CN113291703A - Discharge opening blockage detection method and device - Google Patents
Discharge opening blockage detection method and device Download PDFInfo
- Publication number
- CN113291703A CN113291703A CN202010896816.2A CN202010896816A CN113291703A CN 113291703 A CN113291703 A CN 113291703A CN 202010896816 A CN202010896816 A CN 202010896816A CN 113291703 A CN113291703 A CN 113291703A
- Authority
- CN
- China
- Prior art keywords
- image
- neural network
- convolutional neural
- camera
- discharge opening
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000013145 classification model Methods 0.000 claims abstract description 29
- 239000000463 material Substances 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 44
- 238000012360 testing method Methods 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 29
- 238000012795 verification Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000007599 discharging Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G15/00—Conveyors having endless load-conveying surfaces, i.e. belts and like continuous members, to which tractive effort is transmitted by means other than endless driving elements of similar configuration
- B65G15/30—Belts or like endless load-carriers
- B65G15/32—Belts or like endless load-carriers made of rubber or plastics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/34—Devices for discharging articles or materials from conveyor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/04—Detection means
- B65G2203/041—Camera
Abstract
The application provides a method and a device for detecting blockage of a discharge opening, wherein the method comprises the following steps: acquiring images shot by a camera at preset intervals, wherein the camera is arranged above the discharge opening; inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials; and when the detection label is blocked, sending an alarm signal. In the embodiment of the application, gather the image in real time through the camera, utilize preset classification model, can judge whether the discharge opening takes place the putty, if the putty, then in time remind the site personnel to handle, avoid the material to pile up and cause the discharge opening to block up completely.
Description
Technical Field
The application relates to a discharging technology, in particular to a method and a device for detecting blockage at a discharging opening.
Background
The belt conveyor is a friction-driven machine for continuously conveying materials, and the materials are conveyed on a certain conveying line by the belt conveyor, and the conveying process of the materials is completed from an initial feeding point to a final discharging point.
At present, belt conveyors are widely used in port, power plant and metallurgy industries, and the length of the belt conveyors is dozens of meters to thousands of meters. As shown in figure 1, belt conveyor 1 is unloading the in-process, and bold material and metallic foreign matter lead to discharge opening 2 to appear the putty easily when the blanking, lead to the material to pile up at the blanking mouth fast easily when the blanking condition appears in discharge opening 2, block up the discharge opening completely, lead to the mill to shut down, cause serious economic loss. At present, the factory can not effectively detect the blockage of the discharge opening in time.
Disclosure of Invention
The application provides an anti-collision method and device of a reclaimer, which are used for avoiding the problem that the blockage of a blockage port cannot be found in time.
According to a first aspect of embodiments of the present application, there is provided a discharge opening blockage detection method, the method including:
acquiring images shot by a camera at preset intervals, wherein the camera is arranged above the discharge opening;
inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials;
and when the detection label is blocked, sending an alarm signal.
In some embodiments, the step of determining the preset classification model comprises:
acquiring an image sample, wherein the image sample comprises a plurality of images shot by a camera;
preprocessing the image in the image sample to obtain a preprocessed image;
determining a label corresponding to the preprocessed image;
splitting the preprocessed image and the corresponding detection label into a training set, a verification set and a test set;
training the convolutional neural network by using the training set to obtain a trained convolutional neural network;
adjusting the parameters of the trained convolutional neural network by using the verification set to obtain a final convolutional neural network;
testing the final convolutional neural network by using the test set to obtain a test result;
and if the test result is qualified, determining the final convolutional neural network as a preset classification model.
In some embodiments, the step of preprocessing the image in the image sample to obtain a preprocessed image includes:
resizing an image in the image sample;
and performing linear filtering processing on the image after the size adjustment to obtain a preprocessed image.
In some embodiments, the convolutional neural network comprises a residual neural network.
In a second aspect, a discharge opening blockage detection device is provided, the device comprising:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring images shot by a camera at intervals of preset time, and the camera is arranged above a discharge opening;
the determining unit is used for inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials;
and the alarm unit is used for sending an alarm signal when the detection label is blocked.
In some embodiments, the step of determining the preset classification model comprises:
acquiring an image sample, wherein the image sample comprises a plurality of images shot by a camera;
preprocessing the image in the image sample to obtain a preprocessed image;
determining a label corresponding to the preprocessed image;
splitting the preprocessed image and the corresponding detection label into a training set, a verification set and a test set;
training the convolutional neural network by using the training set to obtain a trained convolutional neural network;
adjusting the parameters of the trained convolutional neural network by using the verification set to obtain a final convolutional neural network;
testing the final convolutional neural network by using the test set to obtain a test result;
and if the test result is qualified, determining the final convolutional neural network as a preset classification model.
