Maximum Likelihood classification

In Anthropocene, Earth's social-ecological systems are experiencing intense pressure as a result of human-induced resource over-exploitation at a magnitude never seen before. Consequently, land use and cover change (LUCC) dynamics have implications for environment through the resultant land degradation. This study focuses on understanding the spatio-temporal dynamics associated with mining activities in Zambia's Solwezi copper mining district. Landsat-5 (TM), Landsat-8 (OLI and TIRS) satellite images were classified using Supervised Classification and Maximum Likelihood Approach in ERDAS Imagine 2015 for the LUCC detection between 1995 and 2019. The images were categorized into six different classes: water body, mine, agriculture, built-up, barren and forest areas. The results show a rapid reduction of forest cover and water body from 82.32% and 1.88% to 54.14% and 0.47% in 1995 and 2019, respectively. Built-up area on the other hand increased from 2.04% in 1995 to 4.9% in 2019. Mine area increased from 0.02% in 1995 to 1.43% in 2019. Barren and agriculture areas both gradually increased from 8.24% and 5.5% to 19.52% and 19.53% in 1995 and 2019, respectively. Thus, there was progressive LUCC with increase in the mining activities in the study area. The results obtained from this study proffer lessons that will benefit policy and environmental management strategies applicable to mining-dominated landscapes. We suggest that multiple stakeholders make use of such baselines to guide conservation planning and mitigation measures in resource-rich and mining-dominated landscapes.

Abstract: This paper reviews the approach and techniques of Remote Sensing (RS) based crop discrimination and area estimation including single date approach based on maximum likelihood classification as well as hierarchical/growth profile for crop classification. Uniqueness of both optical and microwave data for crop identification in operational scenario in Rabi and Kharif season is presented. In the past two decades, studies on RS based crop inventory of more than 20 crops at various spatial scales (village to national) ...

Different decomposition approaches have been proposed in order to analyse and interpret SAR polarimetric images. These are based either on the complex voltage reflection matrix, like Pauli, or on power reflection matrix, like the covariance or coherency matrix. They produce polarimetric parameters which are appropriate to retrieve information on the scattering process of the target. If the target is distributed, polarimetric parameters are affected by speckle. The objectives of this work are to search and point out the parameters most appropriate for the interpretation of different land uses in a ESAR image; to evaluate Maximum Likelihood (ML) classification results produced by two different polarimetric input sets: the full polarimetric, and the Pauli images; to investigate the most appropriate size of the Lee filter window for polarimetric speckle reduction. Based on the full polarimetric L-band, polarization signatures were extracted and analyzed for four land cover classes: urba...

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images, and different classification algorithms - maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA), and object-based classification (OBC), were explored. The results indicated that a combination of vegetation indices as extra bands into Landsat TM multispectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multispectral bands improved overall classification accuracy by 5.6% and kappa coefficient by 6.25%. Comparis...

Mapping land use/land cover (LULC) and change detection using remote sensing and GIS techniques is an area of interest that has been attracting increasing attention. This paper is an attempt to assess the changes in land use/land cover in some parts of south-western Nigeria over a 16 year period. The study made use of LandSat imageries of 1986 and 2002.

utilizing multi-temporal remote sensing imagery. Halabja city has been facing severe land use/land cover changes following a series of wars beginning with Iraq-Iran war (1980-1988) to the just concluded invasion of Iraq (March 19, 2003 – 2011). In this study, multi-temporal Landsat images (TM) between the years of 1986 and 1990 were used. All images are rectified and registered to Universal Transverse Mercator (UTM), zone 38N and WGS_84 datum. Hybrid classification as a combine of k-Means and Maximum Likelihood Classification (MLC) algorithms were applied to classify the images in five different land cover categories: water body, cultivated area, shrub land, urban area and bare land. Quantitative analysis was conducted by using post-classification change detection technique. The results show an overall accuracy for 1986 and 1990 images are 92.2 % and 96.8 % respectively. During 1986 to 1990 land use / land cover changes a lot with a huge decrease about 40.8 % in cultivated area wher...

Identification of tree crowns from remote sensing requires detailed spectral information and submeter spatial resolution imagery. Traditional pixel-based classification techniques do not fully exploit the spatial and spectral characteristics of remote sensing datasets. We propose a contextual and probabilistic method for detection of tree crowns in urban areas using a Markov random field based super resolution mapping (SRM) approach in very high resolution images. Our method defines an objective energy function in terms of the conditional probabilities of panchromatic and multispectral images and it locally optimizes the labeling of tree crown pixels. Energy and model parameter values are estimated from multiple implementations of SRM in tuning areas and the method is applied in QuickBird images to produce a 0.6m tree crown map in a city of The Netherlands. The SRM output shows an identification rate of 66% and commission and omission errors in small trees and shrub areas. The metho...

Remotely sensed data are essentially used for land cover and vegetation classification. However, classes of interest are often imperfectly separable in the feature space provided by the spectral data. One of the most common attempts to improve image classification is the integration of ancillary data into classification. In this study, an approach for integrating topographic data into land cover classification is presented. Integration is basically through selection of training set in order to provide additional sensitivity to topographical characteristics associated with each land cover class in the study area. Topographic data including elevation, slope and aspect are tested for their correlation with land cover classes and correlated topographic data are used as input. Signatures from topographical data are assumed to represent the topographical preferences of land cover classes and are extracted with respect to the spatial position of spectral signatures from the remotely sensed...