CN111894046B - Cutting construction monitoring system - Google Patents
Cutting construction monitoring system Download PDFInfo
- Publication number
- CN111894046B CN111894046B CN202010576432.2A CN202010576432A CN111894046B CN 111894046 B CN111894046 B CN 111894046B CN 202010576432 A CN202010576432 A CN 202010576432A CN 111894046 B CN111894046 B CN 111894046B
- Authority
- CN
- China
- Prior art keywords
- information
- rock
- soil
- cutting construction
- cutting
- 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.)
- Active
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02D—FOUNDATIONS; EXCAVATIONS; EMBANKMENTS; UNDERGROUND OR UNDERWATER STRUCTURES
- E02D33/00—Testing foundations or foundation structures
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
- B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02D—FOUNDATIONS; EXCAVATIONS; EMBANKMENTS; UNDERGROUND OR UNDERWATER STRUCTURES
- E02D17/00—Excavations; Bordering of excavations; Making embankments
- E02D17/20—Securing of slopes or inclines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Paleontology (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a cutting construction monitoring system, which comprises: the field terminal is used for acquiring sun altitude angle information and light intensity information of the cutting construction field; the plurality of first unmanned machines are used for acquiring first images; the plurality of second unmanned aerial vehicles are used for acquiring second images; the server identifies initial rock and soil color information from the first image and identifies rock and soil texture information from the second image, the server inputs the rock and soil color information and the rock and soil texture information into the first neural network prediction model, actual rock and soil type information of a plurality of preset monitoring points of the cutting construction site is respectively output and is compared with the predicted rock and soil type information of the preset monitoring points to obtain a comparison difference value, and if the comparison difference value is larger than a preset threshold value, a warning signal is sent out. According to the method and the device, the rock and soil type is judged according to the obtained rock and soil color information and rock and soil texture information, a basis is provided for designers to modify a construction scheme, the efficiency is improved, and the labor cost is reduced.
Description
Technical Field
The invention relates to the field of road construction. More particularly, the present invention relates to a cutting construction monitoring system.
Background
When the cutting is in the construction process, the collapse accident of the slope happens frequently, and the common reason is that the actual rock and soil types cannot be accurately considered in the design scheme. The actual rock and soil types are obtained in time in the construction process, designers can change the construction scheme as soon as possible, the accident occurrence probability can be reduced to a large extent, however, the method needs a large number of designers to follow up the construction in real time, the efficiency is low, and the labor cost is high. Therefore, it is desirable to design a technical solution that can overcome the above-mentioned drawbacks to a certain extent.
Disclosure of Invention
The invention aims to provide a cutting construction monitoring system, which judges the rock and soil type according to the obtained rock and soil color information and rock and soil texture information, provides a basis for designers to modify a construction scheme, improves the efficiency and reduces the labor cost.
To achieve these objects and other advantages and in accordance with the purpose of the invention, as embodied and broadly described herein, there is provided a cutting construction monitoring system including:
the field terminal is used for acquiring sun altitude angle information and light intensity information of the cutting construction field;
the system comprises a plurality of first unmanned machines, a plurality of second unmanned machines and a monitoring server, wherein the first unmanned machines are used for collecting first images at a plurality of first preset positions above a cutting construction site, and the first preset positions respectively correspond to a plurality of preset monitoring points of the cutting construction site;
the second unmanned aerial vehicles are used for acquiring second images at a plurality of second preset positions above the cutting construction site, and the second preset positions respectively correspond to the preset monitoring points of the cutting construction site;
the server is in communication connection with the field terminal, the first unmanned aerial vehicles and the second unmanned aerial vehicles, the server identifies initial rock and soil color information from the first image and identifies rock and soil texture information from the second image, the server also acquires the solar altitude angle information and the light intensity information of the cutting construction field, and the server corrects the initial rock and soil color information according to the solar altitude angle information and the light intensity information of corresponding time points to obtain rock and soil color information;
the server inputs the rock-soil color information and the rock-soil texture information into a first neural network prediction model, respectively outputs actual rock-soil type information of a plurality of preset monitoring points of the cutting construction site, compares the actual rock-soil type information with predicted rock-soil type information of the preset monitoring points to obtain a comparison difference value, and sends out a warning signal if the comparison difference value is larger than a preset threshold value, wherein the predicted rock-soil type information is rock-soil type information utilized by a cutting design drawing;
the first neural network prediction model is obtained by training by taking the color information and the texture information of the rock and soil sample as input data and the type information of the rock and soil sample as output data.
Further, for each preset monitoring point, the distance between the corresponding second preset position and the preset monitoring point is smaller than the distance between the corresponding first preset position and the preset monitoring point.
Furthermore, the cutting construction monitoring system determines a plurality of preset monitoring points according to a cutting design drawing and position information of a cutting construction site.
Furthermore, the cutting construction monitoring system determines longitude and latitude information and height information of the first preset positions and the second preset positions according to longitude and latitude information and height information of the preset monitoring points.
Further, in the cutting construction monitoring system, the server inputs initial rock-soil color information, the solar altitude angle information and the light intensity information of corresponding time points into a second neural network prediction model to obtain rock-soil color information;
and the second neural network prediction model is obtained by training by taking the apparent color information of the rock-soil sample, the corresponding solar altitude angle information and the corresponding light intensity information as input data and taking the actual color information of the rock-soil sample as output data.
Further, the cutting construction monitoring system eliminates the sundry areas in the first image and the second image before the first image and the second image are identified.
Further, the cutting construction monitoring system, the field terminal collects solar altitude angle information and light intensity information of a cutting construction site in real time, the first unmanned aerial vehicles collect first images at intervals of preset time, and the second unmanned aerial vehicles collect second images at intervals of preset time.
The invention at least comprises the following beneficial effects:
according to the invention, the first unmanned aerial vehicle and the second unmanned aerial vehicle are utilized to respectively obtain the first image and the second image in the cutting construction process, the first image and the second image are utilized to obtain rock-soil color information and rock-soil texture information, and the first neural network prediction model is utilized to judge the actual rock-soil type, so that a basis is provided for designers to modify the construction scheme, the construction efficiency is improved, the labor cost is reduced, and the occurrence rate of slope collapse accidents is further reduced.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
Fig. 1 is a frame diagram of the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
It will be understood that terms such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
As shown in fig. 1, an embodiment of the present invention provides a cutting construction monitoring system, including: the field terminal is used for acquiring sun altitude angle information and light intensity information of the cutting construction field; the system comprises a plurality of first unmanned machines, a plurality of second unmanned machines and a monitoring server, wherein the first unmanned machines are used for collecting first images at a plurality of first preset positions above a cutting construction site, and the first preset positions respectively correspond to a plurality of preset monitoring points of the cutting construction site; the second unmanned aerial vehicles are used for acquiring second images at a plurality of second preset positions above the cutting construction site, and the second preset positions respectively correspond to the preset monitoring points of the cutting construction site; the server is in communication connection with the field terminal, the first unmanned aerial vehicles and the second unmanned aerial vehicles, the server identifies initial rock and soil color information from the first image and identifies rock and soil texture information from the second image, the server also acquires the solar altitude angle information and the light intensity information of the cutting construction field, and the server corrects the initial rock and soil color information according to the solar altitude angle information and the light intensity information of corresponding time points to obtain rock and soil color information; the server inputs the rock-soil color information and the rock-soil texture information into a first neural network prediction model, respectively outputs actual rock-soil type information of a plurality of preset monitoring points of the cutting construction site, compares the actual rock-soil type information with predicted rock-soil type information of the preset monitoring points to obtain a comparison difference value, and sends out a warning signal if the comparison difference value is larger than a preset threshold value, wherein the predicted rock-soil type information is rock-soil type information utilized by a cutting design drawing; the first neural network prediction model is obtained by training by taking the color information and the texture information of the rock and soil sample as input data and the type information of the rock and soil sample as output data.
