WO2023022587A1 - Geographic data processing methods and systems for assessing geohazard risk - Google Patents

Geographic data processing methods and systems for assessing geohazard risk Download PDF

Info

Publication number
WO2023022587A1
WO2023022587A1 PCT/MY2022/050072 MY2022050072W WO2023022587A1 WO 2023022587 A1 WO2023022587 A1 WO 2023022587A1 MY 2022050072 W MY2022050072 W MY 2022050072W WO 2023022587 A1 WO2023022587 A1 WO 2023022587A1
Authority
WO
WIPO (PCT)
Prior art keywords
slope
geographic area
hazard
data
geographic
Prior art date
Application number
PCT/MY2022/050072
Other languages
French (fr)
Inventor
Tareq Aziz Hasan ALQUTAMI
Nian Wei TAN
Muhammad Arif B ABDUL RAHMAN
Naila Rusma Bt IDRIS
Mohd Nazri B AHMAD
Swee Ling KOI
Mohd Syazwan Kamil BIN ABDULLAH
Original Assignee
Petroliam Nasional Berhad (Petronas)
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Petroliam Nasional Berhad (Petronas) filed Critical Petroliam Nasional Berhad (Petronas)
Publication of WO2023022587A1 publication Critical patent/WO2023022587A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation

Definitions

  • the present disclosure relates to geographic data processing methods and systems.
  • the present disclosure relates to methods and systems for assessing risk due to geological features and environmental conditions.
  • a geographic data processing method for assessing geohazard risk comprises: receiving elevation data and image data for a geographic area; performing geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extracting lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyzing the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
  • extracting lineaments from the elevation data comprises applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
  • the method further comprises applying line extraction to the detected edges in the hillshade map to obtain a set of line segments.
  • the method further comprises identifying lineaments as line segments from the set of line segments which fulfil a length threshold.
  • extracting slope faces from the elevation data comprises calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
  • the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
  • analyzing the image data to determine a slope cover classification comprises performing a tile-based image classification on the image data using machine learning.
  • the tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
  • combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area comprises combining as a weighted average obtained using a scoring matrix.
  • a computer readable medium storing processor executable instructions which when executed on a processor cause the processor to carry out a method as set out above is provided.
  • a geographic data processing system for assessing geohazard risk.
  • the geographic data processing system comprises: a processor and a data storage device storing computer program instructions operable to cause the processor to: perform geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extract lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyze the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
  • the data storage device further stores computer program instructions operable to cause the processor to: extract lineaments from the elevation data by applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
  • the data storage device further stores computer program instructions operable to cause the processor to: apply line extraction to the detected edges in the hillshade map to obtain a set of line segments.
  • the data storage device further stores computer program instructions operable to cause the processor to: identify lineaments as line segments from the set of line segments which fulfil a length threshold.
  • the data storage device further stores computer program instructions operable to cause the processor to: extract slope faces from the elevation data by calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect.
  • the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
  • the data storage device further stores computer program instructions operable to cause the processor to: analyze the image data to determine a slope cover classification by performing a tile-based image classification on the image data using machine learning.
  • tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
  • the data storage device further stores computer program instructions operable to cause the processor to: combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area by combining as a weighted average obtained using a scoring matrix.
  • a geographic data processing method for assessing geohazard risk comprising: receiving elevation data and image data for a geographic area; performing geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extracting lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyzing the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
  • extracting lineaments from the elevation data comprises applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
  • a method according to clause 2 further comprising applying line extraction to the detected edges in the hillshade map to obtain a set of line segments.
  • extracting slope faces from the elevation data comprises calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
  • the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
  • analyzing the image data to determine a slope cover classification comprises performing a tile-based image classification on the image data using machine learning.
  • the tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
  • combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area comprises combining as a weighted average obtained using a scoring matrix.
  • a computer readable medium storing processor executable instructions which when executed on a processor cause the processor to carry out a method according to any one of clauses 1 to 9.
  • a geographic data processing system for assessing geohazard risk, the geographic data processing system comprising: a processor and a data storage device storing computer program instructions operable to cause the processor to: perform geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extract lineaments from the elevation data, extracting slope feces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyze the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
  • a geographic data processing system according to clause 11 , wherein the data storage device further stores computer program instructions operable to cause the processor to: extract lineaments from the elevation data by applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