In some embodiments, the step of preprocessing the image in the image sample to obtain a preprocessed image includes:
resizing an image in the image sample;
and performing linear filtering processing on the image after the size adjustment to obtain a preprocessed image.
In some embodiments, the convolutional neural network comprises a residual neural network.
According to the above technology, the embodiment of the application provides a method and a device for detecting material blockage at a discharge opening, wherein the method comprises the following steps: acquiring images shot by a camera at preset intervals, wherein the camera is arranged above the discharge opening; inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials; and when the detection label is blocked, sending an alarm signal. In the embodiment of the application, gather the image in real time through the camera, utilize preset classification model, can judge whether the discharge opening takes place the putty, if the putty, then in time remind the site personnel to handle, avoid the material to pile up and cause the discharge opening to block up completely.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise. Furthermore, these descriptions should not be construed as limiting the embodiments, wherein elements having the same reference number designation are identified as similar elements throughout the figures, and the drawings are not to scale unless otherwise specified.
FIG. 1 is a diagram illustrating an application scenario according to an exemplary embodiment of the present application;
FIG. 2 is a flow chart illustrating a discharge port blockage detection method according to an exemplary embodiment of the present application;
FIG. 3 is a flow chart illustrating yet another discharge port blockage detection method according to an exemplary embodiment of the present application;
FIG. 4 is an image of a discharge opening in a normal condition shown in accordance with an exemplary embodiment of the present application;
FIG. 5 is an image of a discharge opening in a plugged condition shown in accordance with an exemplary embodiment of the present application;
FIG. 6 is a schematic diagram of a structure of a residual neural network, shown schematically in accordance with an embodiment of the present application;
fig. 7 is a schematic structural diagram of a discharge port blockage detection device according to an exemplary embodiment of the present application.
Detailed Description
As shown in figure 1, belt conveyor 1 is unloading the in-process, and bold material and metallic foreign matter lead to discharge opening 2 to appear the putty easily when the blanking, lead to the material to pile up at the blanking mouth fast easily when the blanking condition appears in discharge opening 2, block up the discharge opening completely, lead to the mill to shut down, cause serious economic loss. At present, the factory can not effectively detect the blockage of the discharge opening in time.
The embodiment of the application provides a discharge opening putty detection method, as shown in fig. 2, the method includes:
s101, acquiring images shot by a camera at preset intervals, wherein the camera is arranged above the discharge opening.
It should be noted that the installation requirement of the camera is to ensure that the shooting range of the camera includes the discharge opening, and for example, as shown in fig. 1, the camera 3 is disposed above the discharge opening 2 to facilitate the camera to shoot the image including the discharge opening. In addition, the preset time in the embodiment of the present application may be 1 s. And taking a picture through a camera in every 1s interval as a basis for detecting whether the discharge port is blocked.
S102, inputting the image into a preset classification model to obtain a label corresponding to the image, wherein the label comprises normal or blocked materials. The preset classification model is a classification model which is packaged in advance and used for identifying whether the discharge opening is blocked or not.
In some embodiments, the step of determining the preset classification model, as shown in fig. 3, includes:
s1021, obtaining an image sample, wherein the image sample comprises a plurality of images shot by a camera. Specifically, a large number of images are taken by a camera as an image sample when a preset classification model is determined. In capturing the image in the image sample, the installation requirements of the camera are the same as those of the camera in step S101.
S1022, in order to better extract the characteristics of the image under the normal condition of the discharge port and the condition of material blockage of the discharge port, the image in the image sample is preprocessed to obtain the preprocessed image. Illustratively, fig. 4 is an image of a discharge opening in a normal condition, and fig. 5 is an image of a discharge opening in a plugged condition.
In some embodiments, the step of preprocessing the image in the image sample to obtain a preprocessed image includes: resizing an image in the image sample. Illustratively, the size of the images in the image sample is uniformly cropped to a size of 1024 × 1024 pixels for subsequent use in training the convolutional neural network.