In the above embodiment, the field terminal includes the necessary light intensity sensor, sun tracking sensor, communication module and control element, so that the field terminal can collect the sun altitude angle information and the light intensity information and transmit them to the server. The first unmanned aerial vehicle and the second unmanned aerial vehicle are provided with necessary camera equipment and a communication module, and can shoot a first image and a second image and transmit the first image and the second image to the server. The predetermined monitoring points are construction areas, the first predetermined position is not specifically limited, the rock and soil color of the construction areas can be clearly obtained, the second predetermined position is not specifically limited, and the rock and soil texture can be clearly obtained. When the predetermined monitoring point, the first predetermined position and the second predetermined position are actually determined, adjustment can be performed by combining feedback of site construction personnel. The specific type of server is not limited, and may be a local server or a cloud server. For the first image, the server identifies and acquires initial rock and soil color information, and optionally, an RGB value capable of representing the entire color, such as a pixel with a large number percentage, may be selected from the RGB values of each pixel to serve as the initial rock and soil color information. Outdoor, the color of ground in the sun altitude angle and light intensity will be influenced to first image, especially along with the change of sun altitude angle and light intensity, the color of ground can change, consequently need rectify initial ground color information, specifically rectify through the relevance of sun altitude angle, light intensity and color, obtain ground color information. The rock texture information is the surface structure of the rock, the surface structure of different rocks is different, and the rock texture information is obtained through the second image. And (3) inputting the rock and soil color information and the rock and soil texture information into the first neural network prediction model to obtain actual rock and soil type information, optionally converting the rock and soil color information and the rock and soil texture information into vectors and inputting the vectors into the first neural network prediction model. The actual rock and soil type information is compared with the predicted rock and soil type information of the corresponding position, the predicted rock and soil type information is the rock and soil type information adopted in the design stage, the comparison refers to comparison of properties of the rock and soil, when the property difference is large, the comparison difference value is large, particularly, when the comparison is achieved, assignment can be carried out on the rock and soil of each type in advance according to the property difference, and the comparison difference value is calculated according to the assignment. And when the difference value is larger, sending a warning signal to remind a designer to redesign the construction scheme according to the actual rock and soil type information. The first neural network prediction model is obtained through training of some training data, when the accuracy reaches a set standard, practical application is carried out, the training data are selected from rock and soil samples in a local area, and color information, texture information and types of the rock and soil samples are obtained and used as the training data. It can be seen that in the cutting construction process, the first unmanned aerial vehicle and the second unmanned aerial vehicle are used for respectively obtaining the first image and the second image, the first image and the second image are used for obtaining rock-soil color information and rock-soil texture information, the first neural network prediction model is used for judging the actual rock-soil type, a basis is provided for designers to modify the construction scheme, the construction efficiency is improved, the labor cost is reduced, and the accident rate of slope collapse is further reduced.
In other embodiments, for each of the predetermined monitoring points, the distance between the corresponding second predetermined position and the predetermined monitoring point is smaller than the distance between the corresponding first predetermined position and the predetermined monitoring point, and the geotechnical texture information requires more details and requires a second image to be acquired close to the predetermined monitoring point.
In other embodiments, a plurality of the predetermined monitoring points are determined according to the cutting design drawing and the position information of the cutting construction site, the position information can be determined by combining GPS positioning and site exploration, and then the plurality of the predetermined monitoring points are determined by combining the cutting design drawing, optionally, the predetermined monitoring points are areas which are easy to collapse.
In other embodiments, according to the longitude and latitude information and the height information of the plurality of predetermined monitoring points, the longitude and latitude information and the height information of the plurality of first predetermined locations and the plurality of second predetermined locations are determined, that is, the first image acquired by the first unmanned aerial vehicle and the second image acquired by the second unmanned aerial vehicle can obtain sufficient color information, and the second image can obtain sufficient texture information.
In other embodiments, the server inputs the initial rock-soil color information, the solar altitude information and the light intensity information corresponding to the time point into a second neural network prediction model to obtain rock-soil color information; and the second neural network prediction model is obtained by training by taking the apparent color information of the rock-soil sample, the corresponding solar altitude angle information and the corresponding light intensity information as input data and taking the actual color information of the rock-soil sample as output data. The embodiments provide a scheme for correcting initial rock-soil color information by using a second neural network prediction model, compared with other empirical modes, the scheme is more accurate and faster in correction speed, training data are selected from rock-soil samples in a local area, and color information of the rock-soil samples outdoors, corresponding solar altitude angles and light intensities are obtained to serve as the training data.
In other embodiments, before the first image and the second image are identified, the impurity areas in the first image and the second image are removed, and the impurity areas can be areas occupied by shadows, rocks, tasks, weeds and the like.
In other embodiments, the field terminal collects solar altitude angle information and light intensity information of a cutting construction site in real time, the first unmanned aerial vehicles collect first images at intervals of preset time, the second unmanned aerial vehicles collect second images at intervals of preset time, and the solar altitude angle information, the light intensity information, the first images and the second images at a certain moment are synchronously corresponding to each other, so that errors caused by asynchronous time points of each competition are avoided.
The number of apparatuses and the scale of the process described herein are intended to simplify the description of the present invention. Applications, modifications and variations of the cutting construction monitoring system of the present invention will be apparent to those skilled in the art.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (7)
1. Cutting construction monitored control system, its characterized in that includes:
the field terminal is used for acquiring sun altitude angle information and light intensity information of the cutting construction field;
the system comprises a plurality of first unmanned machines, a plurality of second unmanned machines and a monitoring server, wherein the first unmanned machines are used for collecting first images at a plurality of first preset positions above a cutting construction site, and the first preset positions respectively correspond to a plurality of preset monitoring points of the cutting construction site;
the second unmanned aerial vehicles are used for acquiring second images at a plurality of second preset positions above the cutting construction site, and the second preset positions respectively correspond to the preset monitoring points of the cutting construction site;
the server is in communication connection with the field terminal, the first unmanned aerial vehicles and the second unmanned aerial vehicles, the server identifies initial rock and soil color information from the first image and identifies rock and soil texture information from the second image, the server also acquires the solar altitude angle information and the light intensity information of the cutting construction field, and the server corrects the initial rock and soil color information according to the solar altitude angle information and the light intensity information of corresponding time points to obtain rock and soil color information;
the server inputs the rock-soil color information and the rock-soil texture information into a first neural network prediction model, respectively outputs actual rock-soil type information of a plurality of preset monitoring points of the cutting construction site, compares the actual rock-soil type information with predicted rock-soil type information of the preset monitoring points to obtain a comparison difference value, and sends out a warning signal if the comparison difference value is larger than a preset threshold value, wherein the predicted rock-soil type information is rock-soil type information utilized by a cutting design drawing;
the first neural network prediction model is obtained by training by taking the color information and the texture information of the rock and soil sample as input data and the type information of the rock and soil sample as output data.
2. The cut construction monitoring system of claim 1 wherein for each of the predetermined monitoring points, the distance from the corresponding second predetermined location to the predetermined monitoring point is less than the distance from the corresponding first predetermined location to the predetermined monitoring point.
3. The cutting construction monitoring system according to claim 1, wherein a plurality of the predetermined monitoring points are determined based on a cutting design drawing and position information of a cutting construction site.
4. The cutting construction monitoring system according to claim 1, wherein longitude and latitude information and altitude information of a plurality of the first predetermined locations and a plurality of the second predetermined locations are determined based on longitude and latitude information and altitude information of a plurality of the predetermined monitoring points.
5. The cutting construction monitoring system according to claim 1, wherein the server inputs initial rock-soil color information and the solar altitude information and the light intensity information at corresponding time points into a second neural network prediction model to obtain rock-soil color information;
and the second neural network prediction model is obtained by training by taking the apparent color information of the rock-soil sample, the corresponding solar altitude angle information and the corresponding light intensity information as input data and taking the actual color information of the rock-soil sample as output data.
6. The cutting construction monitoring system according to claim 1, wherein the debris area in the first image and the second image is removed before the first image and the second image are identified.
7. The cutting construction monitoring system according to claim 1, wherein the field terminal collects solar altitude information and light intensity information of a cutting construction site in real time, a plurality of the first drones collect first images at predetermined intervals, and a plurality of the second drones collect second images at predetermined intervals.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010576432.2A CN111894046B (en) | 2020-06-22 | 2020-06-22 | Cutting construction monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010576432.2A CN111894046B (en) | 2020-06-22 | 2020-06-22 | Cutting construction monitoring system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111894046A CN111894046A (en) | 2020-11-06 |
CN111894046B true CN111894046B (en) | 2021-09-28 |
Family
ID=73206941
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010576432.2A Active CN111894046B (en) | 2020-06-22 | 2020-06-22 | Cutting construction monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111894046B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102937462A (en) * | 2012-11-06 | 2013-02-20 | 清华大学 | River ecology monitoring method |
CN107101666A (en) * | 2017-03-24 | 2017-08-29 | 广东省交通规划设计研究院股份有限公司 | A kind of intellectual faculties of cut slope Construction engineering geology condition |
CN107328916A (en) * | 2017-08-11 | 2017-11-07 | 潘荣兰 | A kind of effective soil environment monitoring system |
CN107097812B (en) * | 2017-04-30 | 2018-03-02 | 中南大学 | A kind of railway heavy showers amount unmanned plane real-time intelligent measuring method and system |
CN107976528A (en) * | 2017-12-27 | 2018-05-01 | 山东国标环境工程有限公司 | A kind of contaminated soil remediation processing unit monitoring device |
JP2019167751A (en) * | 2018-03-23 | 2019-10-03 | ライト工業株式会社 | Survey method of ground property |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7848905B2 (en) * | 2000-12-26 | 2010-12-07 | Troxler Electronic Laboratories, Inc. | Methods, systems, and computer program products for locating and tracking objects |
GB0229625D0 (en) * | 2002-12-19 | 2003-01-22 | British Telecomm | Searching images |
-
2020
- 2020-06-22 CN CN202010576432.2A patent/CN111894046B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102937462A (en) * | 2012-11-06 | 2013-02-20 | 清华大学 | River ecology monitoring method |
CN107101666A (en) * | 2017-03-24 | 2017-08-29 | 广东省交通规划设计研究院股份有限公司 | A kind of intellectual faculties of cut slope Construction engineering geology condition |
CN107097812B (en) * | 2017-04-30 | 2018-03-02 | 中南大学 | A kind of railway heavy showers amount unmanned plane real-time intelligent measuring method and system |
CN107328916A (en) * | 2017-08-11 | 2017-11-07 | 潘荣兰 | A kind of effective soil environment monitoring system |
CN107976528A (en) * | 2017-12-27 | 2018-05-01 | 山东国标环境工程有限公司 | A kind of contaminated soil remediation processing unit monitoring device |
JP2019167751A (en) * | 2018-03-23 | 2019-10-03 | ライト工業株式会社 | Survey method of ground property |
Also Published As
Publication number | Publication date |
---|---|
CN111894046A (en) | 2020-11-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9942440B2 (en) | Image-based field boundary detection and identification | |
Khan et al. | Unmanned aerial vehicle–based traffic analysis: Methodological framework for automated multivehicle trajectory extraction | |
CN110889327B (en) | Intelligent detection method for sewage outlet around water area based on thermal infrared image | |
CN111915128B (en) | Post-disaster evaluation and rescue auxiliary system for secondary landslide induced by earthquake | |
CN107316457B (en) | Method for judging whether road traffic condition accords with automatic driving of automobile | |
CN103625649A (en) | Aircraft autonomous landing region judging method based on self adaptive region division and window communication | |
CN114442665B (en) | Wind power blade inspection line planning method based on unmanned aerial vehicle | |
CN114089786A (en) | Autonomous inspection system based on unmanned aerial vehicle vision and along mountain highway | |
KR20190043396A (en) | Method and system for generating and providing road weather information by using image data of roads | |
CN115331190A (en) | Road hidden danger identification method and device based on radar fusion | |
CN112285733A (en) | Urban and rural planning verification and mapping data processing method | |
CN110413002B (en) | Unmanned aerial vehicle remote sensing information acquisition method and device | |
CN113330334A (en) | Reducing the scale of weather forecasts | |
WO2022107619A1 (en) | Data analysis device and method, and program | |
WO2022107620A1 (en) | Data analysis device and method, and program | |
CN111894046B (en) | Cutting construction monitoring system | |
CN112926415A (en) | Pedestrian avoiding system and pedestrian monitoring method | |
CN116736409A (en) | Automobile safety early warning method, device, equipment and storage medium | |
CN114581748B (en) | Multi-agent perception fusion system based on machine learning and implementation method thereof | |
CN114024997B (en) | Intelligent equipment based on automatic driving and AIOT Internet of things platform method | |
US20220215645A1 (en) | Computer Vision Systems and Methods for Determining Roof Conditions from Imagery Using Segmentation Networks | |
CN113052474B (en) | Cross-crossing key part early warning method and system based on power grid | |
Li et al. | Prediction of wheat gains with imagery from four-rotor UAV | |
CN115035051A (en) | Component segmentation method and device for photovoltaic power station, electronic equipment and storage medium | |
KR102209866B1 (en) | Preprocessing Method of Distortion Image for Ground Based Total Cloude Cover Automatic Retrieval |
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 |