Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps
نویسندگان
چکیده
To improve the accuracy of classification with a small amount of training data, this paper presents a self-learning approach that defines class labels from sequential patterns using a series of past land-cover maps. By stacking past land-cover maps, unique sequence rule information from sequential change patterns of land-covers is first generated, and a rule-based class label image is then prepared for a given time. After the most informative pixels with high uncertainty are selected from the initial classification, rule-based class labels are assigned to the selected pixels. These newly labeled pixels are added to training data, which then undergo an iterative classification process until a stopping criterion is reached. Time-series MODIS NDVI data sets and cropland data layers (CDLs) from the past five years are used for the classification of various crop types in Kansas. From the experiment results, it is found that once the rule-based labels are derived from past CDLs, the labeled informative pixels could be properly defined without analyst intervention. Regardless of different combinations of past CDLs, adding these labeled informative pixels to training data increased classification accuracy and the maximum improvement of 8.34 percentage points in overall accuracy was achieved when using three CDLs, compared to the initial classification result using a small amount of training data. Using more than three consecutive CDLs showed slightly better classification accuracy than when using two CDLs (minimum and maximum increases were 1.56 and 2.82 percentage points, respectively). From a practical viewpoint, using three or four CDLs was the best choice for this study area. Based on these experiment results, the presented approach could be applied effectively to areas with insufficient training data but access to past land-cover maps. However, further consideration should be given to select the optimal number of past land-cover maps and reduce the impact of errors of rule-based labels.
منابع مشابه
Change Detection Gamasiab River Margins in Kermanshah by Comparison Pixel Base and Object Orientd Algorithms
Introduction Land use reflects the interactive characteristics of humans and the environment and describes how human exploitation works for one or more targets on the ground. Land use is usually defined on the basis of human use of the land, with an emphasis on the functional role of land in economic activities. Land use, which is associated with human activity, is undergoing change over time....
متن کاملComparing the Capability of Sentinel 2 and Landsat 8 Satellite Imagery in Land Use and Land Cover Mapping Using Pixel-based and Object-based Classification Methods
Introduction: Having accurate and up-to-date information on the status of land use and land cover change is a key point to protecting natural resources, sustainable agriculture management and urban development. Preparing the land cover and land use maps with traditional methods is usually time and cost consuming. Nowadays satellite imagery provides the possibility to prepare these maps in less ...
متن کاملLand Cover Classification Using IRS-1D Data and a Decision Tree Classifier
Land cover is one of basic data layers in geographic information system for physical planning and environmentalmonitoring. Digital image classification is generally performed to produce land cover maps from remote sensing data,particularly for large areas. In the present study the multispectral image from IRS LISS-III image along with ancillary datasuch as vegetation indices, principal componen...
متن کاملApplication of remote sensing and geographical information system in mapping land cover of the national park
The study was conducted with the objective of mapping landscape cover of Nechsar National park in Ethiopia to produce spatially accurate and timely information on land use and changing pattern. Monitoring provides the planners and decision-makers with required information about the current state of its development and the nature of changes that have occurred. Remote sensing and Geographical Inf...
متن کاملMapping Land Cover Patterns of Gunma Prefecture, Japan, by Using Remote Sensing
A set of land-cover pattern maps for the Gunma Prefecture was produced to help understand and assess the ecological implications of regional spatial patterns. Covering a total area of approximately 6,360 square kilometers, about 77 percent of this area can be regarded as “vegetation cover”. The land cover map was derived from the supervised classification process with the combined use of TM, SP...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Remote Sensing
دوره 9 شماره
صفحات -
تاریخ انتشار 2017