73 research outputs found
Spatio-temporal fusion for daily Sentinel-2 images
No full textAbstract Sentinel-2 and Sentinel-3 are two newly launched satellites for global monitoring. The Sentinel-2 Multispectral Imager (MSI) and Sentinel-3 Ocean and Land Colour Instrument (OLCI) sensors have very different spatial and temporal resolutions (Sentinel-2 MSI sensor 10 m, 20 m and 60 m, 10 days, albeit 5 days with 2 sensors, conditional upon clear skies; Sentinel-3 OLCI sensor 300 m, < 1.4 days with 2 sensors). For local monitoring (e.g., the growing cycle of plants) one either has the desired spatial or temporal resolution, but not both. In this paper, spatio-temporal fusion is considered to fuse Sentinel-2 with Sentinel-3 images to create nearly daily Sentinel-2 images. A challenging issue in spatio-temporal fusion is that there can be very few cloud-free fine spatial resolution images temporally close to the prediction time, or even available, strong temporal (i.e., seasonal) changes may exist. To this end, a three-step method consisting of regression model fitting (RM fitting), spatial filtering (SF) and residual compensation (RC) is proposed, which is abbreviated as Fit-FC. The Fit-FC method can be performed using only one Sentinel-3–Sentinel-2 pair and is advantageous for cases involving strong temporal changes (i.e., mathematically, the correlation between the two Sentinel-3 images is small). The effectiveness of the method was validated using two datasets. The created nearly daily Sentinel-2 time-series images have great potential for timely monitoring of highly dynamic environmental, agricultural or ecological phenomena
A geostatistical filter for remote sensing image enhancement
No full textIn this paper, a new method was investigated to enhance remote sensing images by alleviating the point spread function (PSF) effect. The PSF effect exists ubiquitously in remotely sensed imagery. As a result, image quality is greatly affected, and this imposes a fundamental limit on the amount of information captured in remotely sensed images. A geostatistical filter was proposed to enhance image quality based on a downscaling-then-upscaling scheme. The difference between this method and previous methods is that the PSF is represented by breaking the pixel down into a series of sub-pixels, facilitating downscaling using the PSF and then upscaling using a square-wave response. Thus, the sub-pixels allow disaggregation as an attempt to remove the PSF effect. Experimental results on simulated and real data sets both suggest that the proposed filter can enhance the original images by reducing the PSF effect and quantify the extent to which this is possible. The predictions using the new method outperform the original coarse PSF-contaminated imagery as well as a benchmark method. The proposed method represents a new solution to compensate for the limitations introduced by remote sensors (i.e., hardware) using computer techniques (i.e., software). The method has widespread application value, particularly for applications based on remote sensing image analysis
Enhancing spectral unmixing by considering the point spread function effect
No full textThe point spread function (PSF) effect exists ubiquitously in real remotely sensed data and such that the observed pixel signal is not only determined by the land cover within its own spatial coverage but also by that within neighboring pixels. The PSF, thus, imposes a fundamental limit on the amount of information captured in remotely sensed images and it introduces great uncertainty in the widely applied, inverse goal of spectral unmixing. Until now, spectral unmixing has erroneously been performed by assuming that the pixel signal is affected only by the land cover within the pixel, that is, ignoring the PSF. In this paper, a new method is proposed to account for the PSF effect within spectral unmixingto produce more accurate predictions of land cover proportions. Based on the mechanism of the PSF effect, the mathematical relation between the coarse proportion and sub-pixel proportions in a local window was deduced. Area-to-point kriging (ATPK) was then proposed to find a solution for the inverse prediction problem of estimating the sub-pixel proportions from the original coarse proportions. The sub-pixel proportions were finally upscaled using an ideal square wave response to produce the enhanced proportions. The effectiveness of the proposed method was demonstrated using two datasets. The proposed method has great potential for wide application since spectral unmixing is an extremely common approach in remote sensing.</p
Hyperspectral Target Detection via Global Spatial–Spectral Attention Network and Background Suppression
No full textThe accuracy of hyperspectral target detection is often affected by the problems of spectral variation and complex background distribution. Inspired by the powerful representational ability of deep learning, we proposed a three-dimensional (3-D) convolution-based global spatial–spectral attention network (GS2A-Net) to deal with spectral variation in hyperspectral images (HSIs). GS2A-Net uses 3-D convolution kernels of different sizes to capture local spatial and spectral features to achieve multiscale information interaction. Different from the previous 2-D attention mechanisms, GS2A-Net simultaneously considers the information in the spatial and spectral dimensions, and creates a weight map consistent with the size of the original HSI. Furthermore, we proposed a new background suppression strategy based on the spectral angle mapping to achieve more accurate target detection, which can preserve the targets as much as possible when suppressing the background. The method was validated through experiments on five real-world HSI datasets. Compared with several classical and deep-learning-based methods, the proposed method exhibits greater detection accuracy
Spatial-spectral radial basis function-based interpolation for Landsat ETM+ SLC-off image gap filling
No full textThe scan-line corrector (SLC) of the Landsat 7 ETM+ failed permanently in 2003, resulting in about 22% unscanned gap pixels in the SLC-off images, affecting greatly the utility of the ETM+ data. To address this issue, we propose a spatial-spectral radial basis function (SSRBF)-based interpolation method to fill gaps in SLC-off images. Different from the conventional spatial-only radial basis function (RBF) that has been widely used in other domains, SSRBF also integrates a spectral RBF to increase the accuracy of gap filling. Concurrently, global linear histogram matching is applied to alleviate the impact of potentially large differences between the known and SLC-off images in feature space, which is demonstrated mathematically in this article. SSRBF fully exploits information in the data themselves and is user-friendly. The experimental results on five groups of data sets covering different heterogeneous regions show that the proposed SSRBF method is an effective solution to gap filling, and it can produce more accurate results than six popular benchmark methods
Virtual image pair-based spatio-temporal fusion
No full textSpatio-temporal fusion is a technique used to produce images with both fine spatial and temporal resolution. Generally, the principle of existing spatio-temporal fusion methods can be characterized by a unified framework of prediction based on two parts: (i) the known fine spatial resolution images (e.g., Landsat images), and (ii) the fine spatial resolution increment predicted from the available coarse spatial resolution increment (i.e., a downscaling process), that is, the difference between the coarse spatial resolution images (e.g., MODIS images) acquired at the known and prediction times. Owing to seasonal changes and land cover changes, there always exist large differences between images acquired at different times, resulting in a large increment and, further, great uncertainty in downscaling. In this paper, a virtual image pair-based spatio-temporal fusion (VIPSTF) approach was proposed to deal with this problem. VIPSTF is based on the concept of a virtual image pair (VIP), which is produced based on the available, known MODIS-Landsat image pairs. We demonstrate theoretically that compared to the known image pairs, the VIP is closer to the data at the prediction time. The VIP can capture more fine spatial resolution information directly from known images and reduce the challenge in downscaling. VIPSTF is a flexible framework suitable for existing spatial weighting- and spatial unmixing-based methods, and two versions VIPSTF-SW and VIPSTF-SU are, thus, developed. Experimental results on a heterogeneous site and a site experiencing land cover type changes show that both spatial weighting- and spatial unmixing-based methods can be enhanced by VIPSTF, and the advantage is particularly noticeable when the observed image pairs are temporally far from the prediction time. Moreover, VIPSTF is free of the need for image pair selection and robust to the use of multiple image pairs. VIPSTF is also computationally faster than the original methods when using multiple image pairs. The concept of VIP provides a new insight to enhance spatio-temporal fusion by making fuller use of the observed image pairs and reducing the uncertainty of estimating the fine spatial resolution increment
Rice crop phenology mapping at high spatial and temporal resolution using downscaled MODIS time-series
No full textSatellite data holds considerable potential as a source of information on rice crop growth which can be used to inform agronomy. However, given the typical field sizes in many rice-growing countries such as China, data from coarse spatial resolution satellite systems such as the Moderate Resolution Imaging Spectroradiometer (MODIS) are inadequate for resolving crop growth variability at the field scale. Nevertheless, systems such as MODIS do provide images with sufficient frequency to be able to capture the detail of rice crop growth trajectories throughout a growing season. In order to generate high spatial and temporal resolution data suitable for mapping rice crop phenology, this study fused MODIS data with lower frequency, higher spatial resolution Landsat data. An overall workflow was developed which began with image preprocessing, calculation of multi-temporal normalized difference vegetation index (NDVI) images, and spatiotemporal fusion of data from the two sensors. The Spatial and Temporal Adaptive Reflectance Fusion Model was used to effectively downscale the MODIS data to deliver a time-series of 30 m spatial resolution NDVI data at 8-day intervals throughout the rice-growing season. Zonal statistical analysis was used to extract NDVI time-series for individual fields and signal filtering was applied to the time-series to generate rice phenology curves. The downscaled MODIS NDVI products were able to characterize the development of paddy rice at fine spatial and temporal resolutions, across wide spatial extents over multiple growing seasons. These data permitted the extraction of key crop seasonality parameters that quantified inter-annual growth variability for a whole agricultural region and enabled mapping of the variability in crop performance between and within fields. Hence, this approach can provide rice crop growth data that is suitable for informing agronomic policy and practice across a wide range of scales.</p
Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data
No full textSentinel-1A synthetic aperture radar (SAR) data present an opportunity for acquiring crop information without restrictions caused by weather and illumination conditions, at a spatial resolution appropriate for individual rice fields and a temporal resolution sufficient to capture the growth profiles of different crop species. This study investigated the use of multi-temporal Sentinel-1A SAR data and Landsat-derived normalized difference vegetation index (NDVI) data to map the spatial distribution of paddy rice fields across parts of the Sanjiang plain, in northeast China. The satellite sensor data were acquired throughout the rice crop-growing season (May–October). A co-registered set of 10 dual polarization (VH/VV) SAR and NDVI images depicting crop phenological development were used as inputs to Support Vector Machine (SVM) and Random Forest (RF) machine learning classification algorithms in order to map paddy rice fields. The results showed a significant increase in overall classification when the NDVI time-series data were integrated with the various combinations of multi-temporal polarization channels (i.e. VH, VV, and VH/VV). The highest classification accuracies overall (95.2%) and for paddy rice (96.7%) were generated using the RF algorithm applied to combined multi-temporal VH polarization and NDVI data. The SVM classifier was most effective when applied to the dual polarization (i.e. VH and VV) SAR data alone and this generated overall and paddy rice classification accuracies of 91.6% and 82.5%, respectively. The results demonstrate the practicality of implementing RF or SVM machine learning algorithms to produce 10 m spatial resolution maps of paddy rice fields with limited ground data using a combination of multi-temporal SAR and NDVI data, where available, or SAR data alone. The methodological framework developed in this study is apposite for large-scale implementation across China and other major rice-growing regions of the world
Fusion of Landsat 8 OLI and Sentinel-2 MSI Data
No full textSentinel-2 is a wide-swath and fine spatial resolution satellite imaging mission designed for data continuity and enhancement of the Landsat and other missions. The Sentinel-2 data are freely available at the global scale, and have similar wavelengths and the same geographic coordinate system as the Landsat data, which provides an excellent opportunity to fuse these two types of satellite sensor data together. In this paper, a new approach is presented for fusion of Landsat 8 Operational Land Imager (OLI) and Sentinel-2 Multispectral Imager (MSI) data to coordinate their spatial resolutions for continuous global monitoring. The 30 m spatial resolution Landsat 8 bands are downscaled to 10 m using available 10 m Sentinel-2 bands. To account for the land-cover/land-use (LCLU) changes that may have occurred between the Landsat 8 and Sentinel-2 images, the Landsat 8 PAN band was also incorporated in the fusion process. The experimental results showed that the proposed approach is effective for fusing Landsat 8 with Sentinel-2 data, and the use of the PAN band can decrease the errors introduced by LCLU changes. By fusion of Landsat 8 and Sentinel-2 data, more frequent observations can be produced for continuous monitoring (this is particularly valuable for areas that can be covered easily by clouds, thereby, contaminating some Landsat or Sentinel-2 observations), and the observations are at a consistent fine spatial resolution of 10 m. The products have great potential for timely monitoring of rapid changes
Soft-then-hard sub-pixel mapping algorithm for remote sensing images
No full textPolyU Library Call No.: [THS] LG51 .H577P LSGI 2015 Wang189 pages :illustrations (some color)Image classification, one of the most important techniques in remote sensing, is used widely to extract land cover information from remote sensing images. The inevitable mixed pixels in remote sensing images have brought a great challenge for traditional hard classification-based land cover mapping. To solve this mixed pixel problem, soft classification (e.g., spectral unmixing) has been developed to predict land cover proportions for land cover classes that have a spatial frequency higher than the interval between pixels. Soft classifiers exploit the spectral information of remote sensing images, but fail to predict the spatial location of classes within mixed pixels. To address this issue, sub-pixel mapping (SPM) has been developed, in which each mixed pixel is divided into multiple sub-pixels for which class labels are predicted. SPM, thus, transforms a soft classification into a finer resolution hard classification. SPM is also termed super-resolution mapping in remote sensing. It has been receiving increasing attention in recent years. In this thesis, the soft-then-hard SPM (STHSPM) algorithms are summarized for the first time. STHSPM is a type of SPM algorithm consisting of soft class value (between 0 and 1) estimation at fine spatial resolution and hard class allocation for sub-pixels. The STHSPM algorithms provide a good opportunity to achieve SPM solutions quickly. Furthermore, they provide important insight into SPM and open doors to more alternatives. This thesis focuses on the STHSPM algorithm and the main research includes developing new class allocation approaches for the STHSPM algorithms, using additional information in STHSPM to enhance SPM, developing new STHSPM algorithms and applying STHSPM in sub-pixel resolution change detection. Specifically, a new class allocation approach that allocates classes in units of class (UOC) is proposed and UOC is further extended with an adaptive scheme, called AUOC; The multiple shifted images are incorporated to the STHSPM algorithms to decrease the uncertainty in SPM; Two new STHSPM algorithms, radial basis function interpolation and naive indicator cokriging, are proposed; STHSPM is proposed for fast sub-pixel resolution change detection. The experimental results demonstrate the feasibilities of the proposed methods in this thesis.Department of Land Surveying and Geo-InformaticsPh.D., Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, 2015Doctorat
- …
