Comparative Study of Methods for A utomatic Identification
Comparative Study of Methods for A utomatic Identification and Extractio n of Terraces from High Resolution S atellite Data (China-GF-1) Wang Xiaojing1,Zhang Yi2,Zhao Xin1 ,Luo Zhidong3 Beijing Datum Technology Development CO.,LTD. 2 Beijing Forestry University 3 Monitoring Centre of Soil and Water Conservation, Ministry of Water Resources 1 [email protected] August 2016 Contents 1 Introduction 2 Terraces Interpretation Characteristics
3 Automatic Identification and Extraction Method 4 Results Comparison and Discussion 5 Conclusions 1.Introduction Importance of Terraces Effective measures / Long history / Large area / Heavy investment Application of Remote Sensing Technology in T erraces
Lack of new technology-computer automatic identification and extraction of terrac es. Issues to be studied Urgent business needs Research area Hengshan County 4000km2 Data: China GF-1 satellite 2.Terraces Interpretation Characteristics Table 2 Terraces Interpretation Characteristics on GF-1 Satellite type geometry spectrum texture boundary
Typical terrace field: certain width field ridge: narrow, line featuresstraight line, arc or closed curve field: higher reflectivity field ridge: low reflectivity with dark color smooth repeatedly 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 3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite 3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite 3.1Edge Characteristics Statistics Algorithm High Resolution RS Image Landuse Data Template Edge Detection
Terrace Template Training Area Selecting Sample size setti ng Template establishment Template Size Template Vector Template Feature Threshold Training Template Scanning Terraces Identifying Statistics of effective edge numbers in sample Shape Optimizing
N Good Results Y Terraces Technical Route of Edge Characteristics Statistics for Terrace Identification 3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite 3.1Edge Characteristics Statistics Algorithm Image Edge Detection GF-1 2m/8m Fused Image Canny Edge Detection Result Frame Result
3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite 3.1Edge Characteristics Statistics Algorithm Terrace Identification and Shape Optimization Shape Optimization Judgement result of sample attribute Overlapping RS image 3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite 3.2 Template Matching Algorithm High Resolution RS Image
Template Selection Template Size Template Vector Template Scanning Variance Value Graph Template Feature Threshold Terraces Identifying Good Results N Y Shape Optimizing Landuse Data
Terraces Technical Route of Template Matching for Terrace Identification 3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite 3.2 Template Matching Algorithm Template Selection Picture Automatic Identification Effect Picture with Variance Threshold0.45 Template Scanning Pixel by Pixel Picture Panchromatic image Variance Picture of Search Image 3.Automatic Identification and Extraction Method of Terraces based on High Resolution Satellite
3.3 Fourier Transformation Algorithm High Resolution RS Image Image Equalization Window Size Selection Fourier Transformation Threshold Setti ng Characteristics Value Calculation Terraces Identification Shape Optimization N Good Results
N Y Results Extraction Land Use Data Results Optimization Terraces Technical Route of Terrace Identification by Fourier Transformation Algorithm 4.Results Comparison and Discussion Three Algorithms TerraceNum berbyAlg orithm Identifica tionAccuracy 100% ActuralTerraceNumber Table 4 Comparison Table of Algorithm Accuracy Algorithm
Fourier Transformation 91.02% 98.59% 90.25% 4.Results Comparison and Discussion In accuracy Completeness and boundary Others Edge Characteristics Statistics Template Matching Fourier Transformation
5.Conclusions Propose two kinds of new algorithms for automatic identificatio n and extraction of terraces. Verify one algorithm on large exte nt area. It has laid basis for temporal and spatial extension of algorithm , to provide technical support for rapid terrace extraction in a la rge scale. Deficiency For further study, more features and vectors, self-adaptive tem plate can be tried. Thank You !
General Motors Mission Statement: "G.M. is a multinational corporation engaged in socially responsible operations, worldwide. It is dedicated to provide products and services of such quality that our customers will receive superior value while our employees and business partners will...
Labor laws are poorly enforced Cheap labor is abundant Local laws prohibit workers from forming independent trade unions Nike's Excuse Don't own factories They only market shoes Sweatshops and Nike Vietnam and Nike There are about 35,000 workers at five...
ASE is providing the science education support for the Global Learning Programme which is funded by the Department for International Development. This activity can be found on the Global Learning Programme . www.glp-e.org.uk, ASE Primary upd8 . primaryupd8.org.uk. and Practical...
(2) It is understood that, at the time a country becomes bound by this Convention, it will be in a position under its domestic law to give effect to the provisions of this Convention. Article 26 of the Rome Convention...
Consistent axes across poster. Results Cont: Minimize use of tables. Difficult to grasp quickly. Use figure legends/captions as text. Put text near figure it's describing ~1 paragraph per image/image group. RUBRIC! RESULTS. Maximal Impact/Points from: