CN119442142A - Accurate identification method of mining objects based on multi-source remote sensing data fusion technology - Google Patents
Accurate identification method of mining objects based on multi-source remote sensing data fusion technology Download PDFInfo
- Publication number
- CN119442142A CN119442142A CN202411488425.1A CN202411488425A CN119442142A CN 119442142 A CN119442142 A CN 119442142A CN 202411488425 A CN202411488425 A CN 202411488425A CN 119442142 A CN119442142 A CN 119442142A
- Authority
- CN
- China
- Prior art keywords
- data
- remote sensing
- mine
- feature
- unit
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Image Processing (AREA)
Abstract
本发明公开了基于多源遥感数据融合技术的矿山地物精准识别方法，涉及数据识别技术领域，包括以下实施步骤：配置矿山地物远端控制区域服务器IP地址信息；进入数据采集端，通过实时收集来自不同传感器和平台的时序多源遥感数据；进入数据融合端，实时消除传感器误差对数据质量的影响；步骤四：进入综合识别端，实时提取不同地物特征，综合识别后并实时验证和优化结果。该基于多源遥感数据融合技术的矿山地物精准识别方法，及时发出遥感数据预警信号，保证矿山地物信息获取的精准度，对矿山地物发出灾害预警信号，保证矿山地物识别的安全可靠性，实现对露天矿山地物的精准识别，为矿山管理和决策提供有力支持。
The present invention discloses a method for accurately identifying mine features based on multi-source remote sensing data fusion technology, which relates to the field of data identification technology and includes the following implementation steps: configuring the IP address information of the remote control area server of the mine features; entering the data acquisition terminal, collecting time-series multi-source remote sensing data from different sensors and platforms in real time; entering the data fusion terminal, eliminating the influence of sensor errors on data quality in real time; step four: entering the comprehensive identification terminal, extracting different features of features in real time, and verifying and optimizing the results in real time after comprehensive identification. The method for accurately identifying mine features based on multi-source remote sensing data fusion technology can timely issue remote sensing data warning signals, ensure the accuracy of mine feature information acquisition, issue disaster warning signals to mine features, ensure the safety and reliability of mine feature identification, realize accurate identification of open-pit mine features, and provide strong support for mine management and decision-making.
Description
Technical Field
The invention relates to the technical field of data identification, in particular to a mine ground feature accurate identification method based on a multi-source remote sensing data fusion technology.
Background
The mine ground feature identification is a technology for accurately identifying geological features and mineral resources in a mine area by using a remote sensing technology, machine learning, hyperspectral analysis and other methods, and the mine ground feature identification refers to identifying and distinguishing different surface features of the mine area through various technical means such as remote sensing images, hyperspectral imaging and the like. The process has great significance for mineral resource exploration, development and management, and with the development of remote sensing technology and computer vision technology, especially the application of deep learning, the precision and efficiency of mine ground object identification are obviously improved.
Publication number CN202080000930.0 discloses a method and platform for dynamic monitoring of typical features of mining based on multi-source remote sensing data fusion and deep neural network. The method can improve the spatial resolution of the remote sensing data image, enhance the image, and then more easily identify the typical object, and simultaneously can efficiently and accurately identify the typical object by adopting a machine interpretation mode, thereby being capable of monitoring the typical object of the mine on line in real time.
Through searching the above patent, it is found that the typical mine feature can be monitored on line in real time during the recognition of the mine feature, but the on-line monitoring value of the mine feature cannot early warn the change trend of the mine feature in advance due to continuous change of the environment, so that the accurate recognition of the mine feature cannot be ensured, and meanwhile, the early warning of the mine feature according to the on-line monitoring data is difficult.
Therefore, a novel mine ground object precise identification method based on a multi-source remote sensing data fusion technology is provided to solve the problems.
Disclosure of Invention
The invention mainly aims to provide a mine ground object precise identification method based on a multisource remote sensing data fusion technology so as to solve the problems in the background.
In order to achieve the purpose, the technical scheme adopted by the invention is that the mine ground object precise identification method based on the multi-source remote sensing data fusion technology comprises the following implementation steps:
Step one, configuring IP address information of a remote control area server of mine ground objects;
step two, entering a data acquisition end, and judging whether the remote sensing data is abnormal or not by collecting time sequence multi-source remote sensing data from different sensors and platforms in real time and analyzing the collected remote sensing data in real time and judging whether the data quality is abnormal or not in real time;
Thirdly, entering a data fusion end, correcting remote sensing data with abnormal data quality in real time, eliminating the influence of sensor errors on the data quality in real time, organically fusing multi-source heterogeneous remote sensing data by adopting image fusion, constructing a deep neural network model, and extracting ground feature characteristics in the image in real time;
And step four, entering a comprehensive recognition end, dividing a mine area into different ground object types through an image segmentation technology, extracting different ground object features in real time, comprehensively recognizing, and verifying and optimizing the result in real time.
The data acquisition end comprises a data acquisition module, a data analysis module and a data tracking module;
the data acquisition module comprises a ground actual measurement data unit and an auxiliary data unit;
the ground actual measurement data unit is used for acquiring an optical image, a radar image, an infrared image and ground actual measurement data at the current moment in real time through satellite remote sensing, unmanned aerial vehicle remote sensing and a ground sensor data source, and recording the data in real time through the data recorder;
The auxiliary data unit is used for collecting basic geographic information, mining plans and historical monitoring records of the mine ground object area in real time through the data receiver and the data recorder.
The data analysis module comprises a data acquisition unit and an abnormality judgment unit;
the data acquisition unit is used for receiving the acquired basic geographic information, mining plans, historical monitoring records and monitoring records of the mine ground object area at the current moment in real time through the data receiver;
The anomaly judging unit is used for judging whether the data of the current time monitoring record need to be corrected or not in real time through a calculation formula, wherein the current time monitoring record comprises a mine feature atmospheric factor correction value, a radiation correction value and a geometric correction value, firstly, the vegetation index calculation formula taking the atmospheric influence into consideration through an enhanced mine feature vegetation index 2 is combined with a normalized difference vegetation index and an atmospheric correction factor ATB to reduce the interference of the atmosphere on vegetation monitoring in the mine feature, and the formula is that the enhanced mine feature vegetation index 2=2.5 (NIR-RED)/(NIR+2.4 x RED+1) (1-ATB);
wherein NIR is near infrared band reflectivity, RED is RED band reflectivity, ATB is atmospheric correction factor;
The data anomaly calculation formula for judging the current time monitoring record is as follows:
Wherein P n represents a determination data value, U 1 represents a data value before current time monitor recording correction, U 2 represents a data value after current time monitor recording correction, X represents standard remote sensing data energy consumption of the data value, X represents standard remote sensing data energy consumption of the corrected data value, if E n =0 is calculated, the determination data does not need correction, and if E n +.0 is calculated, the determination data needs correction.
The data tracking module comprises a data tracking unit and an abnormality early warning unit;
The data tracking unit is used for tracking the monitoring record data value at the current moment in real time through the data tracker;
the abnormal early warning unit is used for sending out voice alarm reminding by the reporting system when the data are judged to be corrected, and recording the abnormal data to be corrected in real time through the color identification.
The data fusion end comprises a data processing module, a data fusion module and a model building module;
The data processing module comprises a data correction unit, wherein the data correction unit is used for correcting data of heterogeneous data which is judged to need to be corrected, and the correction formula is as follows:
wherein U, V, x and y are the image coordinates of the data values before and after transformation, P ij and Q ij are polynomial correction coefficients, n represents polynomial degree, and x and y obtained by calculation represent geometric correction data values.
The data fusion module comprises an image generation unit and an image extraction unit;
The generated image unit is used for automatically generating a remote sensing image through an image fusion technology;
The image extraction unit is used for judging specific objects of the mine feature areas on the remote sensing image through the mine feature shape features on the remote sensing image, and the judging steps are as follows:
According to a first point of the mine feature shape feature on the remote sensing image, equidistant feature points of the same shape of the mine feature and feature points of the current tracked mine feature shape, calculating average distances of feature points of the mine feature shape equidistant, wherein the current tracked feature points are feature point positions of different time periods of the remote sensing image, the average distances of the feature points are distances between different time periods of the mine feature and a standard mine feature area of the remote sensing image, and then calculating approximate outlines of the mine feature in the current remote sensing image according to different point values of the feature points at different moments, and an average distance Z t of the matching feature points is calculated according to the following calculation equation:
Wherein f x,y-1 represents characteristic points of the shape of the mine ground object on a designated area of the remote sensing image at the time t-1, f x,y represents characteristic points monitored and recorded at the time t, M represents the distance between the characteristic points tracked at the time t, X represents a value in the X-axis direction of a point position, and Y represents a value in the Y-axis direction of a moving position;
By moving the pixel point on the known t-1 time route by Z t, the approximate outline of the object in the mine ground feature characteristic of the remote sensing image at the t time can be obtained.
The model building module comprises a model building unit, a manual interpretation unit, an online monitoring unit and a trend early warning unit;
The model building unit is used for building a convolutional neural network model, and the convolutional neural network model is used for setting mine feature identification parameters based on a multi-source remote sensing data fusion technology, wherein the mine feature identification parameters comprise standard values of environmental parameters, disaster early warning parameter grades, mineral distribution range parameters, vegetation destruction parameters and soil erosion parameters;
The manual interpretation unit is used for introducing manual visual interpretation as an auxiliary means and verifying and correcting a machine interpretation result;
The on-line monitoring unit is used for monitoring basic parameters of the current mine ground object area in real time through the data monitoring equipment, wherein the basic parameters comprise environmental parameters, disaster grades, mineral distribution ranges, vegetation destruction rates, water and soil loss rates and historical parameter differences;
the trend early warning unit is used for creating, managing, analyzing and drawing each remote sensing image area through a GIS, and predicting the development trend of the mine ground object in real time through the mine ground object monitoring parameters in the remote sensing image areas, and the prediction method is as follows:
Setting planning standard parameters of mine ground object planning projects corresponding to remote sensing image areas, detecting execution parameters of the mine ground object planning areas in real time by using earthquake monitoring equipment, landslide monitoring equipment, debris flow monitoring equipment, ground settlement monitoring equipment, volcanic eruption monitoring equipment, temperature sensors, humidity sensors and light sensors, and analyzing environmental parameters, disaster grades, mineral distribution ranges, vegetation destruction rates, water and soil loss rates and historical parameter differences of the mine ground object planning areas in real time;
And II, calculating a difference value between the execution parameters of the corresponding area and the planning standard parameters, judging that the planning parameters tend to be safe if the difference value is = +/0.002, judging that the planning parameters exceed the safe value if the difference value is more than 0.002 or < 0.002, sending a planning trend early warning signal, calculating seven days as a period, predicting the development trend of the mine ground object of the corresponding area according to the planning parameters of three periods, judging that the mine ground object development plan of the corresponding area is safe and stable if the planning parameter average value of the three periods does not exceed the planning standard parameters, and judging that the mine ground object development plan of the corresponding area is abnormal if the planning parameter average value of the three periods exceeds the planning standard parameters.
The comprehensive recognition terminal comprises an image segmentation module, a feature extraction module, a feature classification module and a comprehensive recognition module;
The image segmentation module comprises a ground object type unit, wherein the ground object type unit is used for dividing a mine ground object area into different ground object types through calculation of approximate contours, and the ground object types comprise a pit, a waste stone pile and a tailing pond.
The characteristic extraction module is used for extracting the spectrum, texture and shape characteristics in the mine ground object area through a calculation formula of the image extraction unit;
The feature classification module is used for classifying the extracted characteristics of the mine ground objects into different categories, wherein the categories comprise pits, waste rock piles, rivers, buildings and tailing ponds.
The comprehensive analysis module comprises a multi-source data combination unit and a data verification unit;
The multi-source data combination unit is used for combining remote sensing data with a GIS, carrying out space distribution and statistical analysis on mine ground features by utilizing the space analysis function of the GIS, combining the remote sensing data with ground investigation data, carrying out difference calculation on a data analysis value and a trend early warning value at the current moment in real time, judging that the data analysis is effective if the difference value=0, judging that the data analysis is ineffective if the difference value is not equal to 0, and carrying out data correction for the second time;
the data verification unit is used for correcting the data combination and the data identification result by carrying out data verification in real time through a data anomaly calculation formula on the data result of the multi-source data structure unit.
The invention has the following beneficial effects:
1. According to the method, the data acquisition end is arranged, when the mine ground object is accurately identified, the collected remote sensing data is analyzed in real time, whether the remote sensing data is abnormal or not is judged in real time through the remote sensing data collected at the current moment, and remote sensing data early warning signals are timely sent out, so that the accuracy of acquiring the mine ground object information is ensured, and the data errors in the process of acquiring the mine ground object information are reduced;
2. According to the invention, by setting the data fusion end, when accurately identifying the mine ground object, real-time correction is carried out on the remote sensing data with abnormal data quality, and the multi-source heterogeneous remote sensing data are organically fused by adopting image fusion, so that the ground object characteristics in the remote sensing image are extracted in real time, trend prediction is carried out on the monitoring data in real time, disaster early warning signals are sent to the mine ground object in advance, and the safety and reliability of the mine ground object identification are ensured;
3. According to the invention, by arranging the comprehensive recognition terminal, when the mine ground object is accurately recognized, the space distribution and the statistical analysis are carried out on the mine ground object by utilizing the space analysis function of the GIS, the remote sensing data and the ground investigation data are combined, the characteristics of different ground objects are extracted in real time, and after comprehensive recognition, the result is verified and optimized in real time, so that the accurate recognition of the surface mine ground object is realized, and powerful support is provided for mine management and decision.
Drawings
FIG. 1 is an overall flow chart of a mine ground object precise identification method based on a multi-source remote sensing data fusion technology;
FIG. 2 is a schematic diagram of a data acquisition end of the mine ground object precise identification method based on the multi-source remote sensing data fusion technology;
FIG. 3 is a schematic diagram of a data fusion end of the mine ground object precise identification method based on the multi-source remote sensing data fusion technology;
Fig. 4 is a schematic diagram of a comprehensive recognition end of the mine ground object precise recognition method based on the multi-source remote sensing data fusion technology.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Example 1
Referring to fig. 1 to 2, the mine ground object precise identification method based on the multi-source remote sensing data fusion technology comprises the following implementation steps:
Step one, configuring IP address information of a remote control area server of mine ground objects;
step two, entering a data acquisition end, and judging whether the remote sensing data is abnormal or not by collecting time sequence multi-source remote sensing data from different sensors and platforms in real time and analyzing the collected remote sensing data in real time and judging whether the data quality is abnormal or not in real time;
Thirdly, entering a data fusion end, correcting remote sensing data with abnormal data quality in real time, eliminating the influence of sensor errors on the data quality in real time, organically fusing multi-source heterogeneous remote sensing data by adopting image fusion, constructing a deep neural network model, and extracting ground feature characteristics in the image in real time;
And step four, entering a comprehensive recognition end, dividing a mine area into different ground object types through an image segmentation technology, extracting different ground object features in real time, comprehensively recognizing, and verifying and optimizing the result in real time.
The data acquisition end comprises a data acquisition module, a data analysis module and a data tracking module;
The data acquisition module comprises a ground actual measurement data unit and an auxiliary data unit;
The ground actual measurement data unit is used for acquiring an optical image, a radar image, an infrared image and ground actual measurement data at the current moment in real time through satellite remote sensing, unmanned aerial vehicle remote sensing and a ground sensor data source, and recording the data in real time through a data recorder;
The auxiliary data unit is used for collecting basic geographic information, mining plans and historical monitoring records of the mine ground object area in real time through the data receiver and the data recorder.
The data analysis module comprises a data acquisition unit and an abnormality judgment unit;
the data acquisition unit is used for receiving the acquired basic geographic information, mining plans, historical monitoring records and monitoring records of the mine ground object area at the current moment in real time through the data receiver;
The anomaly judging unit is used for judging whether the data of the monitoring record of the current moment needs to be corrected or not in real time through a calculation formula, wherein the monitoring record of the current moment comprises a mine feature atmospheric factor correction value, a radiation correction value and a geometric correction value, firstly, the vegetation index calculation formula considering the atmospheric influence through an enhanced mine feature vegetation index 2 is combined with a normalized difference vegetation index and an atmospheric correction factor ATB to reduce the interference of the atmosphere on vegetation monitoring in the mine feature, and the formula is that the enhanced mine feature vegetation index 2=2.5 (NIR-RED)/(NIR+2.4 x RED+1) (1-ATB);
wherein NIR is near infrared band reflectivity, RED is RED band reflectivity, ATB is atmospheric correction factor;
The data anomaly calculation formula for judging the current time monitoring record is as follows:
Wherein P n represents a determination data value, U 1 represents a data value before current time monitor recording correction, U 2 represents a data value after current time monitor recording correction, X represents standard remote sensing data energy consumption of the data value, X represents standard remote sensing data energy consumption of the corrected data value, if E n =0 is calculated, the determination data does not need correction, and if E n +.0 is calculated, the determination data needs correction.
The data tracking module comprises a data tracking unit and an abnormality early warning unit;
the data tracking unit is used for tracking the monitoring record data value at the current moment in real time through the data tracker;
the abnormal early warning unit is used for sending out voice alarm reminding by the reporting system when the data is judged to be corrected, and recording the abnormal data to be corrected in real time through the color identification.
The time sequence multi-source remote sensing data from different sensors and platforms are collected in real time, the collected remote sensing data are analyzed in real time, whether the remote sensing data are abnormal or not is judged in real time through the remote sensing data collected at the current moment, the current data of the remote sensing data are tracked in real time, remote sensing data early warning signals are timely sent out, accuracy of mine ground object information acquisition is guaranteed, and data errors existing in the mine ground object information acquisition process are reduced.
Example two
Referring to fig. 3, based on the first embodiment, the data fusion end includes a data processing module, a data fusion module, and a model building module;
The data processing module comprises a data correction unit, wherein the data correction unit is used for correcting the data of the heterogeneous data which is judged to need to be corrected, and the correction formula is as follows:
wherein U, V, x and y are the image coordinates of the data values before and after transformation, P ij and Q ij are polynomial correction coefficients, n represents polynomial degree, and x and y obtained by calculation represent geometric correction data values.
The data fusion module comprises a generated image unit and an image extraction unit;
the generated image unit is used for automatically generating a remote sensing image through an image fusion technology;
The image extraction unit is used for judging specific objects of the mine feature area on the remote sensing image through the mine feature shape feature on the remote sensing image, and the judging steps are as follows:
According to a first point of the mine feature shape feature on the remote sensing image, equidistant feature points of the same shape of the mine feature and feature points of the current tracked mine feature shape, calculating average distances of feature points of the mine feature shape equidistant, wherein the current tracked feature points are feature point positions of different time periods of the remote sensing image, the average distances of the feature points are distances between different time periods of the mine feature and a standard mine feature area of the remote sensing image, and then calculating approximate outlines of the mine feature in the current remote sensing image according to different point values of the feature points at different moments, and an average distance Z t of the matching feature points is calculated according to the following calculation equation:
Wherein f x,y-1 represents characteristic points of the shape of the mine ground object on a designated area of the remote sensing image at the time t-1, f x,y represents characteristic points monitored and recorded at the time t, M represents the distance between the characteristic points tracked at the time t, X represents a value in the X-axis direction of a point position, and Y represents a value in the Y-axis direction of a moving position;
By moving the pixel point on the known t-1 time route by Z t, the approximate outline of the object in the mine ground feature characteristic of the remote sensing image at the t time can be obtained.
The model building module comprises a model building unit, a manual interpretation unit, an online monitoring unit and a trend early warning unit;
the model building unit is used for building a convolutional neural network model, and the convolutional neural network model is used for setting mine feature identification parameters based on a multi-source remote sensing data fusion technology, wherein the mine feature identification parameters comprise standard values of environmental parameters, disaster early warning parameter grades, mineral distribution range parameters, vegetation destruction parameters and soil erosion parameters;
The artificial interpretation unit is used for introducing artificial visual interpretation as an auxiliary means and verifying and correcting the machine interpretation result;
The on-line monitoring unit is used for monitoring basic parameters of the current mine ground object area in real time through the data monitoring equipment, wherein the basic parameters comprise environmental parameters, disaster grades, mineral distribution ranges, vegetation destruction rates, water and soil loss rates and historical parameter differences;
The trend early warning unit is used for creating, managing, analyzing and drawing each remote sensing image area through the GIS, and predicting the development trend of the mine ground object in real time through the mine ground object monitoring parameters in the remote sensing image areas, and the prediction method is as follows:
Setting planning standard parameters of mine ground object planning projects corresponding to remote sensing image areas, detecting execution parameters of the mine ground object planning areas in real time by using earthquake monitoring equipment, landslide monitoring equipment, debris flow monitoring equipment, ground settlement monitoring equipment, volcanic eruption monitoring equipment, temperature sensors, humidity sensors and light sensors, and analyzing environmental parameters, disaster grades, mineral distribution ranges, vegetation destruction rates, water and soil loss rates and historical parameter differences of the mine ground object planning areas in real time;
And II, calculating a difference value between the execution parameters of the corresponding area and the planning standard parameters, judging that the planning parameters tend to be safe if the difference value is = +/0.002, judging that the planning parameters exceed the safe value if the difference value is more than 0.002 or < 0.002, sending a planning trend early warning signal, calculating seven days as a period, predicting the development trend of the mine ground object of the corresponding area according to the planning parameters of three periods, judging that the mine ground object development plan of the corresponding area is safe and stable if the planning parameter average value of the three periods does not exceed the planning standard parameters, and judging that the mine ground object development plan of the corresponding area is abnormal if the planning parameter average value of the three periods exceeds the planning standard parameters.
The time sequence multi-source remote sensing data from different sensors and platforms are collected in real time, the collected remote sensing data are analyzed in real time, whether the remote sensing data are abnormal or not is judged in real time through the remote sensing data collected at the current moment, the current data of the remote sensing data are tracked in real time, remote sensing data early warning signals are timely sent out, accuracy of mine ground object information acquisition is guaranteed, and data errors existing in the mine ground object information acquisition process are reduced.
Example III
Referring to fig. 4, based on the first embodiment, the comprehensive recognition terminal includes an image segmentation module, a feature extraction module, a feature classification module, and a comprehensive recognition module;
The image segmentation module comprises a ground object type unit, wherein the ground object type unit is used for dividing a mine ground object area into different ground object types through calculation of approximate contours, and the ground object types comprise a pit, a waste stone pile and a tailing pond.
The feature extraction module is used for extracting the spectrum, texture and shape features in the mine ground object region through a calculation formula of the image extraction unit;
the feature classification module is used for classifying the extracted characteristics of the mine ground objects into different categories, wherein the categories comprise pits, waste rock piles, rivers, buildings and tailing ponds.
The comprehensive analysis module comprises a multi-source data combination unit and a data verification unit;
the multi-source data combination unit is used for combining the remote sensing data with the GIS, carrying out space distribution and statistical analysis on mine ground features by utilizing the space analysis function of the GIS, combining the remote sensing data with ground investigation data, carrying out difference calculation on a data analysis value and a trend early warning value at the current moment in real time, judging that the data analysis is effective if the difference value=0, judging that the data analysis is ineffective if the difference value is not equal to 0, and carrying out data correction for the second time;
The data verification unit is used for correcting the data combination and the data identification result by carrying out data verification in real time through the data anomaly calculation formula on the data result of the multi-source data structure unit.
The method comprises the steps of extracting different ground feature characteristics in real time, comprehensively identifying and verifying and optimizing results in real time, carrying out space distribution and statistical analysis on mine ground features by utilizing a space analysis function of a GIS, carrying out image segmentation, feature extraction and classification extraction type identification, combining remote sensing data with ground investigation data, extracting different ground feature characteristics in real time, comprehensively identifying and verifying and optimizing results in real time, realizing accurate identification on surface mine ground features, and providing powerful support for mine management and decision.
According to the mine ground object precise identification method based on the multi-source remote sensing data fusion technology, firstly, IP address information of a remote control area server of the mine ground object is configured; the method comprises the steps of entering a data acquisition end, real-time collecting time sequence multisource remote sensing data from different sensors and platforms, real-time analyzing the collected remote sensing data, judging whether the remote sensing data is abnormal or not, real-time collecting time sequence multisource remote sensing data from different sensors and platforms, real-time analyzing the collected remote sensing data, real-time judging whether the remote sensing data is abnormal or not, real-time tracking the current data of the remote sensing data, timely sending out remote sensing data early warning signals, guaranteeing accuracy of mine ground object information acquisition, reducing data errors existing in the process of obtaining mine ground object information, entering a data fusion end, real-time correcting the remote sensing data with abnormal data, real-time eliminating influence of sensor errors on the data quality, adopting image fusion to organically fuse the multisource heterogeneous remote sensing data, real-time extracting ground object characteristics in images, timely eliminating influence of the sensor errors on the data quality, adopting image fusion to organically fuse the multisource heterogeneous data, constructing a depth neural network, timely sending out remote sensing data early warning signals, timely correcting real-time monitoring and real-time data interpretation machine prediction data, carrying out visual disaster prediction and real-time data analysis, and real-time data analysis and real-time data prediction and real-time data interpretation and real-time prediction and carrying out real-time prediction and data interpretation, the method comprises the steps of determining the type of the mine ground object, determining the safety and reliability of the mine ground object, entering a comprehensive recognition end, dividing the mine area into different ground object types through an image segmentation technology, extracting different ground object features in real time, comprehensively recognizing and verifying and optimizing results in real time, performing spatial distribution and statistical analysis on the mine ground object by utilizing a spatial analysis function of a GIS, performing image segmentation, feature extraction and classification extraction type recognition, combining remote sensing data with ground investigation data, extracting different ground object features in real time, comprehensively recognizing and verifying and optimizing results in real time, and realizing accurate recognition of the surface mine ground object, thereby providing powerful support for mine management and decision.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411488425.1A CN119442142A (en) | 2024-10-24 | 2024-10-24 | Accurate identification method of mining objects based on multi-source remote sensing data fusion technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411488425.1A CN119442142A (en) | 2024-10-24 | 2024-10-24 | Accurate identification method of mining objects based on multi-source remote sensing data fusion technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119442142A true CN119442142A (en) | 2025-02-14 |
Family
ID=94506876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411488425.1A Pending CN119442142A (en) | 2024-10-24 | 2024-10-24 | Accurate identification method of mining objects based on multi-source remote sensing data fusion technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119442142A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120278558A (en) * | 2025-06-09 | 2025-07-08 | 四川省综合地质调查研究所 | Data extraction method and system for digital geological mineral exploration |
| CN120635707A (en) * | 2025-06-06 | 2025-09-12 | 泰安泰山新晨地理信息有限公司 | An intelligent classification method and system for urban land based on remote sensing technology |
-
2024
- 2024-10-24 CN CN202411488425.1A patent/CN119442142A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120635707A (en) * | 2025-06-06 | 2025-09-12 | 泰安泰山新晨地理信息有限公司 | An intelligent classification method and system for urban land based on remote sensing technology |
| CN120278558A (en) * | 2025-06-09 | 2025-07-08 | 四川省综合地质调查研究所 | Data extraction method and system for digital geological mineral exploration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117576581B (en) | Geological exploration remote sensing monitoring method based on image processing | |
| CN119442142A (en) | Accurate identification method of mining objects based on multi-source remote sensing data fusion technology | |
| CN108489403B (en) | A fast and precise method for evaluating the occurrence of rock mass joints in open-pit mine slopes based on 3D laser scanning | |
| CN118887767B (en) | Forest fire early warning method, system and equipment based on satellite Internet of things | |
| CN116416401B (en) | Polluted site assessment method and system based on unmanned aerial vehicle aerial photography | |
| CN119672910A (en) | A method for monitoring active targets of geological hazards based on dynamic visual tracking | |
| CN119573744B (en) | Path planning and optimizing system for offshore wind power mine sweeping operation | |
| CN119984162A (en) | Highway slope deformation monitoring system and method | |
| CN119596334A (en) | Reservoir bank slope geological disaster risk identification method based on unmanned plane laser radar | |
| CN117433440B (en) | Roadway deformation real-time detection method and device based on laser point cloud and storage medium | |
| CN118447155A (en) | Cable trench mapping system based on wireless inspection | |
| CN116403093B (en) | Multi-source remote sensing interpretation method and device for potential landslide along railway | |
| CN117218524A (en) | Urban violation area identification method based on space-sky-earth multi-view image collaboration | |
| CN120196909B (en) | A high-cut slope stability assessment method based on multi-source data fusion | |
| WO2023187251A1 (en) | Method and system for remotely analysing trees | |
| CN119665905B (en) | Deformation detection method and system for river flood control wall | |
| CN120543550A (en) | A method and system for visual detection of surrounding rock deformation in coal mine tunnels | |
| CN118864157B (en) | Intelligent management system and method for new energy stations based on 5G communication | |
| CN119939148A (en) | Intelligent identification method, system and storage medium of landslide disaster in reservoir area based on deep learning | |
| CN118747698A (en) | An environmental protection intelligent monitoring system for power transmission and transformation project construction period based on drones | |
| CN119089158B (en) | Digital highway construction and operation method based on 5G communication and holographic perception | |
| Zeybek | Estimation of powerline route from airborne lidar | |
| CN120182911A (en) | Vision-based risk assessment and control method and system for rockfall impact on structures | |
| Ochiel et al. | An Internet of Things Based system for Road Surface Condition Assessment Using Machine Learning | |
| Shen et al. | Coarse-to-Fine Separation of Wood and Leaf from MLS Street Tree Point Clouds Using Branch Tilt Prior and Enhanced Shortest Path Tracing |
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 |