Because the discharge opening site environment is comparatively abominable, noise interference appears in the image that the camera was gathered easily, in order to eliminate or attenuate the influence of noise to the image, the image after this application embodiment carries out linear filtering with size adjustment handles, obtains the image after the preliminary treatment. The linear filtering process is performed according to the following formula:
wherein f (i + k, j + l) is an input pixel value of the linear filtering processing, g (i, j) is an output pixel value of the linear filtering processing, h (k, l) is a weighting coefficient of the filter, and the value range of k and l is between 0 and 1024. After linear filtering processing, the material blocking condition of the discharge opening in the image is more obvious in characteristic compared with the normal condition.
And S1023, determining a label corresponding to the preprocessed image, wherein the label comprises normal or blocked materials. Specifically, the process of determining the label corresponding to the preprocessed image may be determined manually.
S1024, splitting the preprocessed image and the corresponding detection label into a training set, a verification set and a test set. Specifically, the preprocessed image and the detection label in the image sample may be split into a training set, a verification set, and a test set according to a quantitative ratio. For small-scale image samples, a common ratio is the number of images in the training set: number of images in verification set: the number of images in the test set is 6:2:2, and illustratively, when the image sample has 10000 images, the training set is 6000 images and corresponding detection labels, the verification set is 2000 images and corresponding detection labels, and the test set is 2000 images and corresponding detection labels.
For a large-scale image sample, the ratio of the number of images in the training set, the number of images in the verification set, and the number of images in the test set may be increased by a large amount. For example, 1000000 images in total, the training set is 9980000 images and corresponding detection labels, the verification set is 10000 images and corresponding detection labels, and the test set is 10000 images and corresponding detection labels.
And S1025, training the convolutional neural network by using the training set to obtain the trained convolutional neural network. In some embodiments, the convolutional neural network comprises a residual neural network.
As shown in fig. 6, the residual neural network in the embodiment of the present application includes a residual layer and a fully connected layer, the residual layer is formed by a plurality of residual blocks, and the residual blocks include convolutional layers and pooling layers. The output of each layer of residual block is the sum of the output of the upper layer of residual block and the output of the residual block of the current layer, and the output result of the residual layer is obtained through layer-by-layer superposition. In each residual block, the input data passes through a convolutional layer and a pooling layer, respectively, and the output superposition is regarded as the final output result. In some embodiments, the size of the convolutional layer is 32 dimensions, and after the input data is sequentially subjected to the normalization operation and the regularization operation, the convolutional layer is convolved by 3 × 3 with the step size of 1 to obtain an output result. The full-connection layer is the last layer of the residual error neural network, the output of the residual error layer is the input of the full-connection layer, and the output result is obtained by inputting the input into the average regularization layer after standardized calculation. Each stage in the full link layer is connected with all nodes of the residual layer, and the features extracted by the residual layer are integrated.
S1027, adjusting parameters of the trained convolutional neural network by using the verification set to obtain a final convolutional neural network.
Before training, the residual error neural network needs to initialize all parameters, firstly, initializing all weight values (weight), bias values (bias) and Batch normalization scale factor values (Batch normalization), and inputting the values into the residual error neural network; inputting the training set into a residual error neural network to obtain a multi-dimensional output characteristic value matrix of the image; inputting the verification set into a residual error neural network of a training image, loading image features into a classifier for classification according to the extracted output characteristic value matrix, wherein the classifier can be a softmax classifier for an exemplary purpose, comparing a classification result with a detection label, returning an error rate error and a loss to the residual error neural network, and updating a weight value and an offset value in a random gradient descending manner. And repeating the training until the loss is reduced to 0.01, and stopping the training to obtain the final residual error neural network.
S1028, testing the final convolutional neural network by using the test set to obtain a test result. Illustratively, the test set is input into a final convolutional neural network, and a label corresponding to the image is obtained. The label is compared with the detection label in the test set, if the label is the same as the detection label in the test set, the result is determined to be correct, in the embodiment of the application, the label corresponding to the image in the test set is compared with the detection label, the result accuracy is determined, if the result accuracy is higher than the preset accuracy, the test result is determined to be qualified, and otherwise, the test result is determined to be unqualified.
S1029, if the test result is qualified, determining the final convolutional neural network as a preset classification model. And if the test result is not qualified, the preset classification model needs to be determined again.
In the embodiment of the application, the preset classification model is adopted to determine the corresponding label for the image shot in real time. S103, when the label is blocked, an alarm signal is sent. Like this, can in time discover the putty condition of discharge opening.
The embodiment of this application still provides a discharge opening putty detection device, as shown in fig. 7, the device includes:
the device comprises an acquisition unit 101, a control unit and a control unit, wherein the acquisition unit is used for acquiring images shot by a camera at intervals of preset time, and the camera is arranged above a discharge opening;
a determining unit 102, configured to input the image into a preset classification model to obtain a detection label corresponding to the image, where the detection label includes a normal or blocked material;
and the alarm unit 103 is used for sending an alarm signal when the detection label is blocked.
In some embodiments, the step of determining the preset classification model comprises:
acquiring an image sample, wherein the image sample comprises a plurality of images shot by a camera;
preprocessing the image in the image sample to obtain a preprocessed image;
determining a label corresponding to the preprocessed image;
splitting the preprocessed image and the corresponding detection label into a training set, a verification set and a test set;
training the convolutional neural network by using the training set to obtain a trained convolutional neural network;
adjusting the parameters of the trained convolutional neural network by using the verification set to obtain a final convolutional neural network;
testing the final convolutional neural network by using the test set to obtain a test result;
and if the test result is qualified, determining the final convolutional neural network as a preset classification model.
In some embodiments, the step of preprocessing the image in the image sample to obtain a preprocessed image includes:
resizing an image in the image sample;
and performing linear filtering processing on the image after the size adjustment to obtain a preprocessed image.
In some embodiments, the convolutional neural network comprises a residual neural network.
According to the above technology, the embodiment of the application provides a method and a device for detecting material blockage at a discharge opening, wherein the method comprises the following steps: acquiring images shot by a camera at preset intervals, wherein the camera is arranged above the discharge opening; inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials; and when the detection label is blocked, sending an alarm signal. In the embodiment of the application, gather the image in real time through the camera, utilize preset classification model, can judge whether the discharge opening takes place the putty, if the putty, then in time remind the site personnel to handle, avoid the material to pile up and cause the discharge opening to block up completely.
The specific manner in which each unit \ module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (8)
1. A discharge port blockage detection method, comprising:
acquiring images shot by a camera at preset intervals, wherein the camera is arranged above the discharge opening;
inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials;
and when the detection label is blocked, sending an alarm signal.
2. The method of claim 1, wherein the step of determining the preset classification model comprises:
acquiring an image sample, wherein the image sample comprises a plurality of images shot by a camera;
preprocessing the image in the image sample to obtain a preprocessed image;
determining a label corresponding to the preprocessed image;
splitting the preprocessed image and the corresponding detection label into a training set, a verification set and a test set;
training the convolutional neural network by using the training set to obtain a trained convolutional neural network;
adjusting the parameters of the trained convolutional neural network by using the verification set to obtain a final convolutional neural network;
testing the final convolutional neural network by using the test set to obtain a test result;
and if the test result is qualified, determining the final convolutional neural network as a preset classification model.
3. The method of claim 2, wherein the step of pre-processing the image in the image sample to obtain a pre-processed image comprises:
resizing an image in the image sample;
and performing linear filtering processing on the image after the size adjustment to obtain a preprocessed image.
4. The method of claim 2, wherein the convolutional neural network comprises a residual neural network.
5. A discharge opening putty detecting device, characterized in that the device includes:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring images shot by a camera at intervals of preset time, and the camera is arranged above a discharge opening;
the determining unit is used for inputting the image into a preset classification model to obtain a detection label corresponding to the image, wherein the detection label comprises normal or blocked materials;
and the alarm unit is used for sending an alarm signal when the detection label is blocked.
6. The apparatus of claim 5, wherein the step of determining the preset classification model comprises:
acquiring an image sample, wherein the image sample comprises a plurality of images shot by a camera;
preprocessing the image in the image sample to obtain a preprocessed image;
determining a label corresponding to the preprocessed image;
splitting the preprocessed image and the corresponding detection label into a training set, a verification set and a test set;
training the convolutional neural network by using the training set to obtain a trained convolutional neural network;
adjusting the parameters of the trained convolutional neural network by using the verification set to obtain a final convolutional neural network;
testing the final convolutional neural network by using the test set to obtain a test result;
and if the test result is qualified, determining the final convolutional neural network as a preset classification model.
7. The apparatus of claim 6, wherein the step of pre-processing the image in the image sample to obtain a pre-processed image comprises:
resizing an image in the image sample;
and performing linear filtering processing on the image after the size adjustment to obtain a preprocessed image.
8. The apparatus of claim 6, wherein the convolutional neural network comprises a residual neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010896816.2A CN113291703A (en) | 2020-08-31 | 2020-08-31 | Discharge opening blockage detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010896816.2A CN113291703A (en) | 2020-08-31 | 2020-08-31 | Discharge opening blockage detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113291703A true CN113291703A (en) | 2021-08-24 |
Family
ID=77318605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010896816.2A Pending CN113291703A (en) | 2020-08-31 | 2020-08-31 | Discharge opening blockage detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113291703A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554004A (en) * | 2021-09-18 | 2021-10-26 | 三一汽车制造有限公司 | Detection method and detection system for material overflow of mixer truck, electronic equipment and mixing station |
| CN114049300A (en) * | 2021-10-11 | 2022-02-15 | 中冶南方工程技术有限公司 | Method for detecting material yard belt blocking based on target detection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105373799A (en) * | 2015-12-18 | 2016-03-02 | 北京环境特性研究所 | Space target ISAR image processing method for template identification |
| CN108648495A (en) * | 2018-06-08 | 2018-10-12 | 华南理工大学 | A kind of method and system of the intelligence real-time display bus degree of crowding |
| CN109522819A (en) * | 2018-10-29 | 2019-03-26 | 西安交通大学 | A kind of fire image recognition methods based on deep learning |
| US20190163955A1 (en) * | 2017-11-24 | 2019-05-30 | International Business Machines Corporation | Image classification using limited labeled data |
-
2020
- 2020-08-31 CN CN202010896816.2A patent/CN113291703A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105373799A (en) * | 2015-12-18 | 2016-03-02 | 北京环境特性研究所 | Space target ISAR image processing method for template identification |
| US20190163955A1 (en) * | 2017-11-24 | 2019-05-30 | International Business Machines Corporation | Image classification using limited labeled data |
| CN108648495A (en) * | 2018-06-08 | 2018-10-12 | 华南理工大学 | A kind of method and system of the intelligence real-time display bus degree of crowding |
| CN109522819A (en) * | 2018-10-29 | 2019-03-26 | 西安交通大学 | A kind of fire image recognition methods based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 石明国: "《现代医学影像技术学》", 30 April 2007, pages: 478 - 479 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554004A (en) * | 2021-09-18 | 2021-10-26 | 三一汽车制造有限公司 | Detection method and detection system for material overflow of mixer truck, electronic equipment and mixing station |
| CN114049300A (en) * | 2021-10-11 | 2022-02-15 | 中冶南方工程技术有限公司 | Method for detecting material yard belt blocking based on target detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104169945B (en) | To the two-stage classification of the object in image | |
| CN107328787A (en) | A kind of metal plate and belt surface defects detection system based on depth convolutional neural networks | |
| CN113291703A (en) | Discharge opening blockage detection method and device | |
| Rabby et al. | A modified canny edge detection algorithm for fruit detection & classification | |
| CN112862770B (en) | Defect analysis and diagnosis system, method and device based on artificial intelligence | |
| Ali et al. | Automated fruit grading system | |
| Thakur et al. | An innovative approach for fruit ripeness classification | |
| CN115065708B (en) | Industrial Internet of things system based on machine vision detection and control method thereof | |
| TW202242390A (en) | Defect inspection device, defect inspection method, and manufacturing method | |
| CN113297885A (en) | Belt conveyor surface state detection method and device based on convolutional neural network | |
| WO2021232149A1 (en) | Method and system for training inspection equipment for automatic defect classification | |
| US20200090319A1 (en) | Machine learning method implemented in aoi device | |
| CN112305379A (en) | Mode identification method and system for GIS insulation defect | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| CN108108678B (en) | Tungsten ore identification and separation method | |
| CN110570398A (en) | Cable joint welding spot qualification detection method based on deep learning technology | |
| CN110935646A (en) | Full-automatic crab grading system based on image recognition | |
| CN117314901A (en) | Scale-adaptive chip detection neural network system | |
| Agustin et al. | Automatic milled rice quality analysis | |
| CN111160330B (en) | Training method for improving image recognition accuracy with assistance of electronic tag recognition | |
| JP2019113914A (en) | Data identification device and data identification method | |
| CN112240888A (en) | Visual detection method and visual detection system | |
| KR20210085795A (en) | Agricultural Products Classification Apparatus Using Artificial Intelligence | |
| US20230316718A1 (en) | Learning model generating method and inspection device | |
| CN111047550A (en) | Product abnormity detection method, device and equipment based on machine vision |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |