CN115035340B - Remote sensing image classification result verification method - Google Patents

Remote sensing image classification result verification method Download PDF

Info

Publication number
CN115035340B
CN115035340B CN202210661165.8A CN202210661165A CN115035340B CN 115035340 B CN115035340 B CN 115035340B CN 202210661165 A CN202210661165 A CN 202210661165A CN 115035340 B CN115035340 B CN 115035340B
Authority
CN
China
Prior art keywords
remote sensing
sensing image
classification
boundary
area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210661165.8A
Other languages
Chinese (zh)
Other versions
CN115035340A (en
Inventor
陈云坪
路创江
杨玥
陈彦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Electronic Science and Technology of China
Original Assignee
University of Electronic Science and Technology of China
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 University of Electronic Science and Technology of China filed Critical University of Electronic Science and Technology of China
Priority to CN202210661165.8A priority Critical patent/CN115035340B/en
Publication of CN115035340A publication Critical patent/CN115035340A/en
Application granted granted Critical
Publication of CN115035340B publication Critical patent/CN115035340B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06V10/764—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; 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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a remote sensing image classification result verification method, which utilizes a remote sensing image classification technology to classify remote sensing image data, extracts classification boundary lines of a target landform and other areas in the remote sensing image according to the remote sensing image classification result, samples and selects a plurality of boundary investigation pre-selected points on the extracted classification boundary lines, and ground personnel performs investigation at the boundary investigation pre-selected points to obtain actual boundary point coordinates between the target landform and other areas, calculates the vector distance between each actual boundary point and the corresponding nearest boundary point, constructs a vector distance sequence, adopts T-test to test the difference significance of the vector distance sequence and 0 value, if the result is not significant, the remote sensing image classification result is accurate, otherwise, the classification result is inaccurate. According to the invention, boundary sample information is considered, and the verification of the classification effect of the remote sensing image is realized by combining T-test.

