The Experts below are selected from a list of 288 Experts worldwide ranked by ideXlab platform
Akira Hirose - One of the best experts on this subject based on the ideXlab platform.
-
unsupervised fine Land Classification using quaternion autoencoder based polarization feature extraction and self organizing mapping
IEEE Transactions on Geoscience and Remote Sensing, 2018Co-Authors: Akira HiroseAbstract:We propose an unsupervised polarimetric synthetic aperture radar (PolSAR) Land Classification system consisting of a series of two unsupervised neural networks, namely, a quaternion autoencoder and a quaternion self-organizing map (SOM). Most of the existing PolSAR Land Classification systems use a set of feature information that humans designed beforehand. However, such methods will face limitations in the near future when we expect Classification into a large number of Land categories recognizable to humans. By using a quaternion autoencoder, our proposed system extracts feature information based on the natural distribution of PolSAR features. In this paper, we confirm that the information necessary for Land Classification is extracted as the features while noise is filtered. Then, we show that the extracted features are classified by the quaternion SOM in an unsupervised manner. As a result, we can discover even new and more detailed Land categories. For example, town areas are divided into residential areas and factory sites, and grass areas are subcategorized into furrowed farmLands and flat grass areas. We also examine the realization of topographic mapping of the features in the SOM space.
-
quaternion neural network based polsar Land Classification in poincare sphere parameter space
IEEE Transactions on Geoscience and Remote Sensing, 2014Co-Authors: Fang Shang, Akira HiroseAbstract:We propose a quaternion neural-network-based Land Classification in Poincare-sphere-parameter space. By representing the Stokes vector on/in the Poincare sphere geometrically, we construct two analysis parameters, namely, the position vector and the variation vector, to describe the feature of a pixel in test area. Then, by employing a quaternion feedforward neural network, we generate successful Classification results for detecting lake, grass, forest, and town areas. In comparison with the conventional C-matrix-based methods, the proposed method has higher Classification performance, especially in detecting forest and town areas. Moreover, the Classification result of the proposed method is not influenced by height information. This fact suggests that the proposed Classification method can be used for complicated terrains.
-
use of poincare sphere parameters for fast supervised polsar Land Classification
International Geoscience and Remote Sensing Symposium, 2013Co-Authors: Fang Shang, Akira HiroseAbstract:We propose the use of Poincare sphere parameters for a fast supervised PolSAR Land Classification. The scattering matrix is represented by a point which indicates the polarization states on/in Poincare sphere. Then, by analyzing the distribution features of the points, the test area is classified into, for example, four types of targets: lake, grass, town and forest. This analyzing process can be implemented by employing a neural network. The experimental result shows that the Poincare sphere parameters are highly useful for Classification. It is possible that the method will contribute to reduce the computational complexity of PolSAR Classification process and provide higher accuracy.
Sudeep Sarkar - One of the best experts on this subject based on the ideXlab platform.
-
hydra an ensemble of convolutional neural networks for geospatial Land Classification
IEEE Transactions on Geoscience and Remote Sensing, 2019Co-Authors: Rodrigo Minetto, Mauricio Pamplona Segundo, Sudeep SarkarAbstract:In this paper, we describe Hydra, an ensemble of convolutional neural networks (CNNs) for geospatial Land Classification. The idea behind Hydra is to create an initial CNN that is coarsely optimized but provides a good starting pointing for further optimization, which will serve as the Hydra’s body. Then, the obtained weights are fine-tuned multiple times with different augmentation techniques, crop styles, and classes weights to form an ensemble of CNNs that represent the Hydra’s heads. By doing so, we prompt convergence to different endpoints, which is a desirable aspect for ensembles. With this framework, we were able to reduce the training time while maintaining the Classification performance of the ensemble. We created ensembles for our experiments using two state-of-the-art CNN architectures, residual network (ResNet), and dense convolutional networks (DenseNet). We have demonstrated the application of our Hydra framework in two data sets, functional map of world (FMOW) and NWPU-RESISC45, achieving results comparable to the state-of-the-art for the former and the best-reported performance so far for the latter. Code and CNN models are available at https://github.com/maups/hydra-fmow .
-
hydra an ensemble of convolutional neural networks for geospatial Land Classification
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Rodrigo Minetto, Mauricio Pamplona Segundo, Sudeep SarkarAbstract:We describe in this paper Hydra, an ensemble of convolutional neural networks (CNN) for geospatial Land Classification. The idea behind Hydra is to create an initial CNN that is coarsely optimized but provides a good starting pointing for further optimization, which will serve as the Hydra's body. Then, the obtained weights are fine tuned multiple times to form an ensemble of CNNs that represent the Hydra's heads. By doing so, we were able to reduce the training time while maintaining the Classification performance of the ensemble. We created ensembles using two state-of-the-art CNN architectures, ResNet and DenseNet, to participate in the Functional Map of the World challenge. With this approach, we finished the competition in third place. We also applied the proposed framework to the NWPU-RESISC45 database and achieved the best reported performance so far. Code and CNN models are available at this https URL
Fang Shang - One of the best experts on this subject based on the ideXlab platform.
-
quaternion neural network based polsar Land Classification in poincare sphere parameter space
IEEE Transactions on Geoscience and Remote Sensing, 2014Co-Authors: Fang Shang, Akira HiroseAbstract:We propose a quaternion neural-network-based Land Classification in Poincare-sphere-parameter space. By representing the Stokes vector on/in the Poincare sphere geometrically, we construct two analysis parameters, namely, the position vector and the variation vector, to describe the feature of a pixel in test area. Then, by employing a quaternion feedforward neural network, we generate successful Classification results for detecting lake, grass, forest, and town areas. In comparison with the conventional C-matrix-based methods, the proposed method has higher Classification performance, especially in detecting forest and town areas. Moreover, the Classification result of the proposed method is not influenced by height information. This fact suggests that the proposed Classification method can be used for complicated terrains.
-
use of poincare sphere parameters for fast supervised polsar Land Classification
International Geoscience and Remote Sensing Symposium, 2013Co-Authors: Fang Shang, Akira HiroseAbstract:We propose the use of Poincare sphere parameters for a fast supervised PolSAR Land Classification. The scattering matrix is represented by a point which indicates the polarization states on/in Poincare sphere. Then, by analyzing the distribution features of the points, the test area is classified into, for example, four types of targets: lake, grass, town and forest. This analyzing process can be implemented by employing a neural network. The experimental result shows that the Poincare sphere parameters are highly useful for Classification. It is possible that the method will contribute to reduce the computational complexity of PolSAR Classification process and provide higher accuracy.
Yao Guangqing - One of the best experts on this subject based on the ideXlab platform.
-
Applying independent component analysis on sentinel-2 imagery to characterize geomorphological responses to an extreme flood event near the non-vegetated Río Colorado terminus, Salar de Uyuni, Bolivia
2018Co-Authors: Li Jiaguang, Yang Xiucheng, Maffei C., Tooth Stephen, Yao GuangqingAbstract:In some internally-draining dryLand basins, ephemeral river systems terminate at the margins of playas. Extreme floods can exert significant geomorphological impacts on the lower reaches of these river systems and the playas, including causing changes to flood extent, channel-floodplain morphology, and sediment dispersal. However, the characterization of these impacts using remote sensing approaches has been challenging owing to variable vegetation and cloud cover, as well as the commonly limited spatial and temporal resolution of data. Here, we use Sentinel-2 Multispectral Instrument (MSI) data to investigate the flood extent, flood patterns and channel-floodplain morphodynamics resulting from an extreme flood near the non-vegetated terminus of the Río Colorado, located at the margins of the world's largest playa (Salar de Uyuni, Bolivia). Daily maximum precipitation frequency analysis based on a 42-year record of daily precipitation data (1976 through 2017) indicates that an approximately 40-year precipitation event (40.7 mm) occurred on 6 January 2017, and this was associated with an extreme flood. Sentinel-2 data acquired after this extreme flood were used to separate water bodies and Land, first by using modified normalized difference water index (MNDWI), and then by subsequently applying independent component analysis (ICA) on the Land section of the combined pre- and post-flood images to extract flooding areas. The area around the Río Colorado terminus system was classified into three categories: water bodies, wet Land, and dry Land. The results are in agreement with visual assessment, with an overall accuracy of 96% and Kappa of 0.9 for water-Land Classification and an overall accuracy of 83% and Kappa of 0.65 for dry Land-wet Land Classification. The flood extent mapping revealed preferential overbank flow paths on the floodplain, which were closely related to geomorphological changes. Changes included the formation and enlargement of crevasse splays, channel avulsion, and the development of erosion cells (floodplain scour-transport-fill features). These changes were visualized by Sentinel-2 images along with WorldView satellite images. In particular, flooding enlarged existing crevasse splays and formed new ones, while channel avulsion occurred near the river's terminus. Greater overbank flow on the floodplain led to rapid erosion cell development, with changes to channelized sections occurring as a result of adjustments in flow sources and intensity combined with the lack of vegetation on the fine-grained (predominantly silt, clay) sediments. This study has demonstrated how ICA can be implemented on Sentinel-2 imagery to characterize the impact of extreme floods on the lower Río Colorado, and the method has potential application in similar contexts in many other dryLands.
-
Applying independent component analysis on sentinel-2 imagery to characterize geomorphological responses to an extreme flood event near the non-vegetated Río Colorado terminus, Salar de Uyuni, Bolivia
'MDPI AG', 2018Co-Authors: Li Jiaguang, Yang Xiucheng, Maffei C., Tooth Stephen, Yao GuangqingAbstract:In some internally-draining dryLand basins, ephemeral river systems terminate at the margins of playas. Extreme floods can exert significant geomorphological impacts on the lower reaches of these river systems and the playas, including causing changes to flood extent, channel-floodplain morphology, and sediment dispersal. However, the characterization of these impacts using remote sensing approaches has been challenging owing to variable vegetation and cloud cover, as well as the commonly limited spatial and temporal resolution of data. Here, we use Sentinel-2 Multispectral Instrument (MSI) data to investigate the flood extent, flood patterns and channel-floodplain morphodynamics resulting from an extreme flood near the non-vegetated terminus of the Río Colorado, located at the margins of the world's largest playa (Salar de Uyuni, Bolivia). Daily maximum precipitation frequency analysis based on a 42-year record of daily precipitation data (1976 through 2017) indicates that an approximately 40-year precipitation event (40.7 mm) occurred on 6 January 2017, and this was associated with an extreme flood. Sentinel-2 data acquired after this extreme flood were used to separate water bodies and Land, first by using modified normalized difference water index (MNDWI), and then by subsequently applying independent component analysis (ICA) on the Land section of the combined pre- and post-flood images to extract flooding areas. The area around the Río Colorado terminus system was classified into three categories: water bodies, wet Land, and dry Land. The results are in agreement with visual assessment, with an overall accuracy of 96% and Kappa of 0.9 for water-Land Classification and an overall accuracy of 83% and Kappa of 0.65 for dry Land-wet Land Classification. The flood extent mapping revealed preferential overbank flow paths on the floodplain, which were closely related to geomorphological changes. Changes included the formation and enlargement of crevasse splays, channel avulsion, and the development of erosion cells (floodplain scour-transport-fill features). These changes were visualized by Sentinel-2 images along with WorldView satellite images. In particular, flooding enlarged existing crevasse splays and formed new ones, while channel avulsion occurred near the river's terminus. Greater overbank flow on the floodplain led to rapid erosion cell development, with changes to channelized sections occurring as a result of adjustments in flow sources and intensity combined with the lack of vegetation on the fine-grained (predominantly silt, clay) sediments. This study has demonstrated how ICA can be implemented on Sentinel-2 imagery to characterize the impact of extreme floods on the lower Río Colorado, and the method has potential application in similar contexts in many other dryLands.Optical and Laser Remote Sensin
Peng Gong - One of the best experts on this subject based on the ideXlab platform.
-
Comparison of Classification algorithms and training sample sizes in urban Land Classification with Landsat thematic mapper imagery
Remote Sensing, 2014Co-Authors: Congcong Li, Luanyun Hu, Jie Wang, Lei Wang, Peng GongAbstract:Although a large number of new image Classification algorithms have been developed, they are rarely tested with the same Classification task. In this research, with the same Landsat Thematic Mapper (TM) data set and the same Classification scheme over Guangzhou City, China, we tested two unsupervised and 13 supervised Classification algorithms, including a number of machine learning algorithms that became popular in remote sensing during the past 20 years. Our analysis focused primarily on the spectral information provided by the TM data. We assessed all algorithms in a per-pixel Classification decision experiment and all supervised algorithms in a segment-based experiment. We found that when sufficiently representative training samples were used, most algorithms performed reasonably well. Lack of training samples led to greater Classification accuracy discrepancies than Classification algorithms themselves. Some algorithms were more tolerable to insufficient (less representative) training samples than others. Many algorithms improved the overall accuracy marginally with per-segment decision making.
