CN114612859A - Intelligent detection method for ore stacking tarpaulin of non-specialized wharf - Google Patents
Intelligent detection method for ore stacking tarpaulin of non-specialized wharf Download PDFInfo
- Publication number
- CN114612859A CN114612859A CN202210177930.9A CN202210177930A CN114612859A CN 114612859 A CN114612859 A CN 114612859A CN 202210177930 A CN202210177930 A CN 202210177930A CN 114612859 A CN114612859 A CN 114612859A
- Authority
- CN
- China
- Prior art keywords
- grid
- stacking
- covered
- neural network
- convolutional neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent detection method for an ore stacking tarpaulin of a non-specialized wharf, which comprises the following steps: gridding and dividing a region to be monitored, and collecting monitoring data and images; constructing a training set based on the monitoring data and the images, and constructing and training a convolutional neural network and a classifier; identifying the monitored image based on the trained convolutional neural network, obtaining the non-covered area ratio, comparing the non-covered area ratio with a preset value, if the non-covered area ratio is smaller than the preset value, covering normally, and if the non-covered area ratio is larger than the preset value, performing the next step; and judging whether the non-covering range is in an operation state or not based on the trained classifier, if not, alarming, if so, detecting the correlation between the operation and the non-covering stacking, if so, finishing the detection, and if not, alarming.
Description
Technical Field
The invention relates to the technical field of ore stacking cover detection, in particular to an intelligent detection method for ore stacking covers of non-specialized wharfs.
Background
At present, the problem of particulate contamination is not optimistic. Particulate pollution is the leading factor in air pollution in most port cities. Harbours are at a peak in the increase of coal and ore throughput, and the problems of dust emission and diffusion pollution caused by the harbour are very severe.
However, due to the huge amount of coal (ore) transported in ports, open-air stockpiling is still adopted in most wharfs, especially non-specialized wharfs, except that closed or semi-closed storage is rarely adopted. According to the requirements of relevant environmental protection management, most local environmental protection departments require port operation enterprises to carry out dust control on coal (ore) stacks in a non-operation state by adopting a covering mode. For a non-specialized wharf bulk cargo yard, the storage place of the stack in the yard is not fixed, the shape and the form of the stack are not fixed, the loading and unloading operation point and time are not fixed, and the automatic judgment of whether the stack is covered or not is difficult to realize by the conventional image monitoring mode. At present, inspection is mainly carried out in a manual mode, and even if image monitoring is assisted, a monitoring area needs to be manually switched and manually judged. Because the area of the storage yard is huge, and reaches hundreds of thousands of square meters or even hundreds of thousands of square meters, the manual inspection increases the operation cost and the labor cost of the port operator, and the timely inspection cannot be ensured.
Therefore, the problem to be solved urgently by the technical personnel in the field is to provide an intelligent detection method for the ore stacking tarpaulin of the non-specialized wharf.
Disclosure of Invention
In view of the above, the invention provides an intelligent detection method for ore stacking tarpaulin of a non-specialized wharf, which converts the identification of an unfixed monitoring image which is difficult to realize (the stacking size, the stacking place and the stacking size are not fixed) into the identification of the exposed color of coal (ore) in the whole grid in a fixed grid which is easy to realize by carrying out gridding division on a yard area, thereby improving the identification accuracy; the characteristic that a grab bucket is in a downward dumping state in the process of carrying out loading and unloading operation on non-specialized wharf coal (ore) loading and unloading machinery is adopted, a loading and unloading operation image recognition training set is established, intelligent recognition of the loading and unloading machinery operation state is achieved, and recognition accuracy is high.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent detection method for ore stacking straw mat cover of non-specialized wharf comprises the following steps:
s1, gridding and dividing the area to be monitored, and collecting monitoring data and images;
s2, constructing a training set based on the monitoring data and the images, and constructing and training a convolutional neural network and a classifier;
s3, identifying the monitored image based on the trained convolutional neural network, obtaining the non-covered area ratio, comparing the non-covered area ratio with a preset value, if the non-covered area ratio is smaller than the preset value, covering normally, and if the non-covered area ratio is larger than the preset value, performing the next step;
and S4, judging whether the non-covering range is in an operation state or not based on the trained classifier, if so, finishing the detection, and if not, giving an alarm.
Preferably, the step S1 specifically includes:
s11, gridding and dividing the area to be monitored, numbering the grids, and acquiring the monitoring angle, the monitoring distance and the focal length of each grid, and the length and the width of each grid based on the monitoring points;
s12, setting the grid and the adjacent grid thereof as the associated grid;
s13, presetting the monitoring time step length and sequence of each grid, and acquiring an image of each grid, wherein the image comprises a stack and/or a working machine;
and S14, establishing a proportional relation between the picture size and the actual size.