Description

Remote sensing image classification result verification method
Technical Field
The invention belongs to the technical field of remote sensing application, and particularly relates to a remote sensing image classification result verification method.
Background
The classification result of the remote sensing image is widely applied to important fields such as natural disaster damage assessment, planting area estimation, land resource monitoring and the like, and the accuracy of the classification result of the remote sensing image is an important precondition of whether remote sensing information is available. Therefore, verification and precision evaluation are required to be carried out on the classification result of the remote sensing image, namely whether the classification result is accurate or not is judged through more accurate reference data.
At present, the verification and precision evaluation of the remote sensing image classification result mainly comprises the steps of selecting sample (pixel) points with determined positions in a remote sensing image classification result area, obtaining the real ground object category of the sample (pixel) points, and calculating the accuracy of the classification result by constructing a confusion matrix and calculating related evaluation indexes such as kappa coefficient, accuracy rate, recall rate and the like.
Often, the overall classification effect is evaluated based on the evaluation index of the confusion matrix, and it is difficult to give the classification effect of a single class, which is insufficient to meet the requirements of users in some practical applications. In addition, the method often ignores a plurality of boundary sample information, and particularly under the condition that the number of samples in each category is unbalanced, the classification effect cannot be well evaluated.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a remote sensing image classification result verification method which considers boundary sample information and combines T-test detection to realize verification of remote sensing image classification effect.
In order to achieve the above object, the remote sensing image classification result verification method of the present invention comprises the following steps:
s1: acquiring a remote sensing image of a target area, and classifying remote sensing image data by utilizing a remote sensing image classification technology to obtain a classification result;
S2: extracting classification boundary lines of the target landform and other areas from the remote sensing image according to the remote sensing image classification result obtained in the step S1, sampling and selecting a plurality of boundary investigation pre-selection points on the extracted classification boundary lines, and recording position coordinate information of each boundary investigation pre-selection point;
S3: according to the position coordinate information of the boundary investigation pre-selected point obtained in the step S2, the ground on-site investigation personnel go to the corresponding position to conduct investigation, and the actual demarcation point coordinates between the target landform and other areas at the boundary investigation pre-selected point are recorded;
s4: for each actual demarcation point obtained in step S3, extracting the closest demarcation point from the classification boundary line in turn, and then calculating the vector distance between the actual demarcation point and the corresponding closest demarcation point, wherein the calculation formula is as follows:
wherein, P (x 1,y1) represents an actually measured demarcation point, P '(x 2,y2) represents a closest demarcation point extracted from the classification boundary line, d (P, P') represents a vector euclidean distance between the actual demarcation point and the closest demarcation point, ρ is a weight value, if the actually measured demarcation point P is within the classification region of the target landform ρ= -1, otherwise ρ=1;
vector distances corresponding to all actually measured demarcation points form a vector distance sequence;
s5: the difference significance between the vector distance sequence obtained in the step S4 and the value 0 is checked by adopting a T-test, if the result is not significant, the remote sensing image classification result is indicated to be accurate, the step S6 is entered, otherwise, the classification result is indicated to be inaccurate, and the verification is ended;
s6: the method for estimating the value range of the area of the target landform area comprises the following steps:
obtaining the length L of a target landform classification boundary line and the area S of a target landform area according to a remote sensing image classification result; calculating average vector distance from vector distance sequence The unit pixel error area s is calculated by adopting the following formula:
Wherein, gamma represents the resolution of the remote sensing image;
And then the error total area delta S is calculated by adopting the following formula:
ΔS＝L/γ×s
If it is The range of the target landform area is [ S, S+DeltaS ], otherwise the range of the target landform area is [ S-DeltaS, S ].
The invention relates to a remote sensing image classification result verification method, which utilizes a remote sensing image classification technology to classify remote sensing image data, extracts classification boundary lines of a target landform and other areas in the remote sensing image according to the remote sensing image classification result, samples and selects a plurality of boundary investigation pre-selected points on the extracted classification boundary lines, and ground personnel performs investigation at the boundary investigation pre-selected points to obtain actual demarcation point coordinates between the target landform and other areas, calculates the vector distance between each actual demarcation point and the corresponding closest demarcation point, constructs a vector distance sequence, adopts the difference significance of a T-test vector distance sequence and 0 value, and if the result is not significant, the remote sensing image classification result is accurate, otherwise, the classification result is inaccurate.
The invention has the following technical effects:
1) The accuracy of the remote sensing classification result is judged by the T-test method, the defect that the confusion matrix method can only evaluate the overall classification effect of the classifier is overcome, and the overall classification effect or the classification effect of a single class can be given according to requirements.
2) The invention can calculate the unit error area according to the resolution ratio of the remote sensing image and the average vector distance on the basis of the accuracy judgment of the remote sensing classification result, further gives the value range of the target landform area by calculating the total error area, and can provide reference and technical guidance for the estimation of the target landform area in other applications.
Drawings
FIG. 1 is a flowchart of a remote sensing image classification result verification method according to an embodiment of the present invention;
FIG. 2 is a remote sensing image before a fire in the investigation region in the present embodiment;
FIG. 3 is a remote sensing image of the investigation region after a fire has occurred in the present embodiment;
FIG. 4 is a classification boundary line diagram of the fire area of the present embodiment;
Fig. 5 is a distribution diagram of actual demarcation points in the present embodiment.
Detailed Description
