Assessment of the area measurement on Cartosat-1 image
The goal of this study was the evaluation of agriculture parcel area measurement accuracy on Cartosat-1 imagery, and the determination of the technical tolerance appropriate for measurement using photointerpretation techniques. A further objective was to find out the influence of image type, land cover or parcel size on the area measurement variability. In our experiment, five independent operators measured 185 parcels, 3 times, on each image. Next, the buffer width, calculated as the difference between measured and reference parcel area, was derived and was the subject of statistical analysis. Prior to verifying the normality of the buffer widths, a detection of anomalous measurements is recommended. This detection of outliers within each group of observations (i.e. parcels) was made using the Jacknife distance test on each type of imagery (Cartosat Aft, Cartosat Fore). Then, the General Linear Model procedure to identify major significant effects and interactions was followed by analysis of variance to ease the interpretation of the variability observed of the area measurement. Finally, two different parameters, reproducibility limit and critical difference, were calculated to make comparison with other sensors like digital aerial orthophoto in this study possible. The repeatability limits gave the acceptability difference between two operators when measuring the same parcel. For orthophoto this value reached 2.86m, on Cartosat-1 5.17m and 8.76m for Aft and Fore image respectively.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Comparison of Segmentation Methods in Remote Sensing for Land Use Land Cover
Land Use Land Cover (LULC) mapping is essential for urban and resource planning, and is one of the key elements in developing smart and sustainable cities.This study evaluates advanced LULC mapping techniques, focusing o…
Semantic segmentation on multi-resolution optical and microwave data using deep learning
Presently, deep learning and convolutional neural networks (CNNs) are widely used in the fields of image processing, image classification, object identification and many more. In this work, we implemented convolutional n…
Deep Learningimage-classificationImage ClassificationMulti-Label Classification+2Comparative analysis of common edge detection techniques in context of object extraction
Edges characterize boundaries and are therefore a problem of practical importance in remote sensing.In this paper a comparative study of various edge detection techniques and band wise analysis of these algorithms in the…
Edge DetectionKi-67 Index Measurement in Breast Cancer Using Digital Image Analysis
Ki-67 is a nuclear protein that can be produced during cell proliferation. The Ki67 index is a valuable prognostic variable in several kinds of cancer. In breast cancer, the index is even routinely checked in many patien…
BinarizationA Theoretical Analysis of Granulometry-based Roughness Measures on Cartosat DEMs
The study of water bodies such as rivers is an important problem in the remote sensing community. A meaningful set of quantitative features reflecting the geophysical properties help us better understand the formation an…