Preferably, the step S2 specifically includes:
s21, constructing an image color recognition training set based on covered, uncovered and non-stacked images acquired by different grids under different illumination conditions;
s22, constructing a convolutional neural network, and training the convolutional neural network by taking the color of the material without covering as a characteristic target training set to enable the convolutional neural network to recognize different colors;
s23, collecting images of the stacking loading and unloading operation machine, selecting images of the operation machine in different states under different light conditions, constructing an operation state training set, and training an operation state classifier of the operation machine based on an AlexNet algorithm.
Preferably, the step S3 specifically includes:
s31, identifying the grid image based on the trained convolutional neural network, and obtaining the area ratio of the color of the non-covering material in the grid area in the grid;
s32, setting a proportion alarm threshold, judging whether the proportion of the color area of the non-covered material in the current grid area is larger than the proportion alarm threshold, if not, judging that the stacking is covered, and if so, judging whether the stacking is an operation area.
Preferably, the step S4 specifically includes:
s41, calling the grid which sends out the processing requirement for judging whether the operation state is required, calling the grid and the related grid thereof, identifying the downward dumping state of the grab bucket of the operation machine, if the state does not appear, judging that the operation is not carried out, alarming, and if the state does appear, carrying out the next step;
s42, carrying out data processing on the grid and the related grid thereof, and calculating the actual distance between the edge point of the non-covering material in the collected stacking grid image and the center point of the operation machine;
and S43, if the actual distance is smaller than the preset value, the current stack is considered to be in operation, early warning is cancelled, if the actual distance is larger than the preset value, the operation is considered to be unrelated to the stack, the stack is not covered under the non-operation state, and an alarm is given out.
According to the technical scheme, compared with the prior art, the invention discloses an intelligent detection method for ore stacking tarpaulin of a non-specialized wharf, through gridding division of a yard area, unfixed monitoring image identification of stacking (the stacking size, the stacking place and the stacking size are not fixed) which is difficult to realize is converted into the identification of the exposed color of coal (ore) in the whole grid of the monitoring image in a fixed grid which is easy to realize, so that the identification accuracy is improved; the characteristic that a grab bucket is in a downward dumping state in the process of carrying out loading and unloading operation on non-specialized wharf coal (ore) loading and unloading machinery is adopted, a loading and unloading operation image recognition training set is established, intelligent recognition of the loading and unloading machinery operation state is achieved, and recognition accuracy is high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of a process flow structure of the method provided by the present invention.
Fig. 2 is a schematic view of the monitoring provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses an intelligent detection method for ore stacking covers of non-specialized wharfs, which comprises the following steps:
s1, gridding and dividing the area to be monitored, and collecting monitoring data and images;
s2, constructing a training set based on the monitoring data and the images, and constructing and training a convolutional neural network and a classifier;
s3, identifying the monitored image based on the trained convolutional neural network, obtaining the non-covered area ratio, comparing the non-covered area ratio with a preset value, if the non-covered area ratio is smaller than the preset value, covering normally, and if the non-covered area ratio is larger than the preset value, performing the next step;
and S4, judging whether the non-covering range is in an operation state or not based on the trained classifier, if so, finishing the detection, and if not, giving an alarm.
To further optimize the above technical solution, step S1 specifically includes:
s11, gridding and dividing the area to be monitored, numbering the grids, and acquiring the monitoring angle, the monitoring distance and the focal length of each grid, and the length and the width of each grid based on the monitoring points;
s12, setting the grid and the adjacent grid as the related grid;
s13, presetting the monitoring time step length and sequence of each grid, and acquiring an image of each grid, wherein the image comprises a stack and/or a working machine;
and S14, establishing a proportional relation between the picture size and the actual size.
To further optimize the above technical solution, step S2 specifically includes:
s21, constructing an image color recognition training set based on covered, uncovered and non-stacked images acquired by different grids under different illumination conditions;
s22, constructing a convolutional neural network, and training the convolutional neural network by taking the color of the material without covering as a characteristic target training set to enable the convolutional neural network to recognize different colors;
s23, collecting images of the stacking loading and unloading operation machine, selecting images of the operation machine in different states under different light conditions, constructing an operation state training set, and training an operation state classifier of the operation machine based on an AlexNet algorithm.
To further optimize the above technical solution, step S3 specifically includes:
s31, identifying the grid image based on the trained convolutional neural network to obtain the area ratio of the color of the non-covering material in the grid area in the grid;
s32, setting an occupancy alarm threshold, judging whether the color area occupancy of the non-covered material in the current grid area is greater than the occupancy alarm threshold, if not, judging that the stacking is covered, and if so, judging whether the stacking is an operation area.