  • a geographic data processing system wherein the data storage device further stores computer program instructions operable to cause the processor to: apply line extraction to the detected edges in the hillshade map to obtain a set of line segments.
  • a geographic data processing system according to clause 13, wherein the data storage device further stores computer program instructions operable to cause the processor to: identify lineaments as line segments from the set of line segments which fulfil a length threshold.
  • a geographic data processing system according to any one of clauses 11 to 14, wherein the data storage device further stores computer program instructions operable to cause the processor to: extract slope faces from the elevation data by calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
  • a geographic data processing system according to any one of clauses 11 to 15, wherein the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
  • a geographic data processing system according to any one of clauses 11 to 16, wherein the data storage device further stores computer program instructions operable to cause the processor to: analyze the image data to determine a slope cover classification by performing a tile-based image classification on the image data using machine learning.
  • a geographic data processing system comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover. 19.
  • the data storage device further stores computer program instructions operable to cause the processor to: combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area by combining as a weighted average obtained using a scoring matrix.
  • FIG.1 shows an overview of the processing carried out in embodiments of the present invention
  • FIG.2 is a block diagram showing a geographic data processing system according to an embodiment of the present invention.
  • FIG.4A to FIG.4C show an image processing method of determining a lineament intersection hazard score according to an embodiment of the present invention
  • FIG.5A to FIG.5C show sample image tiles for classification of ground cover in an embodiment of the present invention
  • FIG.6 is a table showing a comparison of predicted ground cover classification using a model according to an embodiment of the present invention with actual ground cover classification
  • FIG.7A and FIG.7B show a comparison of predicted slope cover with historical report data
  • FIG.8 is table showing a scoring matrix used to combine hazard scores to determine a geohazard risk score in an embodiment of the present invention
  • FIG.9 is a table showing hazard scores and hazard ratings according to an embodiment of the present invention.
  • the present disclosure relates to the autonomous quantification of geohazard risk using data collected by low-altitude aircrafts or drones.
  • Digital elevation map (DEM) data derived from LIDAR and orthophotos which are remote sensing images of the Earth’s surface taken in the visible spectrum post-processed and stitched together into geo-referenced images.
  • FIG.1 shows an overview of the processing carried out in embodiments of the present invention.
  • geospatial calculations 10 comprising slope angle calculation 12, slope height calculation 14 and flow accumulation 16 are carried out
  • the slope angle calculation 12 determines a measure of the steepness of land elevation.
  • the slope height calculation 14 determines a measure of the height of individual slopes from the toe of the slope to the top of the slope.
  • the flow accumulation calculation 16 determines a measure of the potential drainage from rainfall.
  • Computer vision processing 20 determines a measure of lineament intersection 22.
  • the lineament intersection 22 is a measure of slopes intersected by lineaments. Slopes intersected by lineaments are less stable and therefore are considered high risk.
  • Deep learning processing 30 is used to provide a slope cover classification 32.
  • the slope cover is classified as one of barren ground, partial land cover and full land cover. Slopes with vegetation cover are more stable against earth movements and are therefore lower risk.
  • the results of the slope angle calculation 12, the slope height calculation 14, the flow accumulation 16, the lineament intersection 22 and the slope cover classification 32 are combined to give a geohazard score 40 for an area.
  • FIG.2 shows a geographic data processing system according to an embodiment of the present invention.
  • the geographic data processing system 100 is a computer system with memory that stores computer program modules which implement geographic data processing methods according to embodiments of the present invention.
  • the geographic data processing system 100 comprises a processor 110, a working memory 112, an input interface 114, a user interface 116, an output interface 118, program storage 120 and data storage 140.
  • the processor 110 may be implemented as one or more central processing unit (CPU) chips.
  • the program storage 120 is a non-volatile storage device such as a hard disk drive which stores computer program modules. The computer program modules are loaded into the working memory 112 for execution by the processor 110.
  • the input interface 114 is an interface which allows data, such as image data and digital elevation map (DEM) data to be received by the geographic data processing system 100.
  • the input interface 114 may be a wireless network interface such as a Wi-Fi or Bluetooth interface, alternatively it may be a wired interface.
  • the user interface 116 allows a user of the geographic data processing system 100 to input selections and commands and may be implemented as a graphical user interface.
  • the output interface 118 outputs data and may be implemented as a display or a data interface.
  • the program storage 120 stores a geospatial risk score calculation module 122, a lineament intersection risk score calculation module 124, a slope cover risk score calculation module 126, and a geohazard risk score calculation module 128.
  • the computer program modules cause the processor 110 to execute various geographic data processing which is described in more detail below.
  • the program storage 120 may be referred to in some contexts as computer readable storage media and/or non- transitory computer readable media.
  • the computer program modules are distinct modules which perform respective functions implemented by the geographic data processing system 100. It will be appreciated that the boundaries between these modules are exemplary only, and that alternative embodiments may merge modules or impose an alternative decomposition of functionality of modules.
  • modules discussed herein may be decomposed into sub-modules to be executed as multiple computer processes, and, optionally, on multiple computers.
  • alternative embodiments may combine multiple instances of a particular module or sub-module.
  • software implementation of the computer program modules is described herein, these may alternatively be implemented as one or more hardware modules (such as field- programmable gate array(s) or application-specific integrated circuit(s)) comprising circuitry which implements equivalent functionality to that implemented in software.
  • FIG.3 is a flow chart showing method of processing geographic data to of processing geographic data to assess geohazard risk according to an embodiment of the present invention.
  • the method 300 shown in FIG.3 is carried out by the geographic data processing system 100 shown in FIG.2.
  • the geographic data processing system 100 receives elevation data and image data for the geographic area being assessed.
  • the elevation data and the image data may be received by the input interface 114 of the geographic data processing system 100.
  • the elevation data may comprise a digital elevation map compiled from LIDAR scans of the geographic area.
  • the image data may comprise geo-referenced orthophotos. Orthophotos are remote sensing images of the earth's surface taken using the spectrum of visible light, post-processed and stitched into geo-referenced images.
  • the geospatial risk score calculation module 122 is executed by the processor 110 of the geographic data processing system 100 to calculate geohazard hazard scores.
  • Geospatial calculations are carried out to quantify geohazard risk factors, including but not limited to slope height, flow accumulation, and slope angle.
  • the slope height is calculated in meters areas may be allocated according to the range of slope heights into which they fall, for example less than 10m; 10m to 20m; 20m to 35m; 35m to 60m; and greater than 60m.
  • the flow accumulation is calculated in square meters and may be grouped as follows: less than 50; 50 to 100; 100 to 200; 200 to 500; 500 to 1000; 1000 to 2000; and greater than 2000.
  • the slope angle is a measure of steepness of land elevation and may be calculated in degrees. The slope angle may be grouped as follows: less than 15 degrees; 15 to 25 degrees; 25 to 40 degrees; 40 to 60 degrees; and greater than 60 degrees.
  • step 306 the lineament intersection risk score calculation module 124 is executed by the processor 110 of the geographic data processing system 100 to calculate a lineament intersection hazard score.
  • lineaments are extracted from the DEM data.
  • FIG.4A is an image showing the extraction of lineaments in an embodiment of the present invention.
  • the digital elevation map (DEM) data is pre-processed with the hillshading algorithm.
  • canny edge detection is implemented on the hillshade map.
  • Probabilistic Hough Lines Transform is applied to extract vectorized lines from the edge detection output.
  • Post-processing is then applied to remove line segments that do not fulfill a length threshold.
  • slope faces are extracted.
  • FIG.4B is an image showing slope face extraction in an embodiment of the present invention. Slope face aspect per pixel is calculated from the DEM data. The slope faces are sorted into the closest ordinal and cardinal directions. Slope faces are then segmented by grouping similar neighboring pixels. A blob detection algorithm is used to group the pixels to form slope faces.
  • FIG.4C is an image showing slopelineament intersection identification in an embodiment of the present invention. Slope faces which intersect lineaments are highlighted in FIG.4C. The lineament intersection hazard score is calculated from the number of lineament intersections in an area.
  • the slope cover risk score calculation module 126 is executed by the processor 110 of the geographic data processing system 100 to calculate a slope cover hazard score.
  • Tiles of the orthophotos are classified into one of a plurality of slope cover classifications using a classifier.
  • the classifier may be a convolutional neural network classifier.
  • the classifier may be trained to classify tiles as one of full land cover; partial land cover; and barren land cover.
  • the training and testing of the model is carried out using manually labeled test data tiles.
  • FIG.5A shows sample tiles with full land cover.
  • FIG.5B shows example tiles with barren land cover.
  • FIG.5C shows example tiles with partial land cover.
  • FIG.6 is a table showing the confusion matrix of predicted land cover classifications from a classifier according to an embodiment compared with actual land cover classifications. As shown in the table, the model classifies a large majority of forest cover (full cover) and barren cover correctly. Approximately 2/3 of partial ground cover is correctly classified by the model with the remaining 1/3 misclassified as full cover or barren ground.
  • FIG.7A shows a predicted slope cover predictions using a classifier according to an embodiment of the present invention and FIG.7B shows manually labeled slope cover for the same geographical areas.
  • the classifier provides results that are generally consistent with the manually labeled data.
  • the geohazard risk score calculation module 128 is executed by the processor 110 of the geographic data processing system 100 to combine the hazard scores to determine a geohazard risk score for the geographic area.
  • the geohazard risk score is calculated as a weighted average using a scoring matrix obtained via painvise comparison.
  • FIG.8 is a table showing an example scoring matrix according to an embodiment of the present invention. Elements of the scoring matrix are determined from the input used in the geohazard risk methodology. For each input, it is paired against every other input to decide which one of the pair is considered more important (i.e. contributes more) to geohazard risk. If both pairs are equally important, they are given a rating of 1. If one of the pairs is more important, the more important input is given a rating of 2, while the other input is given a rating of 0.5. These ratings are then summed up for each input as the weightage for averaging.
  • the final geohazard score is determined using the scoring matrix, by combining the individual risk scores obtained from the processing of each input, using the weights determined from the scoring matrix.
  • each pixel in the image data is assigned a final geohazard score using this procedure.
  • FIG.9 is a table showing hazard scores and hazard ratings according to an embodiment of the present invention. As shown in FIG.9, the scores for each pixel may be expressed according to a hazard rating of very low, low, medium, high or very high depending on the score. In addition, the hazard score may be displayed on a map as color-coded hazard ratings for communication to the end user.

Abstract

Geographic data processing methods and systems for assessing geohazard risk are disclosed. A geographic data processing method for assessing geohazard risk comprises: receiving elevation data and image data for a geographic area; performing geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extracting lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyzing the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.

Description

GEOGRAPHIC DATA PROCESSING METHODS AND SYSTEMS FOR
ASSESSING GEOHAZARD RISK
TECHNICAL FIELD
The present disclosure relates to geographic data processing methods and systems. In particular, the present disclosure relates to methods and systems for assessing risk due to geological features and environmental conditions.
BACKGROUND
Failures due to soil movement and slope erosion can potentially cause major risks to assets such as pipelines. Such assets can be located in remote and mountainous regions which are difficult for personnel to access.
On top of ground patrolling, helicopter and autonomous drone surveillance have been widely used for pipeline aerial inspection and monitoring of and geohazard threats. The data produced from these inspections are in the forms of aerial photos and videos. However, this has resulted massive datasets which were then manually analysed to identify the threats captured along the pipeline length. The processes are time consuming and costly due to manual interpretation involving massive datasets, many resources and prone to human error during data analysis.
SUMMARY
According to a first aspect of the present disclosure a geographic data processing method for assessing geohazard risk is provided. The method comprises: receiving elevation data and image data for a geographic area; performing geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extracting lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyzing the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
In an embodiment, extracting lineaments from the elevation data comprises applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
In an embodiment the method further comprises applying line extraction to the detected edges in the hillshade map to obtain a set of line segments.
In an embodiment, the method further comprises identifying lineaments as line segments from the set of line segments which fulfil a length threshold.
In an embodiment, extracting slope faces from the elevation data comprises calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
In an embodiment, the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
In an embodiment, analyzing the image data to determine a slope cover classification comprises performing a tile-based image classification on the image data using machine learning.
In an embodiment, the tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
In an embodiment, combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area comprises combining as a weighted average obtained using a scoring matrix.
According to a second aspect of the present disclosure a computer readable medium storing processor executable instructions which when executed on a processor cause the processor to carry out a method as set out above is provided.
According to a third aspect of the present disclosure, a geographic data processing system for assessing geohazard risk is provided. The geographic data processing system comprises: a processor and a data storage device storing computer program instructions operable to cause the processor to: perform geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extract lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyze the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
In an embodiment, wherein the data storage device further stores computer program instructions operable to cause the processor to: extract lineaments from the elevation data by applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
In an embodiment, the data storage device further stores computer program instructions operable to cause the processor to: apply line extraction to the detected edges in the hillshade map to obtain a set of line segments.
In an embodiment, the data storage device further stores computer program instructions operable to cause the processor to: identify lineaments as line segments from the set of line segments which fulfil a length threshold. In an embodiment, the data storage device further stores computer program instructions operable to cause the processor to: extract slope faces from the elevation data by calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect.
In an embodiment, the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
In an embodiment, the data storage device further stores computer program instructions operable to cause the processor to: analyze the image data to determine a slope cover classification by performing a tile-based image classification on the image data using machine learning.
In an embodiment, wherein the tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
In an embodiment, the data storage device further stores computer program instructions operable to cause the processor to: combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area by combining as a weighted average obtained using a scoring matrix.
Further embodiments of the present invention are set out in the following clauses:
1. A geographic data processing method for assessing geohazard risk, the method comprising: receiving elevation data and image data for a geographic area; performing geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extracting lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyzing the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
2. A method according to clause 1, wherein extracting lineaments from the elevation data comprises applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
3. A method according to clause 2, further comprising applying line extraction to the detected edges in the hillshade map to obtain a set of line segments.
4. A method according to clause 3, further comprising identifying lineaments as line segments from the set of line segments which fulfil a length threshold.
5. A method according to any preceding clause, wherein extracting slope faces from the elevation data comprises calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
6. A method according to any preceding clause, wherein the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
7. A method according to any preceding clause, wherein analyzing the image data to determine a slope cover classification comprises performing a tile-based image classification on the image data using machine learning. 8. A method according to clause 7, wherein the tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
9. A method according to any preceding clause, wherein combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area comprises combining as a weighted average obtained using a scoring matrix.
10. A computer readable medium storing processor executable instructions which when executed on a processor cause the processor to carry out a method according to any one of clauses 1 to 9.
11. A geographic data processing system for assessing geohazard risk, the geographic data processing system comprising: a processor and a data storage device storing computer program instructions operable to cause the processor to: perform geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extract lineaments from the elevation data, extracting slope feces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyze the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
12. A geographic data processing system according to clause 11 , wherein the data storage device further stores computer program instructions operable to cause the processor to: extract lineaments from the elevation data by applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
13. A geographic data processing system according to clause 12, wherein the data storage device further stores computer program instructions operable to cause the processor to: apply line extraction to the detected edges in the hillshade map to obtain a set of line segments.
14. A geographic data processing system according to clause 13, wherein the data storage device further stores computer program instructions operable to cause the processor to: identify lineaments as line segments from the set of line segments which fulfil a length threshold.
15. A geographic data processing system according to any one of clauses 11 to 14, wherein the data storage device further stores computer program instructions operable to cause the processor to: extract slope faces from the elevation data by calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
16. A geographic data processing system according to any one of clauses 11 to 15, wherein the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
17. A geographic data processing system according to any one of clauses 11 to 16, wherein the data storage device further stores computer program instructions operable to cause the processor to: analyze the image data to determine a slope cover classification by performing a tile-based image classification on the image data using machine learning.
18. A geographic data processing system according to clause 17, wherein the tilebased image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover. 19. A geographic data processing system according to any one of clauses 11 to 18, wherein the data storage device further stores computer program instructions operable to cause the processor to: combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area by combining as a weighted average obtained using a scoring matrix.
BRIEF DESCRIPTION OF THE DRAWINGS
In the following, embodiments of the present invention will be described as non-limiting examples with reference to the accompanying drawings in which:
FIG.1 shows an overview of the processing carried out in embodiments of the present invention;
FIG.2 is a block diagram showing a geographic data processing system according to an embodiment of the present invention;
FIG.3 is a flow chart showing a method of processing geographic data to assess= geohazard risk according to an embodiment of the present invention;
FIG.4A to FIG.4C show an image processing method of determining a lineament intersection hazard score according to an embodiment of the present invention;
FIG.5A to FIG.5C show sample image tiles for classification of ground cover in an embodiment of the present invention;
FIG.6 is a table showing a comparison of predicted ground cover classification using a model according to an embodiment of the present invention with actual ground cover classification;
FIG.7A and FIG.7B show a comparison of predicted slope cover with historical report data; and FIG.8 is table showing a scoring matrix used to combine hazard scores to determine a geohazard risk score in an embodiment of the present invention; and
FIG.9 is a table showing hazard scores and hazard ratings according to an embodiment of the present invention.
DETAILED DESCRIPTION
The present disclosure relates to the autonomous quantification of geohazard risk using data collected by low-altitude aircrafts or drones. Digital elevation map (DEM) data derived from LIDAR and orthophotos which are remote sensing images of the Earth’s surface taken in the visible spectrum post-processed and stitched together into geo-referenced images.
FIG.1 shows an overview of the processing carried out in embodiments of the present invention. As shown in FIG.1, geospatial calculations 10 comprising slope angle calculation 12, slope height calculation 14 and flow accumulation 16 are carried out The slope angle calculation 12 determines a measure of the steepness of land elevation. The slope height calculation 14 determines a measure of the height of individual slopes from the toe of the slope to the top of the slope. The flow accumulation calculation 16 determines a measure of the potential drainage from rainfall. Computer vision processing 20 determines a measure of lineament intersection 22. The lineament intersection 22 is a measure of slopes intersected by lineaments. Slopes intersected by lineaments are less stable and therefore are considered high risk. Deep learning processing 30 is used to provide a slope cover classification 32. The slope cover is classified as one of barren ground, partial land cover and full land cover. Slopes with vegetation cover are more stable against earth movements and are therefore lower risk. The results of the slope angle calculation 12, the slope height calculation 14, the flow accumulation 16, the lineament intersection 22 and the slope cover classification 32 are combined to give a geohazard score 40 for an area.
FIG.2 shows a geographic data processing system according to an embodiment of the present invention. The geographic data processing system 100 is a computer system with memory that stores computer program modules which implement geographic data processing methods according to embodiments of the present invention.
The geographic data processing system 100 comprises a processor 110, a working memory 112, an input interface 114, a user interface 116, an output interface 118, program storage 120 and data storage 140. The processor 110 may be implemented as one or more central processing unit (CPU) chips. The program storage 120 is a non-volatile storage device such as a hard disk drive which stores computer program modules. The computer program modules are loaded into the working memory 112 for execution by the processor 110. The input interface 114 is an interface which allows data, such as image data and digital elevation map (DEM) data to be received by the geographic data processing system 100. The input interface 114 may be a wireless network interface such as a Wi-Fi or Bluetooth interface, alternatively it may be a wired interface. The user interface 116 allows a user of the geographic data processing system 100 to input selections and commands and may be implemented as a graphical user interface. The output interface 118 outputs data and may be implemented as a display or a data interface.
The program storage 120 stores a geospatial risk score calculation module 122, a lineament intersection risk score calculation module 124, a slope cover risk score calculation module 126, and a geohazard risk score calculation module 128. The computer program modules cause the processor 110 to execute various geographic data processing which is described in more detail below. The program storage 120 may be referred to in some contexts as computer readable storage media and/or non- transitory computer readable media. As depicted in FIG.2, the computer program modules are distinct modules which perform respective functions implemented by the geographic data processing system 100. It will be appreciated that the boundaries between these modules are exemplary only, and that alternative embodiments may merge modules or impose an alternative decomposition of functionality of modules. For example, the modules discussed herein may be decomposed into sub-modules to be executed as multiple computer processes, and, optionally, on multiple computers. Moreover, alternative embodiments may combine multiple instances of a particular module or sub-module. It will also be appreciated that, while a software implementation of the computer program modules is described herein, these may alternatively be implemented as one or more hardware modules (such as field- programmable gate array(s) or application-specific integrated circuit(s)) comprising circuitry which implements equivalent functionality to that implemented in software.
FIG.3 is a flow chart showing method of processing geographic data to of processing geographic data to assess geohazard risk according to an embodiment of the present invention. The method 300 shown in FIG.3 is carried out by the geographic data processing system 100 shown in FIG.2.
In step 302, the geographic data processing system 100 receives elevation data and image data for the geographic area being assessed. The elevation data and the image data may be received by the input interface 114 of the geographic data processing system 100. The elevation data may comprise a digital elevation map compiled from LIDAR scans of the geographic area. The image data may comprise geo-referenced orthophotos. Orthophotos are remote sensing images of the earth's surface taken using the spectrum of visible light, post-processed and stitched into geo-referenced images.
In step 304, the geospatial risk score calculation module 122 is executed by the processor 110 of the geographic data processing system 100 to calculate geohazard hazard scores. Geospatial calculations are carried out to quantify geohazard risk factors, including but not limited to slope height, flow accumulation, and slope angle. The slope height is calculated in meters areas may be allocated according to the range of slope heights into which they fall, for example less than 10m; 10m to 20m; 20m to 35m; 35m to 60m; and greater than 60m. The flow accumulation is calculated in square meters and may be grouped as follows: less than 50; 50 to 100; 100 to 200; 200 to 500; 500 to 1000; 1000 to 2000; and greater than 2000. The slope angle is a measure of steepness of land elevation and may be calculated in degrees. The slope angle may be grouped as follows: less than 15 degrees; 15 to 25 degrees; 25 to 40 degrees; 40 to 60 degrees; and greater than 60 degrees.
In step 306, the lineament intersection risk score calculation module 124 is executed by the processor 110 of the geographic data processing system 100 to calculate a lineament intersection hazard score. First, lineaments are extracted from the DEM data.
FIG.4A is an image showing the extraction of lineaments in an embodiment of the present invention. Initially, the digital elevation map (DEM) data is pre-processed with the hillshading algorithm. Then canny edge detection is implemented on the hillshade map. Probabilistic Hough Lines Transform is applied to extract vectorized lines from the edge detection output. Post-processing is then applied to remove line segments that do not fulfill a length threshold.
Following the extraction of lineaments, slope faces are extracted. FIG.4B is an image showing slope face extraction in an embodiment of the present invention. Slope face aspect per pixel is calculated from the DEM data. The slope faces are sorted into the closest ordinal and cardinal directions. Slope faces are then segmented by grouping similar neighboring pixels. A blob detection algorithm is used to group the pixels to form slope faces.
Then slope-lineament intersections are identified. FIG.4C is an image showing slopelineament intersection identification in an embodiment of the present invention. Slope faces which intersect lineaments are highlighted in FIG.4C. The lineament intersection hazard score is calculated from the number of lineament intersections in an area.
Returning now to FIG.3, in step 308, the slope cover risk score calculation module 126 is executed by the processor 110 of the geographic data processing system 100 to calculate a slope cover hazard score. Tiles of the orthophotos are classified into one of a plurality of slope cover classifications using a classifier. The classifier may be a convolutional neural network classifier. The classifier may be trained to classify tiles as one of full land cover; partial land cover; and barren land cover. The training and testing of the model is carried out using manually labeled test data tiles.
FIG.5A shows sample tiles with full land cover. FIG.5B shows example tiles with barren land cover. FIG.5C shows example tiles with partial land cover. FIG.6 is a table showing the confusion matrix of predicted land cover classifications from a classifier according to an embodiment compared with actual land cover classifications. As shown in the table, the model classifies a large majority of forest cover (full cover) and barren cover correctly. Approximately 2/3 of partial ground cover is correctly classified by the model with the remaining 1/3 misclassified as full cover or barren ground.
FIG.7A shows a predicted slope cover predictions using a classifier according to an embodiment of the present invention and FIG.7B shows manually labeled slope cover for the same geographical areas. As can be seen from comparing FIG.7A and FIG.7B, the classifier provides results that are generally consistent with the manually labeled data.
Returning again to FIG.3, in step 310, the geohazard risk score calculation module 128 is executed by the processor 110 of the geographic data processing system 100 to combine the hazard scores to determine a geohazard risk score for the geographic area. The geohazard risk score is calculated as a weighted average using a scoring matrix obtained via painvise comparison.
FIG.8 is a table showing an example scoring matrix according to an embodiment of the present invention. Elements of the scoring matrix are determined from the input used in the geohazard risk methodology. For each input, it is paired against every other input to decide which one of the pair is considered more important (i.e. contributes more) to geohazard risk. If both pairs are equally important, they are given a rating of 1. If one of the pairs is more important, the more important input is given a rating of 2, while the other input is given a rating of 0.5. These ratings are then summed up for each input as the weightage for averaging.
The final geohazard score is determined using the scoring matrix, by combining the individual risk scores obtained from the processing of each input, using the weights determined from the scoring matrix. Thus, each pixel in the image data is assigned a final geohazard score using this procedure. FIG.9 is a table showing hazard scores and hazard ratings according to an embodiment of the present invention. As shown in FIG.9, the scores for each pixel may be expressed according to a hazard rating of very low, low, medium, high or very high depending on the score. In addition, the hazard score may be displayed on a map as color-coded hazard ratings for communication to the end user.
Whilst the foregoing description has described exemplary embodiments, it will be understood by those skilled in the art that many variations of the embodiments can be made within the scope and spirit of the present invention.

Claims

1. A geographic data processing method for assessing geohazard risk, the method comprising: receiving elevation data and image data for a geographic area; performing geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extracting lineaments from the elevation data, extracting slope faces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyzing the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
2. A method according to claim 1, wherein extracting lineaments from the elevation data comprises applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
3. A method according to claim 2, further comprising applying line extraction to the detected edges in the hillshade map to obtain a set of line segments.
4. A method according to claim 3, further comprising identifying lineaments as line segments from the set of line segments which fulfil a length threshold.
5. A method according to claim 1, wherein extracting slope faces from the elevation data comprises calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect.
6. A method according to claim 1 , wherein the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
7. A method according to claim 1 , wherein analyzing the image data to determine a slope cover classification comprises performing a tile-based image classification on the image data using machine learning.
8. A method according to claim 7, wherein the tile-based image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
9. A method according to claim 1, wherein combining the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area comprises combining as a weighted average obtained using a scoring matrix.
10. A computer readable medium storing processor executable instructions which when executed on a processor cause the processor to carry out a method according to claim 1.
11. A geographic data processing system for assessing geohazard risk, the geographic data processing system comprising: a processor and a data storage device storing computer program instructions operable to cause the processor to: perform geospatial calculations on the elevation data to determine a plurality of geospatial hazard scores for the geographic area; extract lineaments from the elevation data, extracting slope feces from the elevation data, identifying lineament-slope face intersections from the extracted lineaments and the extracted slope faces and determining a lineament intersection hazard score for the geographic area from the identified lineament-slope intersections; analyze the image data to determine a slope cover classification and generating a slope cover hazard score for the geographic area from the slope cover classification; and combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area.
12. A geographic data processing system according to claim 11, wherein the data storage device further stores computer program instructions operable to cause the processor to: extract lineaments from the elevation data by applying a hillshading algorithm to the elevation data to obtain a hillshade map of the geographic area and detecting edges in the hillshade map.
13. A geographic data processing system according to claim 12, wherein the data storage device further stores computer program instructions operable to cause the processor to: apply line extraction to the detected edges in the hillshade map to obtain a set of line segments.
14. A geographic data processing system according to claim 13, wherein the data storage device further stores computer program instructions operable to cause the processor to: identify lineaments as line segments from the set of line segments which fulfil a length threshold.
15. A geographic data processing system according to claim 11, wherein the data storage device further stores computer program instructions operable to cause the processor to: extract slope faces from the elevation data by calculating the slope aspect for pixels of the elevation data and grouping pixels to identify slopes by applying a blob detection algorithm which combines pixels to form slope faces based on the slope aspect
16. A geographic data processing system according to claim 11, wherein the plurality of geospatial hazard scores for the geographic area comprise slope angle, and / or slope height, and / or flow accumulation.
17. A geographic data processing system according to claim 11, wherein the data storage device further stores computer program instructions operable to cause the processor to: analyze the image data to determine a slope cover classification by performing a tile-based image classification on the image data using machine learning.
18. A geographic data processing system according to claim 17, wherein the tilebased image classification comprises classifying tiles as one of a set of possible classifications comprising full slope cover, partial slope cover and barren slope cover.
19. A geographic data processing system according to claim 11, wherein the data storage device further stores computer program instructions operable to cause the processor to: combine the plurality of geospatial hazard scores, the lineament intersection hazard score and the slope cover hazard score for the geographic area to determine a geohazard risk score for the geographic area by combining as a weighted average obtained using a scoring matrix.
PCT/MY2022/050072 2021-08-17 2022-08-16 Geographic data processing methods and systems for assessing geohazard risk WO2023022587A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
MYPI2021004708 2021-08-17
MYPI2021004708 2021-08-17

Publications (1)

Publication Number Publication Date
WO2023022587A1 true WO2023022587A1 (en) 2023-02-23

Family

ID=85240834

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MY2022/050072 WO2023022587A1 (en) 2021-08-17 2022-08-16 Geographic data processing methods and systems for assessing geohazard risk

Country Status (1)

Country Link
WO (1) WO2023022587A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117190974A (en) * 2023-09-08 2023-12-08 中国地质调查局西安地质调查中心(西北地质科技创新中心) Slope height calculation method of geological disaster slope unit

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120044106A1 (en) * 2009-03-04 2012-02-23 Eni S.P.A. Apparatus and method for measuring spatial movements of plant structures
JP2019201275A (en) * 2018-05-15 2019-11-21 国際航業株式会社 Monitoring system
US20200193589A1 (en) * 2018-12-10 2020-06-18 The Climate Corporation Mapping field anomalies using digital images and machine learning models
KR102281829B1 (en) * 2020-10-08 2021-07-23 산림조합중앙회 Method for Evaluating Risk of Slope Collapse Using Shooting Video Image of Unmanned Aerial Vehicle and State Information of Upper Natural Slope, and Medium Being Recorded with Program for Executing the Method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120044106A1 (en) * 2009-03-04 2012-02-23 Eni S.P.A. Apparatus and method for measuring spatial movements of plant structures
JP2019201275A (en) * 2018-05-15 2019-11-21 国際航業株式会社 Monitoring system
US20200193589A1 (en) * 2018-12-10 2020-06-18 The Climate Corporation Mapping field anomalies using digital images and machine learning models
KR102281829B1 (en) * 2020-10-08 2021-07-23 산림조합중앙회 Method for Evaluating Risk of Slope Collapse Using Shooting Video Image of Unmanned Aerial Vehicle and State Information of Upper Natural Slope, and Medium Being Recorded with Program for Executing the Method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ŠILHAVý JAKUB; MINáR JOZEF; MENTLíK PAVEL; SLáDEK JáN: "A new artefacts resistant method for automatic lineament extraction using Multi-Hillshade Hierarchic Clustering (MHHC)", COMPUTERS & GEOSCIENCES, PERGAMON, AMSTERDAM, NL, vol. 92, 31 March 2016 (2016-03-31), AMSTERDAM, NL , pages 9 - 20, XP029532751, ISSN: 0098-3004, DOI: 10.1016/j.cageo.2016.03.015 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117190974A (en) * 2023-09-08 2023-12-08 中国地质调查局西安地质调查中心(西北地质科技创新中心) Slope height calculation method of geological disaster slope unit

Similar Documents

Publication Publication Date Title
CN110287932B (en) Road blocking information extraction method based on deep learning image semantic segmentation
US10015360B1 (en) Image-based field boundary detection and identification
CN107835997B (en) Vegetation management for powerline corridor monitoring using computer vision
CN107735794B (en) Condition detection using image processing
Huang et al. A multidirectional and multiscale morphological index for automatic building extraction from multispectral GeoEye-1 imagery
US8233712B2 (en) Methods of segmenting a digital image
US9619711B2 (en) Multi-spectral image labeling with radiometric attribute vectors of image space representation components
Pádua et al. Vineyard properties extraction combining UAS-based RGB imagery with elevation data
Yue et al. Texture extraction for object-oriented classification of high spatial resolution remotely sensed images using a semivariogram
Shahi et al. Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery
Gašparović Urban growth pattern detection and analysis
WO2023022587A1 (en) Geographic data processing methods and systems for assessing geohazard risk
Weidner et al. An algorithm for measuring landslide deformation in terrestrial lidar point clouds using trees
Csendes et al. Identification and spectral evaluation of agricultural crops on hyperspectral airborne data
Arvind et al. Flood assessment using multi-temporal MODIS satellite images
CN116561536B (en) Landslide hidden danger identification method, terminal equipment and medium
JP6060377B2 (en) Image cluster analyzer
CN103955914A (en) SAR image segmentation method based on random projection and Signature/EMD framework
Dakir et al. Automatic extraction of dunes from Google Earth images New approach to study the dunes migration in the LAÂYOUNE city of Morocco
Storch et al. Detecting Historical Terrain Anomalies With UAV-LiDAR Data Using Spline-Approximation and Support Vector Machines
Van Den Eeckhaut et al. Identification of vegetated landslides using only a lidar-based terrain model and derivatives in an object-oriented environment
Kim et al. Application of data mining technique to complement photogrammetric roughness data
Musleh et al. Comparative analysis of feature extraction and pixel-based classification of high-resolution satellite images using geospatial techniques
CN117171533B (en) Real-time acquisition and processing method and system for geographical mapping operation data
Torsvik et al. Detection of macroplastic on beaches using drones and object-based image analysis

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22858821

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE