset error threshold range includes a preset mean square error threshold range, and the determining whether the training error result satisfies an error criterion indicated by the preset error threshold range includes: and judging whether the mean square error result is smaller than a preset mean square error threshold range.
Optionally, the determining of the model parameters includes: at least one of density attribute, shape attribute, and color attribute of the different kinds of parts.
Optionally, the step of obtaining information about percentage of area of the material set based on the image data set of the material set includes:
the image data set of the material part set comprises at least one original image;
respectively carrying out material part segmentation on the at least one original image by utilizing a pre-trained image semantic segmentation model to obtain at least one material part segmentation image which is in one-to-one correspondence with the at least one original image, wherein each material part segmentation image respectively comprises the type information, the position information, the outline information and the size information of each material part obtained by segmentation in the material part segmentation image;
based on the type information, the position information, the outline information and the size information of each material part respectively included in the at least one material part segmentation image, carrying out duplication removing operation on each material part in the at least one material part segmentation image so that each material part is only subjected to area calculation once based on the size information in all material part segmentation images;
counting the type information of each material part and calculating to obtain the area based on the size information, and acquiring the area percentage of different types of material parts in the material part set;
and integrating the area percentages of the different types of parts in the part set to obtain the area percentage information of the part set.
Optionally, each set of training data of the training data set includes accuracy of the weight percentage information and the area percentage information of the material set corresponding to the set of training data, which both satisfy the accuracy standard indicated by the preset accuracy threshold range.
Optionally, the at least one piece of associated information of the material set related to the result of predicting the weight percentage information of the material set includes price information of the material set;
the determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set comprises:
acquiring the total weight of the material and part set, and acquiring the respective corresponding weights of different types of material and parts in the material and part set by using the weight percentage information prediction result of the material and part set;
and obtaining the price information of the material part set based on the respective corresponding weights of different types of material parts of the material part set and a preset unit price table of each type of material part.
Optionally, the method for acquiring the weight percentage of the material piece is used for acquiring the weight percentage of different types of material pieces in the process of carrying the steel scrap material piece set:
the material part set is a scrap steel material part set in a fixed area;
the image data set of the material part set comprises an initial image of the scrap steel material part set in the fixed area and an image obtained after carrying operation is carried out on a scrap steel material part subset in the scrap steel material part set in the fixed area each time;
the area percentage information of the material part set comprises the area percentage of different types of waste steel material parts in the waste steel material part set in the fixed area;
the weight percentage information of the material part set comprises the weight percentage of different types of waste steel material parts in the waste steel material part set in the fixed area.
The application also provides an acquisition device of material weight percent, the acquisition device of material weight percent includes:
the acquisition module is used for acquiring an image data set of the material part set;
the area percentage information determining module is used for obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentage of different types of material parts in the material part set;
the input module is used for inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
and the information determination module is used for determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
The present application further provides an electronic device, the electronic device including: a memory, a processor, and a program stored on the memory for implementing the method for acquiring weight percent of a part,
the memory is used for storing a program for realizing the acquisition method of the weight percentage of the material;
the processor is used for executing a program for realizing the acquiring method of the weight percentage of the material part so as to realize the steps of the acquiring method of the weight percentage of the material part.
The application also provides a storage medium, wherein a program for realizing the method for acquiring the weight percentage of the material part is stored on the storage medium, and the program for realizing the method for acquiring the weight percentage of the material part is executed by a processor to realize the steps of the method for acquiring the weight percentage of the material part.
The application also provides a computer program product, which comprises a computer program, and the computer program realizes the method for acquiring the weight percentage of the material part when being executed by a processor.
Compared with the prior art that fuzzy prior knowledge is required to be relied on, and the weight percentage of a material set is deduced based on the area percentage of the material set through human intervention, so that the obtained weight percentage of the material set is inaccurate, the method, the device and the storage medium for obtaining the weight percentage of the material set are provided, and an image data set of the material set is obtained; obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentages of different types of material parts in the material part set; inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set; the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information; and determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set. In the application, the area percentages of different types of parts in a part set (the area percentage information of the part set) are obtained based on an image data set of the part set, then the area percentage information of the part set is input into a weight percentage prediction model, and the weight percentage information of the part set is subjected to weight percentage prediction processing, because the weight percentage prediction model is obtained by carrying out iterative training on a preset mapping model based on training data of the part set with the weight percentage information and the area percentage information, the weight percentage information of the part set can be predicted more accurately, and further at least one piece of associated information of the part set related to the weight percentage information prediction result of the part set is determined, namely fuzzy artificial experience is not required to be relied on in the application, the weight percentage of the material assembly can be accurately obtained based on the area percentage of the material assembly.
Drawings
FIG. 1 is a schematic diagram of an apparatus architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for obtaining weight percentages of parts according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for obtaining weight percentages of parts according to a second embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example one
In a first embodiment of the method for acquiring the weight percentage of a material, referring to fig. 2, the method for acquiring the weight percentage of a material includes:
s100, acquiring an image data set of a material part set;
step S200, obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentage of different types of material parts in the material part set;
step S300, inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
step S400, determining at least one type of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
In this embodiment, it should be noted that the method for acquiring the weight percentage of the material may be applied to an apparatus for acquiring the weight percentage of the material, where the apparatus for acquiring the weight percentage of the material belongs to an apparatus for acquiring the weight percentage of the material, and the system for acquiring the weight percentage of the material belongs to the apparatus for acquiring the weight percentage of the material.
In this embodiment, the specific application scenarios may be:
in the prior art, a quality inspector gives a material set and weight percentage information thereof in a vehicle number after seeing the whole unloading process, and the method for judging the weight percentage of the material by the quality inspector is mainly realized by priori knowledge derivation, and the weight percentage of the material set deduced by relying on fuzzy priori knowledge is limited by manual experience to a great extent, so that the weight percentage corresponding to the material cannot be accurately deduced, and the accuracy of the weight percentage of the given material set is low.
In this embodiment, a preset weight percentage prediction model is built in the device for acquiring the weight percentage of the material, or an external preset weight percentage prediction model may be called, and the following description will specifically take the example that the preset weight percentage prediction model is built in the device for acquiring the weight percentage of the material.
In this embodiment, since the preset weight percentage prediction model is a trained model, the area percentage information of the material set is directly input, and thus the prediction result of the weight percentage information corresponding to the material set can be output, and further, at least one piece of associated information of the material set, such as price information, related to the weight percentage information prediction result of the material set can be determined.
The method comprises the following specific steps:
s100, acquiring an image data set of a material part set;
in this embodiment, first, an image data set of the material set is obtained, where the manner of obtaining the image data set of the material set may be:
all the parts are fixed by using the suckers, and the part set images are collected by the camera, wherein the camera can be a camera inside the electronic equipment and also can be a camera externally arranged on the electronic equipment.
In this embodiment, the material assembly can be a section steel assembly, and also can be a scrap steel assembly, specifically, different types of materials in the section steel assembly can be angle steel, round steel, square steel, and different types of materials in the scrap steel assembly can be steel rails, pipes, mechanical parts, and the like.
In this embodiment, the image dataset of the material set includes dataset information such as type information, position information, outline information, and size information of the material, for example, the image dataset information of the material set includes that the type of the material is square steel or round steel; the square steel is positioned at the left side of the image, and the round steel is positioned at the right side of the image; the square steel has a square outline, and the round steel has a round outline; the size of the square steel is 140mm x 140mm, and the size of the round steel is phi 110 mm.
Step S200, obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentage of different types of material parts in the material part set;
in this embodiment, images of different types of parts in the image data set are determined first, and then based on the images of the different types of parts, the area percentages of the different types of parts in the part set are obtained.
Specifically, the step S200 includes the following steps S210 to S250:
step S210, an image data set of the material part set comprises at least one original image;
step S220, respectively carrying out material part segmentation on the at least one original image by utilizing a pre-trained image semantic segmentation model to obtain at least one material part segmentation image which is in one-to-one correspondence with the at least one original image, wherein each material part segmentation image respectively comprises the type information, the position information, the contour information and the size information of each material part obtained by segmentation in the material part segmentation image;
in this embodiment, the image semantic segmentation model is trained and may be called directly, so that the at least one original image is segmented into at least one material segmentation image corresponding to the at least one original image one by using the pre-trained image semantic segmentation model, specifically, the segmented image is obtained by segmenting the at least one original image by using an edge segmentation method in the image semantic segmentation model, where the edge segmentation method is to obtain the segmented image by detecting a place where a gray level or a structure has a sudden change, where the place with the sudden change indicates the end of one region and also the beginning of another region, i.e., where the gray level of an edge pixel in the image is discontinuous, and further distinguish the at least one original image from the at least one original image.
After the material part segmentation image is obtained, the type information, the position information, the outline information and the size information of each material part can be obtained by analyzing the segmented image, specifically, the step of analyzing the segmented image is that the electronic equipment compares and identifies the material part collection image through the material part image information in a material part database to obtain the material part collection type information, wherein the material part database comprises the image information of all the material parts in the engineering project.
Step S230, performing duplication elimination operation on each material piece in the at least one material piece segmentation image based on the type information, the position information, the outline information and the size information of each material piece respectively included in the at least one material piece segmentation image, so that the area of each material piece is calculated only once based on the size information in all the material piece segmentation images;
in this embodiment, the deduplication operation is performed by binarizing each segmented image to obtain pixel values of each pixel point of the binarized image, and comparing the pixel values of all the images to obtain the same part, thereby completing deduplication.
In this embodiment, the purpose of deduplication is: for each material part, the area can be superposed once based on the size information as long as the type is determined, so that redundant other information does not need to be processed, and the computing resource is saved.
Step S240, counting the type information of each material part and calculating the area based on the size information to obtain the area percentage of different types of material parts in the material part set;
for example, a square steel type material piece, with dimensions of 1400mm, was calculated to have an area of 1960000mm2And the size of the round steel type material piece is phi 1100mm, the length of the round steel type material piece is 500mm, and the area of the round steel type material piece is 3627600mm through calculation2。
Step S250, integrating the area percentages of different types of parts in the part set to obtain the area percentage information of the part set.
In this embodiment, the area percentage information of the material set is obtained by taking the area percentage of each of the different types of materials.
For example, the area of a square steel type material piece is: 1960000mm2(ii) a The area ratio or area percentage is A%;
the area of the round steel type material part is as follows: 3627600mm2The area ratio or area percentage is B%.
Step S300, inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
specifically, in this embodiment, the total manner of obtaining the output result based on the input information is adopted to obtain the weight percentage prediction result of the material set, that is, the weight percentage prediction result of the material set is obtained in a manner of obtaining the output result based on the input information by using a trained preset weight percentage prediction model. Specifically, as long as the area percentage information of the material part set is input, the weight percentage prediction result of the material part set can be output, and the output prediction result can be in a numerical mode or a table mode.
The weight percentage prediction result may be a number or a table, since the material set is a set of different types of materials, the area percentage information is a set of area percentage data (area percentages of the different types of materials), and the table refers to table 1, where the area percentage data about the square steel type materials in the obtained area percentage information of the material set is "square steel, area percentage: 23% ", of course, the area percentage information of the material assembly further includes area percentage data about the angle steel type material, and the area percentage data about the angle steel type material may specifically be: angle steel, area percentage: 25% ". Since the area percentage information of the part set is a set (plurality) of percentage data, all kinds of parts and their respective corresponding weight percentage prediction result data can be presented in a table manner.
TABLE 1
The weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information; therefore, the weight percentage information of the material set can be accurately predicted, and further, at least one piece of associated information of the material set related to the weight percentage information prediction result of the material set is determined, namely, the weight percentage of the material set can be accurately obtained based on the area percentage of the material set without relying on fuzzy prior knowledge in the application.
Step S400, determining at least one type of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
In this embodiment, the related information of the material set related to the result of predicting the weight percentage information of the material set may be price information of the material set, or may be volume information of the material set.
The step S400 includes the following steps S410 to S420:
step S410, acquiring the total weight of the material and part set, and acquiring the respective corresponding weights of different types of material and parts in the material and part set by using the weight percentage information prediction result of the material and part set;
for example, the total weight of the material set is 40kg, the prediction result of the weight percentage information of the square steel set is 20%, the prediction result of the weight percentage information of the round steel set is 40%, the prediction result of the weight percentage information of the angle steel set is 40%, the prediction result of the weight percentage information of the square steel set is 8kg, the prediction result of the weight percentage information of the round steel set is 16kg, and the prediction result of the weight percentage information of the angle steel set is 16 kg.
Step S420, obtaining price information of the material assembly based on the weight corresponding to each different type of material in the material assembly and a preset unit price table of each type of material, that is, obtaining the price corresponding to each different type of material in the material assembly.
For example, the prediction result of the square steel set weight percentage information is 8kg, the prediction result of the round steel set weight percentage information is 16kg, the prediction result of the angle steel set weight percentage information is 16kg, the preset square steel unit price table is 3 yuan/kg, the round steel unit price table is 4 yuan/kg, and the angle steel unit price table is 5 yuan/kg, and the square steel part price is 24 yuan, the round steel part price is 64 yuan, and the angle steel part price is 80 yuan.
In addition, step S420 may further include: and obtaining the volume information of the material part set based on the respective corresponding weights of the different types of material parts of the material part set and a preset density table of the different types of material parts, namely obtaining the respective corresponding volumes of the different types of material parts in the material part set.
Compared with the prior art that fuzzy prior knowledge is required to be relied on, and the weight percentage of a material set is deduced based on the area percentage of the material set through human intervention, so that the obtained weight percentage of the material set is inaccurate, the method, the device and the storage medium for obtaining the weight percentage of the material set are provided, and an image data set of the material set is obtained; obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentages of different types of material parts in the material part set; inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set; the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information; and determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set. In the application, the area percentages of different types of parts in a part set (the area percentage information of the part set) are obtained based on an image data set of the part set, then the area percentage information of the part set is input into a weight percentage prediction model, and the weight percentage prediction processing is performed on the area percentage information of the part set, because the weight percentage prediction model is obtained by iteratively training a preset mapping model based on training data of the part set with the weight percentage information and the area percentage information, the weight percentage information of the part set can be accurately predicted, and further at least one piece of associated information of the part set related to the weight percentage information prediction result of the part set is determined, namely fuzzy artificial experience is not required in the application, the weight percentage of the material assembly can be accurately obtained based on the area percentage of the material assembly.
Example two
Based on the first embodiment of the present application, another embodiment of the present application is provided, and in the method for obtaining weight percentages of material pieces provided in this embodiment, before the step of inputting the area percentage information of the material piece set into the preset weight percentage prediction model in step S300, the method includes the following steps a100 to a 300:
step A100, acquiring a training data set, wherein each set of training data of the training data set corresponds to a material set, and the set of training data comprises weight percentage information and area percentage information of the material set corresponding to the set of training data;
in this embodiment, each set of training data in the training data set includes accuracy of the weight percentage information and the area percentage information of the material set corresponding to the set of training data, which both satisfy the accuracy standard indicated by the preset accuracy threshold range. In a specific implementation, each set of training data of the training data set may be a data table, where the data table is used to store weight percentage information and area percentage information of the part set corresponding to the set of training data, that is, is used to store weight percentages and area percentages of different types of parts of the part set corresponding to the set of training data, that is, the part set is a set of different types of parts, the weight percentage information is a set of weight percentage data (weight percentages of the different types of parts), and the area percentage information is a set of area percentage data (area percentages of the different types of parts).
The weight percentage information and the area percentage information of the material set corresponding to any one group of training data can be obtained by measuring and calculating through material measuring equipment, specifically, the weight percentage information of the material set can be obtained by weighing the weight of each material set through a mobile platform scale, the total weight of the material set is calculated, and the training data of the weight percentage information of each material set is obtained through calculation based on the weight of the material set and the total weight of the material set; for example, a square steel set is weighed by a moving platform scale to be 10kg, a round steel set is weighed to be 5kg, an angle steel set is weighed to be 5kg, the total weight of material parts is 20kg, the square steel set weight percentage information is 50%, the angle steel set weight percentage information is 25%, and the round steel set weight percentage information is 25%;
the area percentage information of the material part set can be obtained by measuring the area of the material part set by using an area measuring instrument, calculating the sum of the area of the material part, and calculating the area percentage of the material part set based on the area of the material part set and the sum of the area of the material partTraining data of the ratio information or acquiring images of the total material, and obtaining training data of area percentage information of the material set through difference calculation of each material; for example, the area of the square steel aggregate is 10m as measured by an area measuring instrument2The aggregate area of the round steel is 5m2The collective area of the angle steel is 5m2The total area of the material part is 20m through calculation2The percentage information of the square steel set area is 50%, the percentage information of the angle steel set area is 25%, and the percentage information of the round steel set area is 25%.
The weight percentage information and the area percentage information of the material set corresponding to any one group of training data can also be data which is obtained by a material quality detection worker with abundant experience and meets the accuracy standard indicated by the preset accuracy threshold range after being audited.
Step A200, determining the mapping model parameters based on the training data set;
the correspondence of data elements is established between two data models, and this process is called data mapping. In this embodiment, a mapping model is created first, and the mapping model is a model having a correspondence relationship between weight percentage information and area percentage information, which is preliminarily created based on training data of a material set having the weight percentage information and the area percentage information. The mapping model has the mapping function, and does not need to have high accuracy.
In this embodiment, the determining of the model parameters includes: the density property, the shape property, the color property and other properties of different types of parts, such as square steel, can be different from those of other types of scrap steel due to the square steel's own properties and the square steel model parameters (the mapping relation between the area percentage and the weight percentage).
That is, in this embodiment, the initial model parameter is associated with the mapping relationship between the area percentage information of the material set and the weight percentage information, for example, a set of area percentage data about the angle steel type material in the acquired area percentage information of the material set is "angle steel, area percentage: 10% ", and a group of weight percentage data about angle steel type material parts in the weight percentage information of the corresponding material part set is angle steel, weight percentage: 20% ", i.e. the model parameters for the angle steel in the newly created mapping model are associated with 2 (20%/10%).
Step A300, iteratively training the mapping model based on the training data set and the model parameters to obtain the weight percentage prediction model with model parameters satisfying the precision condition.
