Wang Xiaojing 1 Zhang Yi 2 Zhao Xin 1 Luo Zhidong 3 1 Beijing Datum Technology Development COLTD 2 Beijing Forestry University 3 Monitoring Centre of Soil and Water Conservation Ministry of Water ID: 563161
Download Presentation The PPT/PDF document "Comparative Study of Methods for Automat..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Comparative Study of Methods for Automatic Identification and Extraction of Terraces from High Resolution Satellite Data (China-GF-1)
Wang Xiaojing1,Zhang Yi2,Zhao Xin1 ,Luo Zhidong3
1Beijing Datum Technology Development CO.,LTD.2Beijing Forestry University3Monitoring Centre of Soil and Water Conservation, Ministry of Water Resources
August 2016
wangxiaojing@dtgis.comSlide2
Contents
1
2
3
4
Introduction
Terraces Interpretation
Characteristics
Automatic Identification and
Extraction Method
Results Comparison and Discussion
5
ConclusionsSlide3
1.Introduction
Importance of TerracesEffective measures / Long history / Large area / Heavy investmentApplication of Remote Sensing Technology in Terraces
Lack of new technology-computer automatic identification and extraction of terraces.Issues to be studiedUrgent business needs Research area:Hengshan County 4000km2
Data: China GF-1
satelliteSlide4
2.Terraces Interpretation Characteristics
typegeometryspectrumtexture
boundaryTypical terracefield: certain widthfield ridge: narrow, line features- straight line, arc or closed curvefield: higher reflectivityfield ridge: low reflectivity with dark color
smoothrepeatedly and alternatively
Complicated
near ridge: clear
near hill foot: confused
Atypical terrace
field: narrow
field ridge: cannot be seen
field: higher reflectivity
field ridge: cannot be seen
fuzzy
Same as Typical terrace
Table 2 Terraces Interpretation Characteristics on GF-1 SatelliteSlide5
3.Automatic Identification and Extraction Method of Terraces based on High Resolution SatelliteSlide6
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.1Edge Characteristics Statistics AlgorithmTechnical Route of Edge Characteristics Statistics for Terrace IdentificationSlide7
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.1Edge Characteristics Statistics AlgorithmImage Edge DetectionGF-1 2m/8m Fused Image
Canny Edge Detection ResultFrame ResultSlide8
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.1Edge Characteristics Statistics AlgorithmTerrace Identification and Shape Optimization
Judgement result of sample attribute
Overlapping RS image
Shape OptimizationSlide9
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.2 Template Matching AlgorithmTechnical Route of Template Matching for Terrace IdentificationSlide10
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.2 Template Matching Algorithm
Panchromatic image
Variance Picture of Search Image
Template Selection Picture
Template Scanning Pixel by Pixel Picture
Automatic Identification Effect Picture with Variance Threshold
≤
0.45Slide11
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.3 Fourier Transformation AlgorithmTechnical Route of Terrace Identification by Fourier Transformation AlgorithmSlide12
4.Results Comparison and Discussion
Three Algorithms
AlgorithmOverall Identification AccuracyTypical Terraces Identification AccuracyAtypical Terraces
Identification Accuracy
Edge Characteristics Statistics
55.19%
80.85%
51.34%
Template Matching
95.54%
97.18%
95.38%
Fourier Transformation
91.02%98.59%
90.25%Table 4 Comparison Table of Algorithm AccuracySlide13
4.Results Comparison and Discussion
Edge Characteristics Statistics
Template MatchingFourier Transformation
In accuracy
Completeness
and boundary
OthersSlide14
5.ConclusionsPropose two kinds of new algorithms for automatic identification and extraction of
terraces. Verify one algorithm on large extent area.It has laid basis for temporal and spatial extension of algorithm, to provide technical support for rapid terrace extraction in a large scale.DeficiencyFor further study, more features and vectors, self-adaptive template can be tried.Slide15
Thank You !