Multidisciplinary Digital Publishing Institute
About: Remote Sensing is an academic journal. The journal publishes majorly in the area(s): Normalized Difference Vegetation Index & Synthetic aperture radar. It has an ISSN identifier of 2072-4292. It is also open access. Over the lifetime, 21259 publications have been published receiving 310858 citations.
Topics: Normalized Difference Vegetation Index, Synthetic aperture radar, Land cover, Hyperspectral imaging, Vegetation
Papers published on a yearly basis
TL;DR: In this paper, the authors presented results obtained using 45 ERS SAR images gathered over the Italian town of Camaiore (within a time span of more than 6 years and a range of normal baseline of over 2000 m) are presented.
Abstract: Differential SAR interferometry measurements provide a unique tool for low-cost, large-coverage surface deformations monitoring. Limitations are essentially due to temporal decorrelation and atmospheric inhomogeneities. Though temporal decorrelation and atmospheric disturbances strongly affect interferogram quality, reliable deformation measurements can be obtained in a multi-image framework on a small subset of image pixels, corresponding to stable areas. These points, hereafter called Permanent Scatterers, can be used as a `natural GPS network' to monitor terrain motion, analyzing the phase history of each one. In this paper, results obtained using 45 ERS SAR images gathered over the Italian town of Camaiore (within a time span of more than 6 years and a range of normal baseline of more than 2000 m) are presented. The area is of high geophysical interest because it is known to be unstable. A subterranean cavity collapsed in October 1995 causing the ruin of several houses in that location. Time series analysis of the phase values showed the presence of precursors three months before the collapse.© (1999) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
TL;DR: This paper proposes two scenarios for generating image features via extracting CNN features from different layers and reveals that the features from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low- and mid-level features.
Abstract: Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineered features or unsupervised feature learning, can only generate mid-level image features with limited representative ability, which essentially prevents them from achieving better performance. Recently, the deep convolutional neural networks (CNNs), which are hierarchical architectures trained on large-scale datasets, have shown astounding performance in object recognition and detection. However, it is still not clear how to use these deep convolutional neural networks for high-resolution remote sensing (HRRS) scene classification. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for HRRS scene classification. We propose two scenarios for generating image features via extracting CNN features from different layers. In the first scenario, the activation vectors extracted from fully-connected layers are regarded as the final image features; in the second scenario, we extract dense features from the last convolutional layer at multiple scales and then encode the dense features into global image features through commonly used feature coding approaches. Extensive experiments on two public scene classification datasets demonstrate that the image features obtained by the two proposed scenarios, even with a simple linear classifier, can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low- and mid-level features. Moreover, we tentatively combine features extracted from different CNN models for better performance.
TL;DR: The NDVI3g time series is an improved 8-km normalized difference vegetation index (NDVI) data set produced from Advanced Very High Resolution Radiometer (AVHRR) instruments that extends from 1981 to the present as discussed by the authors.
Abstract: The NDVI3g time series is an improved 8-km normalized difference vegetation index (NDVI) data set produced from Advanced Very High Resolution Radiometer (AVHRR) instruments that extends from 1981 to the present. The AVHRR instruments have flown or are flying on fourteen polar-orbiting meteorological satellites operated by the National Oceanic and Atmospheric Administration (NOAA) and are currently flying on two European Organization for the Exploitation of Meteorological Satellites (EUMETSAT) polar-orbiting meteorological satellites, MetOp-A and MetOp-B. This long AVHRR record is comprised of data from two different sensors: the AVHRR/2 instrument that spans July 1981 to November 2000 and the AVHRR/3 instrument that continues these measurements from November 2000 to the present. The main difficulty in processing AVHRR NDVI data is to properly deal with limitations of the AVHRR instruments. Complicating among-instrument AVHRR inter-calibration of channels one and two is the dual gain introduced in late 2000 on the AVHRR/3 instruments for both these channels. We have processed NDVI data derived from the Sea-Viewing Wide Field-of-view Sensor (SeaWiFS) from 1997 to 2010 to overcome among-instrument AVHRR calibration difficulties. We use Bayesian methods with high quality well-calibrated SeaWiFS NDVI data for deriving AVHRR NDVI calibration parameters. Evaluation of the uncertainties of our resulting NDVI values gives an error of ± 0.005 NDVI units for our 1981 to present data set that is independent of time within our AVHRR NDVI continuum and has resulted in a non-stationary climate data set.