In this embodiment, after the initial training, the mapping model is iteratively trained (for a preset number of times, etc.) based on the training data set and the model parameters, so as to obtain the weight percentage prediction model having the model parameters satisfying the accuracy condition.
In the present embodiment, the accuracy condition is associated with a standard deviation, a variance, and the like.
Referring to fig. 3, the step a300 includes the following steps a310-a 360:
step A310, inputting the area percentage information of each set of training data of the training data set into the mapping model;
step A320, obtaining a weight percentage information training prediction result of each group of training data of the training data set based on the area percentage information of each group of training data of the training data set and the model parameters by using the mapping model;
step A330, performing difference calculation on the weight percentage information training prediction result of each group of training data in the training data set and the weight percentage information of each group of training data in the training data set correspondingly to obtain a training error result;
step A340, judging whether the training error result meets an error standard indicated by a preset error threshold range;
step A350, if the training error result does not meet the error standard indicated by the preset error threshold range, updating the current model parameters of the mapping model, and returning to the step of obtaining the weight percentage information training prediction result of each group of training data of the training data set by using the mapping model based on the area percentage information of each group of training data of the training data set and the model parameters, until the training error result meets the error standard indicated by the preset error threshold range, stopping training;
step A360, the mapping model which is stopped from training is used as the weight percentage prediction model with model parameters meeting the precision condition.
In a specific implementation, step a310 inputs the area percentage information of each set of training data of the training data set into the mapping model, for example, a set of training data:
the area percentage information comprises a plurality of pieces of area percentage data related to different types of material pieces, the area percentage data are input into the mapping model, and the mapping model is used for obtaining a weight percentage information training prediction result of the training data set based on the area percentage information of the training data set and the model parameters, namely, a plurality of pieces of weight percentage data related to each type of material pieces are obtained corresponding to the plurality of pieces of area percentage data related to the different types of material pieces.
Then, carrying out difference calculation on the weight percentage information training prediction result of each group of training data of the training data set and the weight percentage information of each group of training data of the training data set correspondingly to obtain a training error result, and further judging whether the training error result meets an error standard indicated by a preset error threshold range; in this embodiment, the training error result includes a mean square error result:
wherein N represents the total number of pre-specified material categories, wpnRepresents the weight percentage, wp' of the material class n relative to the whole vehiclenAnd (4) representing the weight percentage training prediction result of the material part type n relative to all the material parts of the whole vehicle.
Correspondingly, the preset error threshold includes a preset mean square error threshold, and as known to those skilled in the art, the smaller the mean square error threshold is, the more accurate the representative model is, and the step of determining whether the training error result satisfies the error criterion indicated by the preset error threshold includes: and judging whether the mean square error result is smaller than a preset mean square error threshold value or not.
If the training error result does not meet the error standard indicated by the preset error threshold range, updating the current model parameters of the mapping model, and returning to the step of obtaining the weight percentage information training prediction result of each group of training data of the training data set by using the mapping model based on the area percentage information of each group of training data of the training data set and the model parameters, and stopping training until the training error result meets the error standard indicated by the preset error threshold range;
in this embodiment, the model parameters of the mapping model are updated through iterative training until the training error result meets the error standard indicated by the preset error threshold range, thereby completing the iterative training.
In this embodiment, since the weight percentage prediction model is obtained by accurately training, a foundation is laid for accurately determining at least one piece of associated information of the material set related to the weight percentage information prediction result of the material set.
EXAMPLE III
Based on the first embodiment and the second embodiment in the present application, another embodiment of the present application is provided, in which the step of the method for acquiring weight percentages of parts is used for acquiring weight percentages of different types of parts in a process of transporting a set of scrap parts, and the method includes the following steps B100-B400:
step B100, the material part set is a scrap steel material part set in a fixed area, and the scrap steel material part set comprises different types of material parts;
wherein, fixed area can be a railway carriage or compartment region, also can be a ship case region, for example, has placed a plurality of square steels, a plurality of angle steel and a plurality of round steel in a railway carriage or compartment region, and material set includes a plurality of square steels, a plurality of angle steel and a plurality of round steel promptly.
Step B200, the image data set of the material part set comprises an initial image of the scrap steel material part set in the fixed area and an image obtained after carrying operation is carried out on a scrap steel material part subset in the scrap steel material part set in the fixed area each time;
step B300, the area percentage information of the material part set comprises the area percentage of different types of waste steel material parts in the waste steel material part set in the fixed area;
and step B400, the weight percentage information of the material part set comprises the weight percentage of different types of waste steel material parts in the waste steel material part set in the fixed area.
In this embodiment, an application scenario of the method for obtaining weight percentage of a material part in the present application is obtaining weight percentage of a steel scrap material part in a fixed area, and the method for obtaining weight percentage of a steel scrap material part in a fixed area in the present application is basically the same as each embodiment of the method for obtaining weight percentage of a material part, and is not described herein again.
Example four
The application also provides an acquisition device of material weight percent, the acquisition device of material weight percent includes:
the acquisition module acquires an image data set of the material part set;
the area percentage information determining module is used for obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentage of different types of material parts in the material part set;
the input module is used for inputting the area percentage information of the material part set into a weight percentage prediction model, carrying out weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
and the associated information determining module is used for determining at least one type of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
The specific implementation manner of the device for acquiring the weight percentage of the material part is basically the same as that of each embodiment of the method for acquiring the weight percentage of the material part, and is not described herein again.
EXAMPLE five
The present application further provides an electronic device, the electronic device including: a memory, a processor and an acquisition program stored on the memory for implementing the weight percentage of the part,
the memory is used for storing an acquisition program for realizing the weight percentage of the material;
the processor is used for executing an acquisition program for realizing the weight percentage of the material part so as to realize the steps of the acquisition method for the weight percentage of the material part.
As shown in fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention.
The electronic device in the embodiment of the present invention may be a PC, or may be a mobile electronic device having a display function, such as a smart phone, a tablet computer, an electronic book reader, an MP3(Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3) player, an MP4(Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 3) player, a portable computer, or the like.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the electronic device may further include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and so forth. Such as light sensors, motion sensors, and other sensors. In particular, the light sensor may include an ambient light sensor that adjusts the brightness of the display screen based on the intensity of ambient light, and a proximity sensor that turns off the display screen and/or backlight when the mobile electronic device is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the mobile electronic device is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile electronic device; of course, the mobile electronic device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the electronic device configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an acquisition program of a weight percentage of a part.
In the electronic device shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to invoke the get procedure for the weight percentage of the part in the memory 1005.
The specific implementation manner of the device for acquiring the weight percentage of the material part is basically the same as that of each embodiment of the method for acquiring the weight percentage of the material part, and is not described herein again.
EXAMPLE six
The application also provides a storage medium, wherein the storage medium is stored with a program for realizing the method for acquiring the weight percentage of the material part, and the program for realizing the method for acquiring the weight percentage of the material part is executed by a processor to realize the steps of the method for acquiring the weight percentage of the material part.
The specific implementation of the storage medium of the present application is substantially the same as the embodiments of the method for acquiring the weight percentage of the material part, and is not described herein again.
EXAMPLE seven
The application also provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to realize the method for acquiring the weight percentage of the material part.
The specific implementation manner of the computer program product of the present application is substantially the same as that of each embodiment of the method for acquiring the weight percentage of the material, and is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be substantially or partially embodied in the form of a software product, which is stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling an electronic device (e.g. a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (13)
1. The method for acquiring the weight percentage of the material part is characterized by comprising the following steps of:
acquiring an image data set of a material part set;
obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentages of different types of material parts in the material part set;
inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
and determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
2. The method for acquiring weight percentage of material pieces according to claim 1, wherein the step of inputting the area percentage information of the material piece set into the weight percentage prediction model is preceded by the steps of:
acquiring a training data set, wherein each set of training data of the training data set corresponds to a material set, and the set of training data comprises weight percentage information and area percentage information of the material set corresponding to the set of training data;
determining the mapping model parameters based on the training data set;
and performing iterative training on the mapping model based on the training data set and the model parameters to obtain the weight percentage prediction model with the model parameters meeting the precision condition.
3. The method for obtaining weight percentage of material part according to claim 2, wherein the step of iteratively training the mapping model based on the training data set and the model parameters to obtain the weight percentage prediction model with model parameters satisfying a precision condition includes:
inputting area percentage information for each set of training data of the set of training data to the mapping model;
obtaining weight percentage information training prediction results of each group of training data of the training data set based on the area percentage information of each group of training data of the training data set and the model parameters by using the mapping model;
carrying out difference calculation on the weight percentage information training prediction result of each group of training data of the training data set and the weight percentage information of each group of training data of the training data set correspondingly to obtain a training error result;
judging whether the training error result meets an error standard indicated by a preset error threshold range;
if the training error result does not meet the error standard indicated by the preset error threshold range, updating the current model parameters of the mapping model, and returning to the step of obtaining the weight percentage information training prediction result of each group of training data of the training data set by using the mapping model based on the area percentage information of each group of training data of the training data set and the model parameters, and stopping training until the training error result meets the error standard indicated by the preset error threshold range;
taking the mapping model that has stopped training as the weight percentage prediction model with model parameters that satisfy a precision condition.
4. The method according to claim 3, wherein the training error result comprises a mean square error result, the preset error threshold range comprises a preset mean square error threshold range, and the determining whether the training error result satisfies an error criterion indicated by the preset error threshold range comprises: and judging whether the mean square error result is smaller than a preset mean square error threshold range.
5. The method for acquiring weight percentage of material parts according to claim 2, wherein the determination of the model parameters is based on the following steps: at least one of density attribute, shape attribute, and color attribute of the different kinds of parts.
6. The method for acquiring weight percentage of material pieces according to claim 1, wherein the step of obtaining the area percentage information of the material piece set based on the image data set of the material piece set comprises:
the image data set of the material part set comprises at least one original image;
respectively carrying out material part segmentation on the at least one original image by utilizing a pre-trained image semantic segmentation model to obtain at least one material part segmentation image which is in one-to-one correspondence with the at least one original image, wherein each material part segmentation image respectively comprises the type information, the position information, the outline information and the size information of each material part obtained by segmentation in the material part segmentation image;
based on the type information, the position information, the outline information and the size information of each material part respectively included in the at least one material part segmentation image, carrying out duplication removing operation on each material part in the at least one material part segmentation image so that each material part is only subjected to area calculation once based on the size information in all material part segmentation images;
counting the type information of each material part and calculating to obtain the area based on the size information, and acquiring the area percentage of different types of material parts in the material part set;
and integrating the area percentages of the different types of parts in the part set to obtain the area percentage information of the part set.
7. The method for acquiring weight percentage of material part according to claim 2, wherein each set of training data of the training data set includes the accuracy of the weight percentage information and the area percentage information of the material part set corresponding to the set of training data, which both satisfy the accuracy standard indicated by the preset accuracy threshold range.
8. The method for acquiring the weight percentage of the material part according to claim 1, wherein at least one piece of associated information of the material part set, which is related to the result of predicting the weight percentage information of the material part set, includes price information of the material part set;
the determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set comprises:
acquiring the total weight of the material and part set, and acquiring the respective corresponding weights of different types of material and parts in the material and part set by using the weight percentage information prediction result of the material and part set;
and obtaining the price information of the material part set based on the respective corresponding weights of different types of material parts of the material part set and a preset unit price table of each type of material part.
9. The method for obtaining the weight percentage of the material part according to any one of claims 1 to 8, wherein the method for obtaining the weight percentage of the material part is used for obtaining the weight percentages of different material parts in the process of carrying the scrap steel material part set:
the material part set is a scrap steel material part set in a fixed area;
the image data set of the material part set comprises an initial image of the scrap steel material part set in the fixed area and an image obtained after carrying operation is carried out on a scrap steel material part subset in the scrap steel material part set in the fixed area each time;
the area percentage information of the material part set comprises the area percentage of different types of waste steel material parts in the waste steel material part set in the fixed area;
the weight percentage information of the material part set comprises the weight percentage of different types of waste steel material parts in the waste steel material part set in the fixed area.
10. The device for acquiring the weight percentage of the material part is characterized by comprising the following components in percentage by weight:
the acquisition module is used for acquiring an image data set of the material part set;
the area percentage information determining module is used for obtaining area percentage information of the material part set based on the image data set of the material part set, wherein the area percentage information of the material part set comprises the area percentage of different types of material parts in the material part set;
the input module is used for inputting the area percentage information of the material part set into a weight percentage prediction model, and performing weight percentage prediction processing on the area percentage information of the material part set to obtain a weight percentage information prediction result of the material part set, wherein the weight percentage information prediction result of the material part set comprises weight percentage prediction results of different types of material parts in the material part set;
the weight percentage prediction model is obtained by performing iterative training on a preset mapping model based on training data of a material set with weight percentage information and area percentage information;
and the information determination module is used for determining at least one piece of associated information of the material part set related to the weight percentage information prediction result of the material part set by using the weight percentage information prediction result of the material part set.
11. An electronic device, characterized in that the electronic device comprises: a memory, a processor, and a program stored on the memory for implementing the method for acquiring weight percent of a part,
the memory is used for storing a program for realizing the acquisition method of the weight percentage of the material;
the processor is configured to execute a program for implementing the method for acquiring the weight percentage of the material part, so as to implement the steps of the method for acquiring the weight percentage of the material part according to any one of claims 1 to 9.
12. A storage medium having stored thereon a program for implementing an acquisition method of weight percentage of a piece, the program being executed by a processor to implement the steps of the acquisition method of weight percentage of a piece according to any one of claims 1 to 9.
13. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of obtaining the weight percentage of a material piece according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111515772.5A CN114332196B (en) | 2021-12-10 | 2021-12-10 | Method, equipment, device and storage medium for acquiring weight percentage of material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111515772.5A CN114332196B (en) | 2021-12-10 | 2021-12-10 | Method, equipment, device and storage medium for acquiring weight percentage of material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114332196A true CN114332196A (en) | 2022-04-12 |
| CN114332196B CN114332196B (en) | 2024-04-09 |
Family
ID=81050285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111515772.5A Active CN114332196B (en) | 2021-12-10 | 2021-12-10 | Method, equipment, device and storage medium for acquiring weight percentage of material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114332196B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428114A (en) * | 2019-08-12 | 2019-11-08 | 深圳前海微众银行股份有限公司 | Output of the fruit tree prediction technique, device, equipment and computer readable storage medium |
| CN111008560A (en) * | 2019-10-31 | 2020-04-14 | 重庆小雨点小额贷款有限公司 | Livestock weight determination method, device, terminal and computer storage medium |
| US20200151610A1 (en) * | 2018-11-09 | 2020-05-14 | Industrial Technology Research Institute | Ensemble learning predicting method and system |
| CN111784031A (en) * | 2020-06-15 | 2020-10-16 | 上海东普信息科技有限公司 | Logistics vehicle classification prediction method, device, equipment and storage medium |
| CN113344001A (en) * | 2021-07-02 | 2021-09-03 | 河南牧原智能科技有限公司 | Organism weight estimation method, device, equipment and storage medium |
-
2021
- 2021-12-10 CN CN202111515772.5A patent/CN114332196B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200151610A1 (en) * | 2018-11-09 | 2020-05-14 | Industrial Technology Research Institute | Ensemble learning predicting method and system |
| CN110428114A (en) * | 2019-08-12 | 2019-11-08 | 深圳前海微众银行股份有限公司 | Output of the fruit tree prediction technique, device, equipment and computer readable storage medium |
| CN111008560A (en) * | 2019-10-31 | 2020-04-14 | 重庆小雨点小额贷款有限公司 | Livestock weight determination method, device, terminal and computer storage medium |
| CN111784031A (en) * | 2020-06-15 | 2020-10-16 | 上海东普信息科技有限公司 | Logistics vehicle classification prediction method, device, equipment and storage medium |
| CN113344001A (en) * | 2021-07-02 | 2021-09-03 | 河南牧原智能科技有限公司 | Organism weight estimation method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 郭俊先;李俊伟;胡光辉;刘军;虞飞宇;: "新疆冰糖心红富士苹果RGB图像多指标分析", 新疆农业科学, no. 03, 15 March 2013 (2013-03-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114332196B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784424B (en) | Image classification model training method, image processing method and device | |
| CN113421263B (en) | Part defect detection method, device, medium and computer program product | |
| US11416717B2 (en) | Classification model building apparatus and classification model building method thereof | |
| CN112767366A (en) | Image recognition method, device and equipment based on deep learning and storage medium | |
| CN116152863B (en) | Personnel information identification method and device, electronic equipment and storage medium | |
| CN110825611A (en) | Abnormal program analysis method and device and computer readable storage medium | |
| CN112767354A (en) | Defect detection method, device and equipment based on image segmentation and storage medium | |
| CN112948951A (en) | Building model creating method and device and processing server | |
| Andhy Panca Saputra | Waste Object Detection and Classification using Deep Learning Algorithm: YOLOv4 and YOLOv4-tiny | |
| CN111400439A (en) | Network bad data monitoring method and device and storage medium | |
| CN110659179A (en) | Method and device for evaluating system running condition and electronic equipment | |
| CN111666816A (en) | Method, device and equipment for detecting state of logistics piece | |
| CN111476144B (en) | Pedestrian attribute identification model determining method and device and computer readable storage medium | |
| CN114332196B (en) | Method, equipment, device and storage medium for acquiring weight percentage of material | |
| CN111090242B (en) | Method, device and equipment for verifying precision of automatic driving test system and storage medium | |
| CN116245808A (en) | Workpiece defect detection method and device, electronic equipment and storage medium | |
| CN113344994B (en) | Image registration method, device, electronic equipment and storage medium | |
| CN114332109B (en) | Material weight acquisition method and device, electronic equipment and storage medium | |
| CN114998216A (en) | Method and device for rapidly detecting surface defects of transparent part | |
| CN114022658A (en) | Target detection method, device, storage medium and terminal | |
| CN108009393B (en) | Data processing method, device and computer readable storage medium | |
| CN109685069B (en) | Image detection method, device and computer readable storage medium | |
| CN113268670B (en) | Latent factor hybrid recommendation method, device, equipment and computer storage medium | |
| CN115761815B (en) | Training method of human body detection model, human body detection method, device and medium | |
| CN110738258B (en) | Image classification method and device and terminal equipment |
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 |