To further optimize the above technical solution, step S4 specifically includes:
s41, calling the grid which sends out the processing requirement for judging whether the operation state is required, calling the grid and the related grid thereof, identifying the downward dumping state of the grab bucket of the operation machine, if the state does not appear, judging that the operation is not carried out, alarming, and if the state does appear, carrying out the next step;
s42, processing the grid and the related grid, and calculating the actual distance between the edge point of the non-covered material color in the collected stacking grid image and the center point of the operation machine;
and S43, if the actual distance is smaller than the preset value, the current stack is considered to be in operation, early warning is cancelled, if the actual distance is larger than the preset value, the operation is considered to be unrelated to the stack, the stack is not covered under the non-operation state, and an alarm is given out.
Taking coal as an example, the invention adopts the following technical scheme:
1. and carrying out gridding division of a monitoring area and intelligent identification of the occupation ratio of the non-covered area in the grid.
(1) The method comprises the steps of meshing an area monitored by monitoring equipment, numbering different grids, recording basic information such as monitoring angles of each grid, distances between the grids and the monitoring equipment, focal lengths and the like, setting the grids and adjacent grids around the grids as related grids, and setting programs of the monitoring equipment, so that the monitoring equipment collects pictures of fixed sizes of each grid according to a preset time step (2 minutes or other) and a preset sequence and transmits the pictures to a system.
(2) And establishing a conversion ratio of the size of the collected picture of each fixed point grid to the actual distance according to preset grid numbers, the distance and the angle between the grid and the camera equipment, focal length information and the like.
(3) 5000 images such as covering, uncovering and non-stacking under different light conditions are collected for each grid to form an image color recognition training set of the grid area, monitoring images of the fixed grid area are trained through a system CNN (convolutional neural network), and the area proportion of the color of non-covering materials in the grid area is recognized (for example, the coal is black, the ore is reddish brown, and the color to be recognized is preset according to the specific material characteristics of stacking).
(4) And setting the percentage alarm threshold value to be 5%, and sending out whether the operation state is judged and processed and preliminary early warning when the percentage value exceeds the threshold value.
2. And intelligently identifying whether the non-covering occupation ratio exceeds an alarm threshold value and whether the stacks in the grid are in a loading and unloading operation state.
(1) 5000 images of stacking, loading and unloading operation machinery are collected, images of different light conditions, downward dumping of a grab bucket and other states of the grab bucket are selected to form an image recognition training set for loading and unloading operation, and an AlexNet algorithm is used for training a classifier of the downward dumping state of the grab bucket. The grab bucket downward dumping state identification based on the deep convolutional network has high identification precision.
(2) And (3) calling the grid and the related grids (generally 5-8 grids adjacent to the grid) to identify the downward dumping state of the grab bucket for the grid which sends out the operation state judgment processing requirement, and defaulting that the loading and unloading operation exists at the periphery of the stack without covering for the grid with the state characteristic.
(3) And formally sending an alarm to a related terminal to inform related personnel to process the alarm for the primary early warning that the grab bucket does not fall down.
3. And judging the relevance of the downward dumping state characteristic of the grab bucket and the color of the non-covered material to the initial early warning of the downward dumping state characteristic of the grab bucket (namely that the loading and unloading machine is in an operating state).
(1) And carrying out data processing on the grid and the adjacent grid images, and converting the actual distance between the edge point of the non-covered material color in the acquired yard grid image and the central point of the grab bucket.
(2) And for the actual distance between the edge point of the area without covering and the central point of the grab bucket is less than 20m, the default is that the stacking without covering is caused by the loading and unloading machine in the operating state, and the early warning is cancelled.
(3) And (3) regarding that the actual distance between the edge point of the area without covering and the central point of the grab bucket is more than or equal to 20m, defaulting that the stacking without covering is irrelevant to the operation state of the loading and unloading machine, formally sending an alarm to a relevant terminal, and informing relevant personnel to process.
According to the technical scheme, compared with the prior art, the invention discloses and provides the intelligent detection method and the system for the non-specialized wharf coal (ore) stacking straw mat cover.
The beneficial effect of this application does:
1. by carrying out gridding division on the storage yard area, unfixed stack (stack size, stack place and stack size are unfixed) monitoring image identification which is difficult to realize is converted into identification of the exposed color of the monitoring image coal (ore) in the whole grid in the fixed grid which is easy to realize, so that the identification accuracy is improved.
