CN116229053A - Dynamic adjustment method for red date machine striker plate based on neural network - Google Patents
Dynamic adjustment method for red date machine striker plate based on neural network Download PDFInfo
- Publication number
- CN116229053A CN116229053A CN202211563098.2A CN202211563098A CN116229053A CN 116229053 A CN116229053 A CN 116229053A CN 202211563098 A CN202211563098 A CN 202211563098A CN 116229053 A CN116229053 A CN 116229053A
- Authority
- CN
- China
- Prior art keywords
- neural network
- training
- striker plate
- layer
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for dynamically adjusting a red jujube machine striker plate based on a neural network, which relates to the technical field of sorting equipment and comprises the following steps: collecting images shot in the running process of the red date machine, carrying out background segmentation algorithm processing on the collected color images, and removing a background area; classifying the acquired images, giving different label numbers to each type, constructing a training data sample, and performing neural network training; designing a multi-branch convolutional neural network structure for classification, training by using a data set, and acquiring a neural network model after training is completed; inputting the image acquired by the camera in real time into a neural network model, giving out a corresponding tag value, storing the tag value to the same position, and updating in real time; calculating a label value which is updated in real time and has a fixed length, counting the duty ratio of each class, and determining the adjustment direction of the striker plate; and controlling the motor according to the determined striker plate adjusting scheme to finish adjustment. The invention can improve the feeding and sorting efficiency of the red date machine.
Description
Technical Field
The invention belongs to the technical field of sorting equipment, and particularly relates to a method for dynamically adjusting a material baffle plate of a red date machine based on a neural network, so that the feeding and sorting efficiency of the red date machine is improved.
Background
With the rise of artificial intelligence, the machine letter sorting has replaced artifical letter sorting gradually, and the standard of artifical letter sorting is different and have stronger subjectivity, can't satisfy the demand in market. Since the market competition of the red date sorting apparatus is intense, in order to improve the market competitiveness of the apparatus, it is necessary to further improve the sorting efficiency and usability of the apparatus. The angle of the baffle plate of the existing equipment is preset, and cannot be dynamically adjusted in real time according to the condition of full distribution of the rollers and the accumulation condition of materials.
Disclosure of Invention
(1) The invention aims to solve the technical problems
In the running process of the red date sorting machine, the angle of the material baffle cannot be automatically adjusted to adapt to material sorting; and solves the problem of lower roller full rate or material accumulation and material return caused by the angle of the baffle plate.
(2) The invention adopts the technical proposal that
Aiming at the technical problems, the invention aims to provide a method for dynamically adjusting the angle of a baffle plate of a red date machine based on a neural network, so that the sorting efficiency and stability of the red date machine are improved, and the secondary sorting of materials is reduced.
The method specifically comprises the following steps:
step S1: the method comprises the steps of collecting RGB images shot in the running process of a red date machine by using a camera, carrying out background segmentation algorithm processing on the collected color images, and removing a background area;
step S2: classifying the acquired images, giving different label numbers to each type, constructing a training data sample, and performing neural network training;
step S3: designing a multi-branch convolutional neural network structure for classification, training by using the data set in the step S2, and acquiring a neural network model after training is completed;
step S4: the image acquired by the camera in real time is input into a neural network model through the step S1, corresponding label values are given, and the label values are stored in the same position and updated in real time;
step S5: calculating a label value which is updated in real time and has a fixed length, and counting the duty ratio of each type, so as to determine the adjustment direction of the striker plate and improve the effective filling rate of materials on the red date machine;
step S6: and according to the striker plate adjusting scheme determined in the step S5, the striker plate is sent to the servo motor through the control unit, so that the striker plate is adjusted.
Further, in the step S1, after the background of the collected original RGB image is removed, the image is equally divided, so that the size of each image is ensured to be the same and only one groove for storing materials is provided.
Further, the step S2 includes the steps of:
step S201: uniformly adjusting the image size to 224 x 224 pixels;
step S202: manually classifying the images and giving different labels, wherein 0 represents no date, 1 represents single date, and 2 represents multiple dates;
step S203: the image after being given the label is divided into a training set, a verification set and a test set, wherein the training set, the verification set and the test set are divided into random divisions, the training set accounts for 80%, and the verification set and the test set account for 10% respectively.