The following description of the embodiments of the invention is presented in conjunction with the accompanying drawings to provide a better understanding of the invention to those skilled in the art. It is to be expressly noted that in the description below, detailed descriptions of known functions and designs are omitted here as perhaps obscuring the present invention.
Examples
FIG. 1 is a flowchart of a remote sensing image classification result verification method according to an embodiment of the present invention. As shown in fig. 1, the method for verifying the classification result of the remote sensing image according to the present invention comprises the following specific steps:
S101: remote sensing image classification:
and acquiring a remote sensing image of the target area, and classifying the remote sensing image data by utilizing a remote sensing image classification technology to obtain a classification result. The remote sensing images can be preprocessed before classification, so that noise influence is removed, and classification result accuracy is improved.
S102: extracting boundary lines of classification results and designating boundary investigation pre-selected points:
And (3) extracting classification boundary lines of the target landform and other areas according to the remote sensing image classification result obtained in the step (S101), sampling and selecting a plurality of boundary investigation pre-selection points on the extracted classification boundary lines, and recording position coordinate information of each boundary investigation pre-selection point. In order to make the sample points more representative, the boundary survey pre-selected points are preferably uniformly distributed on the classification boundary line, and the number of the boundary survey pre-selected points should be as large as possible in consideration of the manual survey workload.
S103: actual demarcation point survey on the ground:
and (3) according to the position coordinate information of the boundary investigation pre-selected point obtained in the step (S102), the ground on-site investigation personnel go to the corresponding position to conduct investigation, and the actual demarcation point coordinates between the target landform and other areas at the boundary investigation pre-selected point are recorded.
S104: calculating a vector distance sequence:
For each actual demarcation point obtained in step S103, extracting the closest demarcation point from the classification boundary in turn, and then calculating the vector distance between the actual demarcation point and the corresponding closest demarcation point, wherein the calculation formula is as follows:
Wherein, P (x 1,y1) represents an actually measured demarcation point, P '(x 2,y2) represents a corresponding closest demarcation point on the classification boundary line, d (P, P') represents a vector distance between the actual demarcation point and the closest demarcation point, ρ is a weight value, if the actually measured demarcation point P is in the classification region of the target feature (the actually measured demarcation point P is an internal point) ρ= -1, otherwise (the actually measured demarcation point P is an external point) ρ = 1. The vector distance in the invention is different from the conventional Euclidean distance, and the direction is added, so that the deviation between the actual demarcation point and the classification boundary line can be better represented.
And forming vector distance sequences by the vector distances corresponding to all the actually measured demarcation points.
S105: t-test:
The difference significance between the vector distance sequence obtained in the step S104 and the value 0 is checked by adopting a T-test, and the larger the obtained P value is, the higher the classification result accuracy of the remote sensing image is, so that whether the classification result of the remote sensing image is accurate or not can be judged through the P value, if the result is not significant, the classification result of the remote sensing image is accurate, the step S106 is entered, otherwise, the classification result is inaccurate, and the verification is finished.
S106: target landform area assessment:
When the T-test judges that the remote sensing image classification result is accurate, the area of the target landform area can be estimated, and a value range is provided, and the specific method is as follows:
And obtaining the length L of the target landform classification boundary line and the target landform area S according to the remote sensing image classification result. Calculating average vector distance from vector distance sequence The unit pixel error area s is calculated by adopting the following formula:
wherein, gamma represents the resolution of the remote sensing image.
And then the error total area delta S is calculated by adopting the following formula:
ΔS＝L/γ×s
If it is The range of the target landform area is [ S, S+DeltaS ], otherwise the range of the target landform area is [ S-DeltaS, S ].
In order to better illustrate the technical effects of the invention, the invention is experimentally verified by adopting a specific example. The research area of the embodiment is Lushan area of Liangshan Zhouzhou in Sichuan Wenchang city, and is a forest fire high-rise area. And when the year 2020 is 3,30 and 15, forest fires are sudden in the research area, and huge personnel and property losses are caused. Fig. 2 is a remote sensing image before a fire occurs in the investigation region in the present embodiment. Fig. 3 is a remote sensing image of the investigation region after a fire has occurred in the present embodiment. Firstly, classifying remote sensing image data by utilizing a remote sensing image classification technology to obtain a classification result, and then extracting classification boundary lines of an overfire area and other areas. Fig. 4 is a classification boundary line diagram of the fire area of the present embodiment. And selecting boundary investigation pre-selection points on the classification boundary lines, in the embodiment, selecting 15 boundary investigation pre-selection points, enabling ground on-site investigation personnel to go to corresponding positions by using a high-precision GPS handheld instrument, and recording actual boundary point coordinates between the ground surface fire passing area and the non-fire passing area. Fig. 5 is a distribution diagram of actual demarcation points in the present embodiment. Then, calculating a vector distance sequence and performing T-test, wherein the P value obtained by the T-test in the embodiment is 0.890, the result is not obvious, namely, no obvious difference exists between the vector distance and 0, and the classification result of the fire passing area in the remote sensing image can be considered to be accurate.
Because the classification of the overfire area is accurate, the value range of the overfire area can be estimated, and the specific method is as follows:
According to the remote sensing image classification result, the length L of the classification boundary line of the fire passing area is 87.1 km, and the estimated value of the fire passing area S is 3049.6 hectares. Calculating average vector distance from vector distance sequence For-0.76 m, and the resolution of the remote sensing image is 10 m in this embodiment, the unit pixel error area s=10× (-0.76) = -7.6 square m can be calculated. Thus, the error total area Δs=871000/10× (-0.76) = -6.6 hectare can be further calculated. Due toTherefore, the value range of the fire passing area is [3043.0, 3049.6] hectare.
While the foregoing describes illustrative embodiments of the present invention to facilitate an understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but is to be construed as protected by the accompanying claims insofar as various changes are within the spirit and scope of the present invention as defined and defined by the appended claims.

Claims (2)

1. The remote sensing image classification result verification method is characterized by comprising the following steps of:
s1: acquiring a remote sensing image of a target area, and classifying remote sensing image data by utilizing a remote sensing image classification technology to obtain a classification result;
S2: extracting classification boundary lines of the target landform and other areas from the remote sensing image according to the remote sensing image classification result obtained in the step S1, sampling and selecting a plurality of boundary investigation pre-selection points on the extracted classification boundary lines, and recording position coordinate information of each boundary investigation pre-selection point;
S3: according to the position coordinate information of the boundary investigation pre-selected point obtained in the step S2, the ground on-site investigation personnel go to the corresponding position to conduct investigation, and the actual demarcation point coordinates between the target landform and other areas at the boundary investigation pre-selected point are recorded;
s4: for each actual demarcation point obtained in step S3, extracting the closest demarcation point from the classification boundary line in turn, and then calculating the vector distance between the actual demarcation point and the corresponding closest demarcation point, wherein the calculation formula is as follows:
wherein, P (x 1,y1) represents an actually measured demarcation point, P '(x 2,y2) represents a closest demarcation point extracted from the classification boundary line, d (P, P') represents a vector euclidean distance between the actual demarcation point and the closest demarcation point, ρ is a weight value, if the actually measured demarcation point P is within the classification region of the target landform ρ= -1, otherwise ρ=1;
vector distances corresponding to all actually measured demarcation points form a vector distance sequence;
S5: the difference significance between the vector distance sequence obtained in the step S104 and the value 0 is checked by adopting a T-test, if the result is not significant, the remote sensing image classification result is indicated to be accurate, the step S6 is entered, otherwise, the classification result is indicated to be inaccurate, and the verification is ended;
s6: the method for estimating the value range of the area of the target landform area comprises the following steps:
obtaining the length L of a target landform classification boundary line and the area S of a target landform area according to a remote sensing image classification result; calculating average vector distance from vector distance sequence The unit pixel error area s is calculated by adopting the following formula:
Wherein, gamma represents the resolution of the remote sensing image;
And then the error total area delta S is calculated by adopting the following formula:
ΔS＝L/γ×s
If it is The range of the target landform area is [ S, S+DeltaS ], otherwise the range of the target landform area is [ S-DeltaS, S ].
2. The method according to claim 1, wherein the boundary investigation pre-selected points in the step S2 are uniformly distributed on the classification boundary line.
CN202210661165.8A 2022-06-13 2022-06-13 Remote sensing image classification result verification method Active CN115035340B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210661165.8A CN115035340B (en) 2022-06-13 2022-06-13 Remote sensing image classification result verification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210661165.8A CN115035340B (en) 2022-06-13 2022-06-13 Remote sensing image classification result verification method

Publications (2)

Publication Number Publication Date
CN115035340A CN115035340A (en) 2022-09-09
CN115035340B true CN115035340B (en) 2024-05-14

Family

ID=83124816

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210661165.8A Active CN115035340B (en) 2022-06-13 2022-06-13 Remote sensing image classification result verification method

Country Status (1)

Country Link
CN (1) CN115035340B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115578607B (en) * 2022-12-08 2023-04-25 自然资源部第三航测遥感院 Method for rapidly extracting coverage range of effective pixels of remote sensing image

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102937574A (en) * 2012-07-20 2013-02-20 北京农业信息技术研究中心 Information extraction method for plant diseases and insect pests based on satellite images
CN104809724A (en) * 2015-04-21 2015-07-29 电子科技大学 Automatic precise registration method for multiband remote sensing images
CN105551028A (en) * 2015-12-09 2016-05-04 中山大学 Method and system for dynamically updating geographic space data based on remote sensing image
WO2017181200A1 (en) * 2016-04-15 2017-10-19 The Regents Of The University Of California Assessment of wound status and tissue viability via analysis of spatially resolved thz reflectometry maps
CN107657262A (en) * 2016-12-30 2018-02-02 航天星图科技（北京）有限公司 A kind of computer automatic sorting Accuracy Assessment
CN109472304A (en) * 2018-10-30 2019-03-15 厦门理工学院 Tree species classification method, device and equipment based on SAR Yu optical remote sensing time series data
CN114549998A (en) * 2021-11-16 2022-05-27 国网浙江省电力有限公司经济技术研究院 Satellite image-based anti-interference evaluation method for photovoltaic potential of roof

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102937574A (en) * 2012-07-20 2013-02-20 北京农业信息技术研究中心 Information extraction method for plant diseases and insect pests based on satellite images
CN104809724A (en) * 2015-04-21 2015-07-29 电子科技大学 Automatic precise registration method for multiband remote sensing images
CN105551028A (en) * 2015-12-09 2016-05-04 中山大学 Method and system for dynamically updating geographic space data based on remote sensing image
WO2017181200A1 (en) * 2016-04-15 2017-10-19 The Regents Of The University Of California Assessment of wound status and tissue viability via analysis of spatially resolved thz reflectometry maps
CN107657262A (en) * 2016-12-30 2018-02-02 航天星图科技（北京）有限公司 A kind of computer automatic sorting Accuracy Assessment
CN109472304A (en) * 2018-10-30 2019-03-15 厦门理工学院 Tree species classification method, device and equipment based on SAR Yu optical remote sensing time series data
CN114549998A (en) * 2021-11-16 2022-05-27 国网浙江省电力有限公司经济技术研究院 Satellite image-based anti-interference evaluation method for photovoltaic potential of roof

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Mapping Burned Areas of Mato Grosso State Brazilian Amazon Using Multisensor Datasets;Yosio Edemir Shimabukuro;《Remote Sensing》;20201121;全文 *
基于卫星遥感的铁路配电网廊道山火易发性评估研究;路创江;《万方数据》;20231002;全文 *
面向对象遥感影像分类的最优分割尺度选择研究;于欢;张树清;孔博;李晓峰;;中国图象图形学报;20100215(02);全文 *

Also Published As

Publication number Publication date
CN115035340A (en) 2022-09-09

Similar Documents

Publication Publication Date Title
CN106295505A (en) State estimating system during pavement usage
CN115035340B (en) Remote sensing image classification result verification method
CN108896021A (en) Method based on aerophotogrammetry data reduction plantation stand structural parameters
CN102012522A (en) Method and device for evaluating seismic acquisition data
CN108801221B (en) Quick and fine dereferencing method for surface mine slope rock mass joint scale based on digital photogrammetry
CN108830317B (en) Rapid and fine evaluation method for joint attitude of surface mine slope rock mass based on digital photogrammetry
CN104406715A (en) Precision evaluation method and system for remote sensing estimation of surface sensible heat/latent heat flux
CN109579827A (en) A kind of magnetic target detection and localization method based on arcuate array
CN114819737B (en) Method, system and storage medium for estimating carbon reserves of highway road vegetation
Hartoyo et al. Carbon stock assessment using forest canopy density mapper in agroforestry land in Berau, East Kalimantan, Indonesia
KR20190124625A (en) Method, apparatus, and system for analyzing vertical distribution of particle material using satellite sensor and surface weather observation
CN113421295A (en) Unmanned aerial vehicle surveying and mapping information acquisition method based on Internet of things and cloud acquisition platform
US6636804B1 (en) Method for associating the features of two geographic databases
CN105116407B (en) A kind of method that vegetation coverage is measured using handheld laser range finder
Shao et al. An explicit index for assessing the accuracy of cover-class areas
CN106501815A (en) A kind of extraterrestrial target orbit maneuver fusion detection method of only Space-based Angle Measured tracking
CN106595472B (en) The precision of Digital Photogrammetric System determines method
Hoppus et al. The status of accurately locating forest inventory and analysis plots using the Global Positioning System
CN114896676A (en) Intelligent monitoring and analyzing system for standardized construction of building engineering based on BIM three-dimensional model
CN109633760B (en) Underground fluid monitoring method based on natural potential equivalent fusion imaging
TWI597405B (en) System and method for monitoring slope with tree displacement
Afti et al. Evaluation of Settlement Space Patterns in Solok City with Remote Sensing
CN104615875A (en) Stable regression method for remote sensing individual tree canopy and forest diameter
CN117932274B (en) Intelligent analysis system and method for on-site investigation information based on big data
Prisley et al. Combining FIA plot data with topographic variables: are precise locations needed?

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant