The Experts below are selected from a list of 106128 Experts worldwide ranked by ideXlab platform
Chandra Giri - One of the best experts on this subject based on the ideXlab platform.
-
a land cover map for south and southeast asia derived from spot vegetation data
Journal of Biogeography, 2007Co-Authors: H J Stibig, A S Belward, P S Roy, U Rosalinawasrin, Shefali Agrawal, P K Joshi, Rene Beuchle, Steffen Fritz, S Mubareka, Chandra GiriAbstract:Aim Our aim was to produce a uniform ‘regional’ land-cover map of South and Southeast Asia based on ‘sub-regional’ mapping results generated in the context of the Global Land Cover 2000 project. Location The ‘region’ of tropical and sub-tropical South and Southeast Asia stretches from the Himalayas and the southern border of China in the north, to Sri Lanka and Indonesia in the south, and from Pakistan in the west to the islands of New Guinea in the far east. Methods The regional land-cover map is based on sub-regional digital mapping results derived from SPOT-VEGETATION satellite data for the years 1998–2000. Image processing, digital Classification and thematic mapping were performed separately for the three sub-regions of South Asia, continental Southeast Asia, and insular Southeast Asia. Landsat TM images, field data and existing national maps served as references. We used the FAO (Food and Agriculture Organization) Land Cover Classification System (LCCS) for coding the sub-regional land-cover Classes and for aggregating the latter to a uniform regional legend. A validation was performed based on a systematic grid of sample points, referring to visual interpretation from high-resolution Landsat imagery. Regional land-cover area estimates were obtained and compared with FAO statistics for the categories ‘forest’ and ‘cropland’. Results The regional map displays 26 land-cover Classes. The LCCS coding provided a standardized Class Description, independent from local Class names; it also allowed us to maintain the link to the detailed sub-regional land-cover Classes. The validation of the map displayed a mapping accuracy of 72% for the dominant Classes of ‘forest’ and ‘cropland’; regional area estimates for these Classes correspond reasonably well to existing regional statistics. Main conclusions The land-cover map of South and Southeast Asia provides a synoptic view of the distribution of land cover of tropical and sub-tropical Asia, and it delivers reasonable thematic detail and quantitative estimates of the main land-cover proportions. The map may therefore serve for regional stratification or modelling of vegetation cover, but could also support the implementation of forest policies, watershed management or conservation strategies at regional scales.
Dimitri Ognibene - One of the best experts on this subject based on the ideXlab platform.
-
binary Classification using pairs of minimum spanning trees or n ary trees
Computer Analysis of Images and Patterns, 2019Co-Authors: Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri OgnibeneAbstract:One-Class Classifiers are trained only with target Class samples. Intuitively, their conservative modeling of the Class Description may benefit Classical Classification tasks where Classes are difficult to separate due to overlapping and data imbalance. In this work, three methods leveraging on the combination of one-Class Classifiers based on non-parametric models, Trees and Minimum Spanning Trees Class descriptors (MST_CD) are proposed.
-
binary Classification using pairs of minimum spanning trees or n ary trees
arXiv: Learning, 2019Co-Authors: Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri OgnibeneAbstract:One-Class Classifiers are trained with target Class only samples. Intuitively, their conservative modelling of the Class Description may benefit Classical Classification tasks where Classes are difficult to separate due to overlapping and data imbalance. In this work, three methods are proposed which leverage on the combination of one-Class Classifiers based on non-parametric models, N-ary Trees and Minimum Spanning Trees Class descriptors (MST-CD), to tackle binary Classification problems. The methods deal with the inconsistencies arising from combining multiple Classifiers and with spurious connections that MST-CD creates in multi-modal Class distributions. As shown by our tests on several datasets, the proposed approach is feasible and comparable with state-of-the-art algorithms.
Francesco P Lovergine - One of the best experts on this subject based on the ideXlab platform.
-
translating land cover land use Classifications to habitat taxonomies for landscape monitoring a mediterranean assessment
Landscape Ecology, 2013Co-Authors: Valeria Tomaselli, Panayotis Dimopoulos, Carmela Marangi, Athanasios S Kallimanis, Maria Adamo, Cristina Tarantino, Maria Panitsa, Massimo Terzi, Giuseppe Veronico, Francesco P LovergineAbstract:Periodic monitoring of biodiversity changes at a landscape scale constitutes a key issue for conservation managers. Earth observation (EO) data offer a potential solution, through direct or indirect mapping of species or habitats. Most national and international programs rely on the use of land cover (LC) and/or land use (LU) Classification systems. Yet, these are not as clearly relatable to biodiversity in comparison to habitat Classifications, and provide less scope for monitoring. While a conversion from LC/LU Classification to habitat Classification can be of great utility, differences in definitions and criteria have so far limited the establishment of a unified approach for such translation between these two Classification systems. Focusing on five Mediterranean NATURA 2000 sites, this paper considers the scope for three of the most commonly used global LC/LU taxonomies—CORINE Land Cover, the Food and Agricultural Organisation (FAO) land cover Classification system (LCCS) and the International Geosphere-Biosphere Programme to be translated to habitat taxonomies. Through both quantitative and expert knowledge based qualitative analysis of selected taxonomies, FAO-LCCS turns out to be the best candidate to cope with the complexity of habitat Description and provides a framework for EO and in situ data integration for habitat mapping, reducing uncertainties and Class overlaps and bridging the gap between LC/LU and habitats domains for landscape monitoring—a major issue for conservation. This study also highlights the need to modify the FAO-LCCS hierarchical Class Description process to permit the addition of attributes based on Class-specific expert knowledge to select multi-temporal (seasonal) EO data and improve Classification. An application of LC/LU to habitat mapping is provided for a coastal Natura 2000 site with high Classification accuracy as a result.
H J Stibig - One of the best experts on this subject based on the ideXlab platform.
-
a land cover map for south and southeast asia derived from spot vegetation data
Journal of Biogeography, 2007Co-Authors: H J Stibig, A S Belward, P S Roy, U Rosalinawasrin, Shefali Agrawal, P K Joshi, Rene Beuchle, Steffen Fritz, S Mubareka, Chandra GiriAbstract:Aim Our aim was to produce a uniform ‘regional’ land-cover map of South and Southeast Asia based on ‘sub-regional’ mapping results generated in the context of the Global Land Cover 2000 project. Location The ‘region’ of tropical and sub-tropical South and Southeast Asia stretches from the Himalayas and the southern border of China in the north, to Sri Lanka and Indonesia in the south, and from Pakistan in the west to the islands of New Guinea in the far east. Methods The regional land-cover map is based on sub-regional digital mapping results derived from SPOT-VEGETATION satellite data for the years 1998–2000. Image processing, digital Classification and thematic mapping were performed separately for the three sub-regions of South Asia, continental Southeast Asia, and insular Southeast Asia. Landsat TM images, field data and existing national maps served as references. We used the FAO (Food and Agriculture Organization) Land Cover Classification System (LCCS) for coding the sub-regional land-cover Classes and for aggregating the latter to a uniform regional legend. A validation was performed based on a systematic grid of sample points, referring to visual interpretation from high-resolution Landsat imagery. Regional land-cover area estimates were obtained and compared with FAO statistics for the categories ‘forest’ and ‘cropland’. Results The regional map displays 26 land-cover Classes. The LCCS coding provided a standardized Class Description, independent from local Class names; it also allowed us to maintain the link to the detailed sub-regional land-cover Classes. The validation of the map displayed a mapping accuracy of 72% for the dominant Classes of ‘forest’ and ‘cropland’; regional area estimates for these Classes correspond reasonably well to existing regional statistics. Main conclusions The land-cover map of South and Southeast Asia provides a synoptic view of the distribution of land cover of tropical and sub-tropical Asia, and it delivers reasonable thematic detail and quantitative estimates of the main land-cover proportions. The map may therefore serve for regional stratification or modelling of vegetation cover, but could also support the implementation of forest policies, watershed management or conservation strategies at regional scales.
Riccardo La Grassa - One of the best experts on this subject based on the ideXlab platform.
-
binary Classification using pairs of minimum spanning trees or n ary trees
Computer Analysis of Images and Patterns, 2019Co-Authors: Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri OgnibeneAbstract:One-Class Classifiers are trained only with target Class samples. Intuitively, their conservative modeling of the Class Description may benefit Classical Classification tasks where Classes are difficult to separate due to overlapping and data imbalance. In this work, three methods leveraging on the combination of one-Class Classifiers based on non-parametric models, Trees and Minimum Spanning Trees Class descriptors (MST_CD) are proposed.
-
binary Classification using pairs of minimum spanning trees or n ary trees
arXiv: Learning, 2019Co-Authors: Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri OgnibeneAbstract:One-Class Classifiers are trained with target Class only samples. Intuitively, their conservative modelling of the Class Description may benefit Classical Classification tasks where Classes are difficult to separate due to overlapping and data imbalance. In this work, three methods are proposed which leverage on the combination of one-Class Classifiers based on non-parametric models, N-ary Trees and Minimum Spanning Trees Class descriptors (MST-CD), to tackle binary Classification problems. The methods deal with the inconsistencies arising from combining multiple Classifiers and with spurious connections that MST-CD creates in multi-modal Class distributions. As shown by our tests on several datasets, the proposed approach is feasible and comparable with state-of-the-art algorithms.