Further, the design convolutional neural network of the step S3 includes the following steps:
step S301: designing a convolutional neural network consisting of 8 convolutional layers, 4 batch normalization layers, 8 ReLU activation function layers, 1 global average pooling layer and 1 Softmax multi-classification layer, wherein the convolutional neural network comprises 8 convolutional unit blocks, and each unit block comprises a feature extraction layer and a feature superposition layer;
step S302: inputting the trained sample into an input layer of a double-branch convolutional neural network, adopting an AdamW optimization algorithm to replace a traditional SGD algorithm and an Adam algorithm to train the double-branch convolutional neural network, adopting cross entropy to train the network until the loss function of the multi-branch convolutional neural network reaches a minimum value;
step S303: and (3) completing model convergence to obtain a trained network weight coefficient, wherein the network weight coefficient can be used for subsequent prediction.
Further, in step S301, each of the 8 convolution unit blocks is first convolved with a convolution kernel of 3*3 and a convolution kernel of 1*1 to extract features, then is sent to a feature overlapping layer to perform information overlapping, a batch of normalization layers are added in even unit blocks to directly overlap and output with the feature overlapping layer, and are output to the next unit block through a ReLU activation function layer, and after passing through 8 convolution unit blocks, data is flattened through a global average pooling layer, and finally a corresponding result is output through a Softmax classification layer.
Further, the storing the prediction result in step S4 includes the following steps:
step S401: scaling the image to 224 x 224 pixels, inputting the image to a trained convolutional neural network model, and sequentially giving a label value corresponding to each image by the model;
step S402: sequentially storing the tag values in a storage unit, and storing every k images, wherein k is the number of the images equally divided in the step S1, and then continuously updating and increasing the length of the tag values;
step S403: when the length of the label value is consistent with the number of rollers corresponding to the machine chain, the result of the follow-up prediction is continuously stored, and meanwhile, the label data stored in the storage unit at the beginning is deleted.
Further, the step S5 of calculating the different label value duty ratios includes the steps of:
step S501: the data stored in the storage unit are A1, A2, A3, & An, wherein n is the number of machine rollers, A1, A2 and the like represent predicted tag values, the number of data with the tag value of 0 is accumulated and recorded as S0, the number of data with the tag value of 1 is accumulated and recorded as S1, and the number of data with the tag value of 2 is accumulated and recorded as S2;
step S502: the probability of each class is calculated and,
in the three probabilities, firstly comparing whether P2 exceeds a set threshold M2, wherein the threshold M2 is set in advance, if the threshold M2 is reached, sending down a signal for adjusting the angle of the large baffle plate, if the threshold M2 is not reached, comparing whether the value of P0 reaches the set threshold M0, if the threshold M0 is exceeded, sending down a signal for adjusting the angle of the small baffle plate, and if the threshold M0 is not exceeded, not adjusting;
step S503: in the dynamic updating of the stored tag value data, P0, P1 and P2 are continuously updated, and whether the striker plate needs to be adjusted is determined in real time according to the sequence of step S502.
The invention has the beneficial effects that:
(1) The distribution condition of the materials in the image can be automatically identified by the method of the invention, and manual adjustment is not needed after manual observation;
(2) The method can automatically adjust according to the image recognition result, and ensure the effective filling rate of the red dates on the machine.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
FIG. 2 is a flow chart of the working structure of an embodiment of the present invention;
fig. 3 is a block diagram of a convolutional neural network in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Examples
In the prior art, as the angle of the baffle plate in the red date sorting equipment cannot be automatically adjusted, feedback cannot be carried out according to the full distribution condition or the accumulation condition of materials on the roller, and the angle of the baffle plate can be automatically adjusted.
Based on the above, the embodiment provides a dynamic adjustment method for the baffle plate of the red date machine based on the neural network, so that the effective filling rate of the red date machine is improved, and the production efficiency of the red date machine is improved.
Referring to fig. 1-3, the method of the present embodiment includes the following steps:
step S1: the RGB images photographed during the operation of the red date machine are collected using a camera. Performing background segmentation algorithm processing on the acquired color image, and removing a background area;
in step S1, after the background of the collected original RGB image is removed, the image is equally divided, so that each image is ensured to have the same size and only one groove for storing materials.
Step S2: classifying the acquired images, giving different label numbers to each type, constructing a training data sample, and performing neural network training;
the step S2 specifically includes the following steps:
s201: uniformly adjusting the image size to 224 x 224 pixels;
s202: manually classifying the images and giving different labels, wherein 0 represents no date, 1 represents single date, and 2 represents multiple dates;
s203: the image given with the label is divided into a training set, a verification set and a test set. The method is divided into random division, the training set accounts for 80%, and the verification set and the test set respectively account for 10%.
Step S3: designing a multi-branch convolutional neural network structure for classification, training by using the data set in the step S2, and acquiring a neural network model after training is completed;
the step S3 of designing the convolutional neural network specifically comprises the following steps:
s301: designing a convolutional neural network consisting of 8 convolutional layers, 4 batch normalization layers, 8 ReLU activation function layers, 1 global average pooling layer and 1 Softmax multi-classification layer, wherein the convolutional neural network mainly comprises 8 convolutional unit blocks, and each unit block comprises a feature extraction layer and a feature superposition layer;
s302: inputting the trained sample into an input layer of a double-branch convolutional neural network, adopting an AdamW optimization algorithm to replace a traditional SGD algorithm and an Adam algorithm to train the double-branch convolutional neural network, adopting cross entropy to train the network until the loss function of the multi-branch convolutional neural network reaches a minimum value;
s303: and (3) completing model convergence, and obtaining a trained network weight coefficient which can be used for subsequent prediction.
In S301, each of the 8 convolution unit blocks adopts a convolution kernel of 3*3 and a convolution kernel of 1*1 to perform convolution extraction on features, then sends the features into a feature overlapping layer to perform information overlapping, adds a batch of normalization layers in even unit blocks to directly overlap and output the features with the feature overlapping layer, outputs the results to the next unit block through a ReLU activation function layer, and after passing through 8 convolution unit blocks, flattens data through a global average pooling layer, and finally outputs corresponding results through a Softmax classification layer.
In step S3 of this embodiment, training and recognition are performed by using a convolutional neural network, so that accuracy in recognizing material distribution conditions is improved, parameters such as area are not required to be utilized like a traditional algorithm, independent parameter settings are not required for red dates with different grades, and usability of the machine is improved.
Step S4: the method comprises the steps that an image acquired by a camera in real time is input into a neural network model through a step S1, a corresponding label value is given, the label value is stored in the same position, and the label value is updated in real time;
the storing of the prediction result in step S4 mainly includes the following steps:
s401: scaling the image to 224 x 224 pixels, inputting the image to a trained convolutional neural network model, and sequentially giving a label value corresponding to each image by the model;
s402: sequentially storing the tag values in a storage unit, and storing every k images (k is the number of the images equally divided in the step S1), and continuously updating and increasing the length of the tag values;
s403: when the length of the label value is consistent with the number of rollers corresponding to the machine chain, the result of the follow-up prediction is continuously stored, and meanwhile, the label data stored in the storage unit at the beginning is deleted.
Step S5: calculating a label value which is updated in real time and has a fixed length, and counting the duty ratio of each type, so as to determine the adjustment direction of the striker plate and improve the effective filling rate of materials on the red date machine;
the step S5 of calculating the different label value duty ratios mainly includes the following steps:
s501: the data stored in the storage unit are A1, A2, A3, & An, (n is the number of machine rollers, A1, A2 and the like represent predicted tag values), the number of data with the tag value of 0 is accumulated and recorded as S0, the number of data with the tag value of 1 is accumulated and recorded as S1, and the number of data with the tag value of 2 is accumulated and recorded as S2;
s502: the probability of each class is calculated and,
in the three probabilities, firstly comparing whether P2 exceeds a set threshold M2 (set in advance by people), if the P2 is reached, sending down a signal for adjusting the angle of the large baffle plate, if the P0 is not reached, comparing whether the P0 value reaches the set threshold M0, if the P0 value is exceeded, sending down a signal for adjusting the angle of the small baffle plate, and if the P0 value is not exceeded, not adjusting the signal;
s503: in the dynamic updating of the stored tag value data, P0, P1 and P2 are continuously updated, and whether the striker plate needs to be adjusted is judged in real time according to the sequence of S502.
In the embodiment, the step S5 can update and store the identification result in real time and calculate in real time, so that the effective full distribution rate of the roller materials in the production of the red date machine is ensured, the efficiency in the production process is improved, the probability of material return is reduced, and meanwhile, the damage to the materials caused by repeated check is avoided.
Step S6: and (5) according to the striker plate adjusting scheme determined in the step (S5), issuing the striker plate adjusting scheme to a servo motor through a control unit, and thus completing the adjustment of the striker plate.
The neural network-based red date machine striker plate dynamic adjustment method is characterized by providing an algorithm for automatically adjusting the angle of the red date machine striker plate in real time and an algorithm for automatically detecting the material distribution condition on the roller of the red date machine.
The foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A method for dynamically adjusting a red date machine striker plate based on a neural network is characterized by comprising the following steps:
step S1: the method comprises the steps of collecting RGB images shot in the running process of a red date machine by using a camera, carrying out background segmentation algorithm processing on the collected color images, and removing a background area;
step S2: classifying the acquired images, giving different label numbers to each type, constructing a training data sample, and performing neural network training;
step S3: designing a multi-branch convolutional neural network structure for classification, training by using the data set in the step S2, and acquiring a neural network model after training is completed;
step S4: the image acquired by the camera in real time is input into a neural network model through the step S1, corresponding label values are given, and the label values are stored in the same position and updated in real time;
step S5: calculating a label value which is updated in real time and has a fixed length, and counting the duty ratio of each type, so as to determine the adjustment direction of the striker plate and improve the effective filling rate of materials on the red date machine;
step S6: and according to the striker plate adjusting scheme determined in the step S5, the striker plate is sent to the servo motor through the control unit, so that the striker plate is adjusted.
2. The method according to claim 1, wherein in the step S1, after removing the background from the collected original RGB image, the images are equally divided, so that each image is identical in size and only one groove for storing the material is provided.
3. The method according to claim 1, wherein said step S2 comprises the steps of:
step S201: uniformly adjusting the image size to 224 x 224 pixels;
step S202: manually classifying the images and giving different labels, wherein 0 represents no date, 1 represents single date, and 2 represents multiple dates;
step S203: the image after being given the label is divided into a training set, a verification set and a test set, wherein the training set, the verification set and the test set are divided into random divisions, the training set accounts for 80%, and the verification set and the test set account for 10% respectively.
4. The method according to claim 1, wherein the designing the convolutional neural network of step S3 comprises the steps of:
step S301: designing a convolutional neural network consisting of 8 convolutional layers, 4 batch normalization layers, 8 ReLU activation function layers, 1 global average pooling layer and 1 Softmax multi-classification layer, wherein the convolutional neural network comprises 8 convolutional unit blocks, and each unit block comprises a feature extraction layer and a feature superposition layer;
step S302: inputting the trained sample into an input layer of a double-branch convolutional neural network, adopting an AdamW optimization algorithm to replace a traditional SGD algorithm and an Adam algorithm to train the double-branch convolutional neural network, adopting cross entropy to train the network until the loss function of the multi-branch convolutional neural network reaches a minimum value;
step S303: and (3) completing model convergence to obtain a trained network weight coefficient, wherein the network weight coefficient can be used for subsequent prediction.
5. The method of claim 4, wherein in step S301, each of the 8 convolution unit blocks is configured to perform convolution with a convolution kernel of 3*3 and a convolution kernel of 1*1 to extract features, then send the features to a feature-stack layer to perform information stacking, add a batch normalization layer to an even unit block to directly perform stacking output with the feature-stack layer, output the result to a next unit block through a ReLU activation function layer, and after passing through 8 convolution unit blocks, flattening the data through a global average pooling layer, and finally output a corresponding result through a Softmax classification layer.
6. The method according to claim 1, wherein the storing of the pair of prediction results of step S4 comprises the steps of:
step S401: scaling the image to 224 x 224 pixels, inputting the image to a trained convolutional neural network model, and sequentially giving a label value corresponding to each image by the model;
step S402: sequentially storing the tag values in a storage unit, and storing every k images, wherein k is the number of the images equally divided in the step S1, and then continuously updating and increasing the length of the tag values;
step S403: when the length of the label value is consistent with the number of rollers corresponding to the machine chain, the result of the follow-up prediction is continuously stored, and meanwhile, the label data stored in the storage unit at the beginning is deleted.
7. The method according to claim 1, wherein said step S5 of calculating different label value duty cycles comprises the steps of:
step S501: the data stored in the storage unit are A1, A2, A3, & An, wherein n is the number of machine rollers, A1, A2 and the like represent predicted tag values, the number of data with the tag value of 0 is accumulated and recorded as S0, the number of data with the tag value of 1 is accumulated and recorded as S1, and the number of data with the tag value of 2 is accumulated and recorded as S2;
step S502: the probability of each class is calculated and,
in the three probabilities, firstly comparing whether P2 exceeds a set threshold M2, wherein the threshold M2 is set in advance, if the threshold M2 is reached, sending down a signal for adjusting the angle of the large baffle plate, if the threshold M2 is not reached, comparing whether the value of P0 reaches the set threshold M0, if the threshold M0 is exceeded, sending down a signal for adjusting the angle of the small baffle plate, and if the threshold M0 is not exceeded, not adjusting;
step S503: in the dynamic updating of the stored tag value data, P0, P1 and P2 are continuously updated, and whether the striker plate needs to be adjusted is determined in real time according to the sequence of step S502.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211563098.2A CN116229053A (en) | 2022-12-07 | 2022-12-07 | Dynamic adjustment method for red date machine striker plate based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211563098.2A CN116229053A (en) | 2022-12-07 | 2022-12-07 | Dynamic adjustment method for red date machine striker plate based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116229053A true CN116229053A (en) | 2023-06-06 |
Family
ID=86571917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211563098.2A Pending CN116229053A (en) | 2022-12-07 | 2022-12-07 | Dynamic adjustment method for red date machine striker plate based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116229053A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842667A (en) * | 2023-06-25 | 2023-10-03 | 成都飞机工业（集团）有限责任公司 | Method for determining manufacturing feasibility of bent pipe |
| CN116989510A (en) * | 2023-09-28 | 2023-11-03 | 广州冰泉制冷设备有限责任公司 | Intelligent refrigeration method combining frosting detection and hot gas defrosting |
-
2022
- 2022-12-07 CN CN202211563098.2A patent/CN116229053A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842667A (en) * | 2023-06-25 | 2023-10-03 | 成都飞机工业（集团）有限责任公司 | Method for determining manufacturing feasibility of bent pipe |
| CN116989510A (en) * | 2023-09-28 | 2023-11-03 | 广州冰泉制冷设备有限责任公司 | Intelligent refrigeration method combining frosting detection and hot gas defrosting |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116229053A (en) | Dynamic adjustment method for red date machine striker plate based on neural network | |
| CN108960245B (en) | Tire mold character detection and recognition method, device, equipment and storage medium | |
| CN109389161B (en) | Garbage identification evolutionary learning method, device, system and medium based on deep learning | |
| CN110728225B (en) | High-speed face searching method for attendance checking | |
| CN110443778B (en) | Method for detecting irregular defects of industrial products | |
| CN112241679A (en) | Automatic garbage classification method | |
| CN109740721B (en) | Wheat ear counting method and device | |
| CN113324864B (en) | Pantograph carbon slide plate abrasion detection method based on deep learning target detection | |
| CN110245663A (en) | One kind knowing method for distinguishing for coil of strip information | |
| CN111881958A (en) | License plate classification recognition method, device, equipment and storage medium | |
| CN113221956B (en) | Target identification method and device based on improved multi-scale depth model | |
| CN114219993A (en) | CNN-based construction waste classification method | |
| CN112258490A (en) | Low-emissivity coating intelligent damage detection method based on optical and infrared image fusion | |
| CN111833322A (en) | Garbage multi-target detection method based on improved YOLOv3 | |
| CN114972952B (en) | Model lightweight-based industrial part defect identification method | |
| CN114663427B (en) | Boiler part size detection method based on image processing | |
| CN114612450B (en) | Image detection segmentation method and system based on data augmentation machine vision and electronic equipment | |
| CN109919994A (en) | A kind of coal mining machine roller automatic height-adjusting system based on deep learning image procossing | |
| CN117253192A (en) | Intelligent system and method for silkworm breeding | |
| CN112419278A (en) | Deep learning-based solid wood floor classification method | |
| CN113591773B (en) | Distribution room object detection method, device and equipment based on convolutional neural network | |
| CN114926420A (en) | Identification and counting method of target naan based on cross-level feature enhancement | |
| CN113269043B (en) | Real-time tracking and identifying method and device for coil loosening of steel coil | |
| CN109948421B (en) | Hyperspectral image classification method based on PCA and attribute configuration file | |
| CN106408433A (en) | Grain yield prediction method and grain yield prediction device based on differential processing |
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 |