2. The characteristic that a grab bucket is in a downward dumping state in the process of carrying out loading and unloading operation on non-specialized wharf coal (ore) loading and unloading machinery is adopted, a loading and unloading operation image recognition training set is established, intelligent recognition of the loading and unloading machinery operation state is achieved, and recognition accuracy is high.
3. By monitoring the information such as the distance and the angle between the grid and the camera equipment, the conversion relation between the fixed-size picture acquired by the fixed-point grid and the actual distance is established, and the relevance judgment of the loading and unloading mechanical operation and the behavior without covering is realized.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. An intelligent detection method for ore stacking covers of non-specialized wharfs is characterized by comprising the following steps:
s1, gridding and dividing the area to be monitored, and collecting monitoring data and images;
s2, constructing a training set based on the monitoring data and the images, and constructing and training a convolutional neural network and a classifier;
s3, identifying the monitored image based on the trained convolutional neural network, obtaining the non-covered area ratio, comparing the non-covered area ratio with a preset value, if the non-covered area ratio is smaller than the preset value, covering normally, and if the non-covered area ratio is larger than the preset value, performing the next step;
and S4, judging whether the non-covering range is in an operation state or not based on the trained classifier, if so, finishing the detection, and if not, giving an alarm.
2. The intelligent detection method for ore stacking covers of non-specialized wharfs according to claim 1, wherein the step S1 specifically comprises:
s11, performing gridding division on the area to be monitored, numbering grids, and acquiring a monitoring angle, a monitoring distance, a focal length, a grid length and a grid width of each grid based on monitoring points;
s12, setting the grid and the adjacent grid thereof as the associated grid;
s13, presetting the monitoring time step length and sequence of each grid, and acquiring an image of each grid, wherein the image comprises a stack and/or a working machine;
and S14, establishing a proportional relation between the picture size and the actual size.
3. The intelligent detection method for ore stacking covers of non-specialized wharfs according to claim 1, wherein the step S2 specifically comprises:
s21, constructing an image color recognition training set based on covered, uncovered and non-stacked images acquired by different grids under different illumination conditions;
s22, constructing a convolutional neural network, and training the convolutional neural network by taking the color of the material without covering as a characteristic target training set to enable the convolutional neural network to recognize different colors;
s23, collecting images of the stacking loading and unloading operation machine, selecting images of the operation machine in different states under different light conditions, constructing an operation state training set, and training an operation state classifier of the operation machine based on an AlexNet algorithm.
4. The intelligent detection method for ore stacking covers of non-specialized wharfs according to claim 1, wherein the step S3 specifically comprises:
s31, identifying the grid image based on the trained convolutional neural network to obtain the area ratio of the color of the non-covering material in the grid area in the grid;
s32, setting an occupancy alarm threshold, judging whether the color area occupancy of the non-covered material in the current grid area is greater than the occupancy alarm threshold, if not, judging that the stacking is covered, and if so, judging whether the stacking is an operation area.
5. The intelligent detection method for ore stacking covers of non-specialized wharfs according to claim 1, wherein the step S4 specifically comprises:
s41, calling the grid which sends out the processing requirement for judging whether the operation state is required, calling the grid and the related grid thereof, identifying the downward dumping state of the grab bucket of the operation machine, if the state does not appear, judging that the operation is not carried out, alarming, and if the state does appear, carrying out the next step;
s42, carrying out data processing on the grid and the related grid thereof, and calculating the actual distance between the edge point of the non-covering material in the collected stacking grid image and the center point of the operation machine;
and S43, if the actual distance is smaller than the preset value, the current stack is considered to be in operation, early warning is cancelled, if the actual distance is larger than the preset value, the operation is considered to be unrelated to the stack, the stack is not covered under the non-operation state, and an alarm is given out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210177930.9A CN114612859B (en) | 2022-02-25 | 2022-02-25 | Intelligent detection method for ore stacking thatch cover of non-specialized wharf |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210177930.9A CN114612859B (en) | 2022-02-25 | 2022-02-25 | Intelligent detection method for ore stacking thatch cover of non-specialized wharf |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114612859A true CN114612859A (en) | 2022-06-10 |