TL;DR: A 3D convolutional neural network framework is proposed for accurate HSI classification, which is lighter, less likely to over-fit, and easier to train, and requires fewer parameters than other deep learning-based methods.
Abstract: Recent research has shown that using spectral–spatial information can considerably improve the performance of hyperspectral image (HSI) classification. HSI data is typically presented in the format of 3D cubes. Thus, 3D spatial filtering naturally offers a simple and effective method for simultaneously extracting the spectral–spatial features within such images. In this paper, a 3D convolutional neural network (3D-CNN) framework is proposed for accurate HSI classification. The proposed method views the HSI cube data altogether without relying on any preprocessing or post-processing, extracting the deep spectral–spatial-combined features effectively. In addition, it requires fewer parameters than other deep learning-based methods. Thus, the model is lighter, less likely to over-fit, and easier to train. For comparison and validation, we test the proposed method along with three other deep learning-based HSI classification methods—namely, stacked autoencoder (SAE), deep brief network (DBN), and 2D-CNN-based methods—on three real-world HSI datasets captured by different sensors. Experimental results demonstrate that our 3D-CNN-based method outperforms these state-of-the-art methods and sets a new record.
TL;DR: Long-term global data sets of vegetation Leaf Area Index (LAI) and Fraction of Photosynthetically Active Radiation absorbed by vegetation (FPAR) are critical to understanding vegetation photosynthesis and its role in climate change.
Abstract: Long-term global data sets of vegetation Leaf Area Index (LAI) and Fraction of Photosynthetically Active Radiation absorbed by vegetation (FPAR) are critical to monitoring global vegetation dynamics and for modeling exchanges of energy, mass and momentum between the land surface and planetary boundary layer. LAI and FPAR are also state variables in hydrological, ecological, biogeochemical and crop-yield models. The generation, evaluation and an example case study documenting the utility of 30-year long data sets of LAI and FPAR are described in this article. A neural network algorithm was first developed between the new improved third generation Global Inventory Modeling and Mapping Studies (GIMMS) Normalized Difference Vegetation Index (NDVI3g) and best-quality Terra Moderate Resolution Imaging Spectroradiometer (MODIS) LAI and FPAR products for the overlapping period 2000–2009. The trained neural network algorithm was then used to generate corresponding LAI3g and FPAR3g data sets with the following attributes: 15-day temporal frequency, 1/12 degree spatial resolution and temporal span of July 1981 to December 2011. The quality of these data sets for scientific research in other disciplines was assessed through (a) comparisons with field measurements scaled to the spatial resolution of the data products, (b) comparisons with broadly-used existing alternate satellite data-based products, (c) comparisons to plant growth limiting climatic variables in the northern latitudes and tropical regions, and (d) correlations of dominant modes of interannual variability with large-scale circulation anomalies such as the EI Nino-Southern Oscillation and Arctic Oscillation. These assessment efforts yielded results that attested to the suitability of these data sets for research use in other disciplines. The utility of these data sets is documented by comparing the seasonal profiles of LAI3g with profiles from 18 state-of-the-art Earth System Models: the models consistently overestimated the satellite-based estimates of leaf area and simulated delayed peak seasonal values in the northern latitudes, a result that is consistent with previous evaluations of similar models with ground-based data. The LAI3g and FPAR3g data sets can be obtained freely from the NASA Earth Exchange (NEX) website.
Related Journals (5)
Remote Sensing of Environment
9.5K papers, 1M citations
International Journal of Remote Sensing
9.4K papers, 402.5K citations
IEEE Transactions on Geoscience and Remote Sensing
15.7K papers, 850.9K citations
Agricultural and Forest Meteorology
6.5K papers, 367K citations
Hydrology and Earth System Sciences
5K papers, 263.8K citations