Effects of pre-processing methods on Landsat OLI-8 land cover classification using OBIA and random forests classifier

Abstract The application of Landsat satellite imagery in land cover classification is affected by atmospheric and topographic errors, which have led to the development of different correction methods. In this study, moderate resolution atmospheric transmission (MODTRAN) and dark object subtraction (DOS) atmospheric corrections, and cosine topographic correction were evaluated individually and combined in a heterogeneous landscape in Zambia. These pre-processing methods were tested using a combination of object-based image analysis (OBIA) and Random Forests (RF) non-parametric classifier (hereafter referred to as OBIA-RF). This assessment aimed at understanding the combined effects of different pre-processing methods and the OBIA-RF classification method on the accuracy of Landsat operational land (OLI-8) imagery with different spatial resolutions. Here, we used pansharpened and standard Landsat OLI-8 images with 15 and 30 m spatial resolutions, respectively. The results showed that non pre-processed images reached a classification accuracy of 68% for pansharpened and 66% for standard Landsat OLI-8. Classification accuracy improved to 93% (pansharpened) and 86% (standard) when combined MODTRAN and cosine topographic correction pre-processing were applied. The results highlight the importance of pansharpening, as well as atmospheric and topographic corrections for Landsat OLI-8 imagery, when used as input in OBIA classification with the RF classifier.

[1]  Asamaporn Sitthi,et al.  Topographic Correction of Landsat TM-5 and Landsat OLI-8 Imagery to Improve the Performance of Forest Classification in the Mountainous Terrain of Northeast Thailand , 2017 .

[2]  Anthony G. Vorster,et al.  A survival guide to Landsat preprocessing. , 2017, Ecology.

[3]  V. Salomonson,et al.  Estimating fractional snow cover from MODIS using the normalized difference snow index , 2004 .

[4]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[5]  Chao-Cheng Wu,et al.  Effects of atmospheric correction and pansharpening on LULC classification accuracy using WorldView-2 imagery , 2015 .

[6]  Jindi Wang,et al.  Bayesian Method for Building Frequent Landsat-Like NDVI Datasets by Integrating MODIS and Landsat NDVI , 2016, Remote. Sens..

[7]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[8]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[9]  O. Csillik,et al.  Automated parameterisation for multi-scale image segmentation on multiple layers , 2014, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[10]  Manfred Ehlers,et al.  Multi-sensor image fusion for pansharpening in remote sensing , 2010 .

[11]  Anton J. J. van Rompaey,et al.  he effect of atmospheric and topographic correction methods on land cover lassification accuracy , 2013 .

[12]  Sarah C. Goslee,et al.  Topographic Corrections of Satellite Data for Regional Monitoring , 2012 .

[13]  G. Kroenung,et al.  The SRTM Data Finishing Process and Products , 2006 .

[14]  Shengwei Zhang,et al.  Local and global evaluation for remote sensing image segmentation , 2017 .

[15]  Jie Wang,et al.  Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery , 2014, Remote. Sens..

[16]  Yun Zhang,et al.  A review and comparison of commercially available pan-sharpening techniques for high resolution satellite image fusion , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[17]  J. Roujean,et al.  Estimating PAR absorbed by vegetation from bidirectional reflectance measurements , 1995 .

[18]  P. Chavez.  An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data , 1988 .

[19]  J. G. White,et al.  Aerial Color Infrared Photography for Determining Early In‐Season Nitrogen Requirements in Corn , 2005 .

[20]  Nicholas C. Coops,et al.  Effect of topographic correction on forest change detection using spectral trend analysis of Landsat pixel-based composites , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[21]  Yang Shao,et al.  Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points , 2012 .

[22]  G. Rondeaux,et al.  Optimization of soil-adjusted vegetation indices , 1996 .

[23]  André Stumpf,et al.  bject-oriented mapping of urban trees using Random Forest lassifiers , 2013 .

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  Massimiliano Pittore,et al.  Performance Evaluation of Machine Learning Algorithms for Urban Pattern Recognition from Multi-spectral Satellite Images , 2014, Remote. Sens..

[26]  Andrew J. Dougill,et al.  Floristic composition, species diversity and carbon storage in charcoal and agriculture fallows and management implications in Miombo woodlands of Zambia , 2013 .

[27]  Jay Gao,et al.  Use of normalized difference built-up index in automatically mapping urban areas from TM imagery , 2003 .

[28]  Martha C. Anderson,et al.  Free Access to Landsat Imagery , 2008, Science.

[29]  Clement Atzberger,et al.  Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data , 2012, Remote. Sens..

[30]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[31]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[32]  Abderrahim Nemmaoui,et al.  Performance evaluation of object based greenhouse detection from Sentinel-2 MSI and Landsat 8 OLI data: A case study from Almería (Spain) , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[33]  Thomas R. Loveland,et al.  A review of large area monitoring of land cover change using Landsat data , 2012 .

[34]  John Rogan,et al.  Segmentation of Landsat Thematic Mapper imagery improves buffelgrass (Pennisetum ciliare) pasture mapping in the Sonoran Desert of Mexico , 2012 .

[35]  C. Woodcock,et al.  Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? , 2001 .

[36]  D. Flanders,et al.  Preliminary evaluation of eCognition object-based software for cut block delineation and feature extraction , 2003 .

[37]  P. Chavez.  Image-Based Atmospheric Corrections - Revisited and Improved , 1996 .

[38]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[39]  Zhiming Zhang,et al.  Influence of different topographic correction strategies on mountain vegetation classification accuracy in the Lancang Watershed, China , 2011 .

[40]  A. Gitelson,et al.  Remote sensing of chlorophyll concentration in higher plant leaves , 1998 .

[41]  Daniel Schläpfer,et al.  Aspects of atmospheric and topographic correction of high spatial resolution imagery , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[42]  Dongmei Chen,et al.  Change detection from remotely sensed images: From pixel-based to object-based approaches , 2013 .

[43]  D. King,et al.  Comparison of pixel- and object-based classification in land cover change mapping , 2011 .

[44]  D. Hadjimitsis,et al.  Atmospheric correction for satellite remotely sensed data intended for agricultural applications: Impact on vegetation indices , 2010 .

[45]  Ioannis Z. Gitas,et al.  A performance evaluation of a burned area object-based classification model when applied to topographically and non-topographically corrected TM imagery , 2004 .

[46]  Clement Atzberger,et al.  Object Based Image Analysis and Data Mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas , 2012 .

[47]  Clement Atzberger,et al.  Comparative analysis of different retrieval methods for mapping grassland leaf area index using airborne imaging spectroscopy , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[48]  Hui Zhang,et al.  Image segmentation evaluation: A survey of unsupervised methods , 2008, Comput. Vis. Image Underst..

[49]  V. Caselles,et al.  Mapping burns and natural reforestation using thematic Mapper data , 1991 .

[50]  N. Goel,et al.  Influences of canopy architecture on relationships between various vegetation indices and LAI and Fpar: A computer simulation , 1994 .

[51]  Stéphane Dupuy,et al.  A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM) , 2017, Remote. Sens..

[52]  Justin Morgenroth,et al.  Developments in Landsat Land Cover Classification Methods: A Review , 2017, Remote. Sens..

[53]  Darius Phiri,et al.  The implication of using a fixed form factor in areas under different rainfall and soil conditions for Pinus kesiya in Zambia , 2016 .

[54]  Abderrahim Nemmaoui,et al.  Object-Based Greenhouse Mapping Using Very High Resolution Satellite Data and Landsat 8 Time Series , 2016, Remote. Sens..

[55]  P. Gong,et al.  Reduction of atmospheric and topographic effect on Landsat TM data for forest classification , 2008 .

[56]  Jaco Kemp,et al.  Effect of pan-sharpening multi-temporal Landsat 8 imagery for crop type differentiation using different classification techniques , 2017, Comput. Electron. Agric..

[57]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[58]  G. Birth,et al.  Measuring the Color of Growing Turf with a Reflectance Spectrophotometer1 , 1968 .

[59]  Xiaolin Zhu,et al.  Improving forest aboveground biomass estimation using seasonal Landsat NDVI time-series , 2015 .

[60]  Budiman Minasny,et al.  The role of atmospheric correction algorithms in the prediction of soil organic carbon from Hyperion data , 2017 .

[61]  G. Groom,et al.  Spatial application of Random Forest models for fine-scale coastal vegetation classification using object based analysis of aerial orthophoto and DEM data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[62]  Thomas Blaschke,et al.  A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[63]  Manuel A. Aguilar,et al.  Object-Based Greenhouse Horticultural Crop Identification from Multi-Temporal Satellite Imagery: A Case Study in Almeria, Spain , 2015, Remote. Sens..

[64]  Michael J. Falkowski,et al.  A review of methods for mapping and prediction of inventory attributes for operational forest management , 2014 .

[65]  Gail A. Carpenter,et al.  A Neural Network Method for Mixture Estimation for Vegetation Mapping , 1999 .

[66]  N. Silleos,et al.  Vegetation Indices: Advances Made in Biomass Estimation and Vegetation Monitoring in the Last 30 Years , 2006 .

[67]  David P. Roy,et al.  The global Landsat archive: Status, consolidation, and direction , 2016 .

[68]  Pedro Antonio Gutiérrez,et al.  Object-Based Image Classification of Summer Crops with Machine Learning Methods , 2014, Remote. Sens..