| CN114612859B CN114612859B (en) | 2023-06-27 |
Family
ID=81859121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210177930.9A Active CN114612859B (en) | 2022-02-25 | 2022-02-25 | Intelligent detection method for ore stacking thatch cover of non-specialized wharf |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114612859B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909898A (en) * | 2017-02-24 | 2017-06-30 | 北京惠达智农科技有限公司 | Image intelligent analysing terminal and method in straw-returning monitoring |
| CN110223022A (en) * | 2019-06-12 | 2019-09-10 | 交通运输部天津水运工程科学研究所 | Dangerous Goods Container stores up method for early warning and system |
| CN110909599A (en) * | 2019-10-16 | 2020-03-24 | 北京文安智能技术股份有限公司 | Detection method, device and system for covering of muck truck |
| CN111899186A (en) * | 2020-06-29 | 2020-11-06 | 深圳中兴网信科技有限公司 | Image data enhancement method, system, storage medium and storage yard coverage detection method |
| CN112215815A (en) * | 2020-10-12 | 2021-01-12 | 杭州视在科技有限公司 | Bare soil coverage automatic detection method for construction site |
| CN113378754A (en) * | 2021-06-24 | 2021-09-10 | 中国计量大学 | Construction site bare soil monitoring method |
| WO2021184479A1 (en) * | 2020-03-19 | 2021-09-23 | 无锡德林海环保科技股份有限公司 | Gridding real-time water quality monitoring method and system |
-
2022
- 2022-02-25 CN CN202210177930.9A patent/CN114612859B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909898A (en) * | 2017-02-24 | 2017-06-30 | 北京惠达智农科技有限公司 | Image intelligent analysing terminal and method in straw-returning monitoring |
| CN110223022A (en) * | 2019-06-12 | 2019-09-10 | 交通运输部天津水运工程科学研究所 | Dangerous Goods Container stores up method for early warning and system |
| CN110909599A (en) * | 2019-10-16 | 2020-03-24 | 北京文安智能技术股份有限公司 | Detection method, device and system for covering of muck truck |
| WO2021184479A1 (en) * | 2020-03-19 | 2021-09-23 | 无锡德林海环保科技股份有限公司 | Gridding real-time water quality monitoring method and system |
| CN111899186A (en) * | 2020-06-29 | 2020-11-06 | 深圳中兴网信科技有限公司 | Image data enhancement method, system, storage medium and storage yard coverage detection method |
| CN112215815A (en) * | 2020-10-12 | 2021-01-12 | 杭州视在科技有限公司 | Bare soil coverage automatic detection method for construction site |
| CN113378754A (en) * | 2021-06-24 | 2021-09-10 | 中国计量大学 | Construction site bare soil monitoring method |
Non-Patent Citations (2)
| Title |
|---|
| NINGNING HONG等: "Wind tunnel investigation on the dust emission characteristics of high moisture coal piles" * |
| 乔雨;牟荣峰;杨宁;晁燕安;刘迎雨;陈世明;: "大坝表面聚氨酯未覆盖区域检测方法" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114612859B (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359594B (en) | Mine belt abnormity detection method and device based on video processing | |
| CN106652551B (en) | Parking space detection method and equipment | |
| CN110854807B (en) | New energy relay protection intelligent checking and early warning system based on OCR technology | |
| US7876229B2 (en) | Flare monitoring | |
| CN110844403B (en) | Garbage classification identification method and device based on target identification | |
| CN108268832A (en) | Electric operating monitoring method, device, storage medium and computer equipment | |
| CN116208745A (en) | Dock ship berthing monitoring and recording system and method | |
| CN110633638A (en) | Garbage collection and transportation supervision method and device, storage medium and intelligent equipment | |
| CN110598981A (en) | Movable intelligent grain unloading platform control system | |
| CN111967410B (en) | Property intelligent management and allocation system based on big data | |
| CN111476712B (en) | Trolley grate image shooting and detecting method and system of sintering machine | |
| CN114140684A (en) | Method, device and equipment for detecting coal blockage and coal leakage and storage medium | |
| CN111767822A (en) | Garbage detection method and related equipment and device | |
| CN114612859A (en) | Intelligent detection method for ore stacking tarpaulin of non-specialized wharf | |
| CN113326783A (en) | Edge early warning method for water conservancy industry | |
| CN113920339A (en) | Crane false alarm method in power transmission line channel hidden danger based on deep learning | |
| CN115762089A (en) | Blanking blockage detecting device for ore bin | |
| CN112949872B (en) | Operation and maintenance management system and method for smart city | |
| CN115565133A (en) | Image recognition-based abnormal loose detection method for coiled cable | |
| CN113920535B (en) | Electronic region detection method based on YOLOv5 | |
| CN115359392A (en) | Roadside construction behavior detection method based on improved YOLOv5 model | |
| CN115424075A (en) | Method and system for monitoring pipeline state | |
| CN115296193A (en) | Intelligent inspection system and method for transformer substation | |
| CN103971159A (en) | Whole bundle of bank note number of passing detection device | |
| CN113489929A (en) | Method and device for monitoring supervision of garbage classification, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |