Final Image Resolution Research Articles

Virtual image pair-based spatio-temporal fusion

Spatio-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.

FSDAF 2.0: Improving the performance of retrieving land cover changes and preserving spatial details

Spatiotemporal fusion is a feasible solution to resolve the tradeoff between the temporal and spatial resolutions of remote sensing images. However, the development of spatiotemporal fusion algorithms has not yet reached maturity, and existing methods still face many challenges, e.g., accurately retrieving land cover changes and improving the robustness of fusion algorithms. The Flexible Spatiotemporal DAta Fusion (FSDAF) method proposed by Zhu et al. in 2016 solved the abovementioned problems to some extent. However, FSDAF has two shortcomings that can be further improved: (1) FSDAF is prone to losing spatial details and predicting a “blurrier” image due to the input of coarse pixels containing type change information and a large amount of boundary information for unmixing calculation, and (2) FSDAF does not optimize the areas of land cover change. In this paper, an improved FSDAF method incorporating change detection technology and an optimized model for changed-type areas (FSDAF 2.0) was proposed to improve the aforementioned problems. Based on the existing FSDAF algorithm, FSDAF 2.0 excludes changed pixels and boundary pixels for unmixing calculation, and establishes a model to optimize the changed pixels. Its performance was compared with that of the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), the original FSDAF, and the enhanced FSDAF that incorporates sub-pixel class fraction change information (SFSDAF). Two sites consisting of landscapes with heterogeneous and large-scale abrupt land cover changes were employed for testing. The results of the experiments demonstrate that FSDAF 2.0 effectively improves the shortcomings of FSDAF, blends synthetic fine-resolution images with higher accuracy than that of the other three methods at two different sites, and strengthens the robustness of the fusion algorithm. More importantly, FSDAF 2.0 has a powerful ability to retrieve land cover changes and provides a feasible way to improve the performance of retrieving land cover changes. Consequently, FSDAF 2.0 has great potential for monitoring complex dynamic changes in the Earth's surface.

Spatio-temporal fusion for remote sensing data: an overview and new benchmark

Spatio-temporal fusion (STF) aims at fusing (temporally dense) coarse resolution images and (temporally sparse) fine resolution images to generate image series with adequate temporal and spatial resolution. In the last decade, STF has drawn a lot of attention and many STF methods have been developed. However, to datethe STF domain still lacks benchmark datasets, which is a pressing issue that needs to be addressed in order to foster the development of this field. In this review, we provide (for the first time in the literature) a robust benchmark STF dataset that includes three important characteristics: (1) diversity of regions, (2) long timespan, and (3) challenging scenarios. We also provide a survey of highly representative STF techniques, along with a detailed quantitative and qualitative comparison of their performance with our newly presented benchmark dataset. The proposed dataset is public and available online.

A new sensor bias-driven spatio-temporal fusion model based on convolutional neural networks

Owing to the tradeoff between scanning swath and pixel size, currently no satellite Earth observation sensors are able to collect images with high spatial and temporal resolution simultaneously. This limits the application of satellite images in many fields, including the characterization of crop yields or the detailed investigation of human-nature interactions. Spatio-temporal fusion (STF) is a widely used approach to solve the aforementioned problem. Traditional STF methods reconstruct fine-resolution images under the assumption that changes are able to be transferred directly from one sensor to another. However, this assumption may not hold in real scenarios, owing to the different capacity of available sensors to characterize changes. In this paper, we model such differences as a bias, and introduce a new sensor bias-driven STF model (called BiaSTF) to mitigate the differences between the spectral and spatial distortions presented in traditional methods. In addition, we propose a new learning method based on convolutional neural networks (CNNs) to efficiently obtain this bias. An experimental evaluation on two public datasets suggests that our newly developed method achieves excellent performance when compared to other available approaches.

Random forest and watershed transformations for mapping quasi-circular vegetation patch using fused multispectral CBERS-04 images

To identify the quasi-circular vegetation patches (QVPs) and monitor their pattern dynamic is the most essential procedure for studying the establishment, encroachment, and maintenance of the QVPs. High resolution satellite remotely sensed technique is a cost-effective approach to distinguish the QVPs. However, the adhesion between the QVPs or between the QVPs and the vegetations of other shapes makes the detection accuracy of the QVPs low. This study used two-seasonal CBERS-04 pansharpened multispectral images to detect the QVPs by integrating random forest classification and watershed transformation image segmentation technique. The results showed that the method proposed by this study could raise the detection accuracy of QVPs, and 5 m spatial resolution CBERS-04 pansharpened imagery may be enough to obtain the number of the QVPs, but not sufficient to calculate the area and shape of QVPs. In the future, more advanced image segmentation algorithms and finer resolution images should be applied to detect the QVPs.

Влияние разрешающей способности цифровых фотокамер на разрешающую способность конечного цифрового изображения (о применимости формул Мороза и Катца в современной фотографии)

Описаны формулы, связывающие разрешающую способность конечного фотографического изобра- жения с разрешающими способностями фотообъектива и светочувствительного слоя в отдельности, которые были получены в середине прошлого века для традиционных фотоматериалов. Представле- ны результаты экспериментальной проверки справедливости этих формул в отношении современных фотообъективов, фотоматериалов и цифровых фотокамер. Сделаны выводы о возможности их приме- нения в цифровой фотографии.

HISTIF: A New Spatiotemporal Image Fusion Method for High-Resolution Monitoring of Crops at the Subfield Level

Satellite-based time-series crop monitoring at the subfield level is essential to the efficient implementation of precision crop management. Existing spatiotemporal image fusion techniques can be helpful, but they were often proposed to generate medium-resolution images. This study proposed a high-resolution spatiotemporal image fusion method (HISTIF) consisting of filtering for cross-scale spatial matching (FCSM) and multiplicative modulation of temporal change (MMTC). In FCSM, we considered both point spread function effect and geo-registration errors between fine and coarse resolution images. Subsequently, MMTC used pixel-based multiplicative factors to estimate the temporal change between reference and prediction dates without image classification. The performance of HISTIF was evaluated using both simulated and real datasets with one from real Gaofen-1 (GF-1) and simulated Landsat-like/Sentinel-like images, and the other from real GF-1 and real Landsat/Sentinel-2 data on two sites. HISTIF was compared with the existing methods spatial and temporal adaptive reflectance fusion model (STARFM), FSDAF, and Fit-FC. The results demonstrated that HISTIF produced substantial reduction in the fusion error from cross-scale spatial mismatch and accurate reconstruction in spatial details within fields, regardless of simulated or real data. The images predicted by STARFM exhibited pronounced blocky artifacts. While the images predicted by HISTIF and Fit-FC both showed clear within-field variability patterns, HISTIF was able to reduce the spectral distortion more significantly than Fit-FC. Furthermore, HISTIF exhibited the most stable performance across sensors. The findings suggest that HISTIF could be beneficial for the frequent and detailed monitoring of crop growth at the subfield level.

Information Loss-Guided Multi-Resolution Image Fusion

Spatial downscaling is an ill-posed, inverse problem, and information loss (IL) inevitably exists in the predictions produced by any downscaling technique. The recently popularized area-to-point kriging (ATPK)-based downscaling approach can account for the size of support and the point spread function (PSF) of the sensor, and moreover, it has the appealing advantage of the perfect coherence property. In this article, based on the advantages of ATPK and the conceptualization of IL, an IL-guided image fusion (ILGIF) approach is proposed. ILGIF uses the fine spatial resolution images acquired in other wavelengths to predict the IL in ATPK predictions based on the geographically weighted regression (GWR) model, which accounts for the spatial variation in land cover. ILGIF inherits all the advantages of ATPK, and its prediction has perfect coherence with the original coarse spatial resolution data which can be demonstrated mathematically. ILGIF was validated using two data sets and was shown in each case to predict downscaled images more accurately than the compared benchmark methods.

Evaluating Multivariable Statistical Methods for Downscaling Nighttime Land Surface Temperature in Urban Areas

For research and practice in fields such as the environment and meteorology, nighttime land surface temperature (LST) images at fine resolution provide important basic data. Since only a few satellite sensors can take fine-resolution thermal infrared images at night, such images are rather scarce. Downscaling of coarse-resolution LST images is a potential method for obtaining high-resolution LST images. However, downscaling methods have been mostly proposed for daytime LST images. This study aimed to evaluate the performance of methods that combine multiple explanatory variables and machine learning algorithms for downscaling coarse-resolution nighttime LST images in urban areas. Verification showed that the errors in the downscaling results were acceptable (mean absolute errors within 2 K). The resulting images could depict the spatial pattern of night LST in the study area in great detail. It was demonstrated that visible-near infrared images taken in the daytime could be used for downscaling of nighttime LST images, the rationality of which was deduced. It was also demonstrated that the performance of the spectral explanatory variables in nighttime LST downscaling was not lower than that of the mechanism explanatory variables. This method has high application value in many academic and practical efforts, such as land-atmosphere interface radiation budget studies, suitability assessments of human settlement, and urban environmental planning.

Flood mapping under vegetation using single SAR acquisitions

Synthetic Aperture Radar (SAR) enables 24-hour, all-weather flood monitoring. However, accurate detection of inundated areas can be hindered by the extremely complicated electromagnetic interaction phenomena between microwave pulses, and horizontal and vertical targets. This manuscript focuses on the problem of inundation mapping in areas with emerging vegetation, where spatial and seasonal heterogeneity makes the systematic distinction between dry and flooded backscatter response even more difficult. In this context, image interpretation algorithms have mostly used detailed field data and reference image(s) to implement electromagnetic models or change detection techniques. However, field data are rare, and despite the increasing availability of SAR acquisitions, adequate reference image(s) might not be readily available, especially for fine resolution acquisitions. To by-pass this problem, this study presents an algorithm for automatic flood mapping in areas with emerging vegetation when only single SAR acquisitions and common ancillary data are available. First, probability binning is used for statistical analysis of the backscatter response of wet and dry vegetation for different land cover types. This analysis is then complemented with information on land use, morphology and context within a fuzzy logic approach. The algorithm was applied to three fine resolution images (one ALOS-PALSAR and two COSMO-SkyMed) acquired during the January 2011 flood in the Condamine-Balonne catchment (Australia). Flood extent layers derived from optical images were used as validation data, demonstrating that the proposed algorithm had an overall accuracy higher than 80% for all case studies. Notwithstanding the difficulty to fully discriminate between dry and flooded vegetation backscatter heterogeneity using a single SAR image, this paper provides an automatic, data parsimonious algorithm for the detection of floods under vegetation.

A Scene Images Diversity Improvement Generative Adversarial Network for Remote Sensing Image Scene Classification

To achieve good remote sensing image scene classification, deep learning models usually require a large number of samples in the training stage. Unfortunately, collecting a large number of training scene images usually involves large acquisition and processing costs. In contrast, after training a generative adversarial network (GAN), scene samples can subsequently be generated automatically by the generator at a low cost. Then, the generated images can be added to the training set. A model with better classification ability will be obtained when these samples include more diverse scene structures and essential features than the original real images. In this letter, we propose the scene images diversity improvement GAN (diversity-GAN). Diversity-GAN has two important advantages. 1) The training process is designed in a progressive manner: the GAN’s generator and discriminator progress from coarse- to fine-resolution scene images. This characteristic can guarantee the diversity of generated samples. In particular, it guarantees the diversity of the structure of the generated scene images. 2) The training progress is controllable: by introducing control parameters, diversity-GAN can directly determine the scene image resolution on which the training process should focus. This characteristic allows diversity-GAN to achieve scene image structure diversity at the coarse-resolution training stage with a few iterations. In the experiments, the UC-Merced and AID data sets are introduced. The results show that the samples generated by diversity-GAN can effectively improve the diversity of the sample set, and these generated samples can grant convolutional neural networks (CNNs) better classification ability in the training stage.

SFSDAF: An enhanced FSDAF that incorporates sub-pixel class fraction change information for spatio-temporal image fusion

Spatio-temporal image fusion methods have become a popular means to produce remotely sensed data sets that have both fine spatial and temporal resolution. Accurate prediction of reflectance change is difficult, especially when the change is caused by both phenological change and land cover class changes. Although several spatio-temporal fusion methods such as the Flexible Spatiotemporal DAta Fusion (FSDAF) directly derive land cover phenological change information (such as endmember change) at different dates, the direct derivation of land cover class change information is challenging. In this paper, an enhanced FSDAF that incorporates sub-pixel class fraction change information (SFSDAF) is proposed. By directly deriving the sub-pixel land cover class fraction change information the proposed method allows accurate prediction even for heterogeneous regions that undergo a land cover class change. In particular, SFSDAF directly derives fine spatial resolution endmember change and class fraction change at the date of the observed image pair and the date of prediction, which can help identify image reflectance change resulting from different sources. SFSDAF predicts a fine resolution image at the time of acquisition of coarse resolution images using only one prior coarse and fine resolution image pair, and accommodates variations in reflectance due to both natural fluctuations in class spectral response (e.g. due to phenology) and land cover class change. The method is illustrated using degraded and real images and compared against three established spatio-temporal methods. The results show that the SFSDAF produced the least blurred images and the most accurate predictions of fine resolution reflectance values, especially for regions of heterogeneous landscape and regions that undergo some land cover class change. Consequently, the SFSDAF has considerable potential in monitoring Earth surface dynamics.

Mapping sugarcane in complex landscapes by integrating multi-temporal Sentinel-2 images and machine learning algorithms

Sugarcane is an important type of cash crop and plays a crucial role in global sugar production. Clarifying the magnitude of sugarcane planting will likely provide very evident supports for local land use management and policy-making. However, sugarcane growth environment in complex landscapes with frequent rainy weather conditions poses many challenges for its rapid mapping. This study thus tried and used 10-m Sentinel-2 images as well as crop phenology information to map sugarcane in Longzhou county of China in 2018. To minimize the influences of cloudy and rainy conditions, this study firstly fused all available images in each phenology stage to obtain cloud-free remote sensing images of three phenology stage (seedling, elongation and harvest) with the help of Google Earth Engine platform. Then, the study used the fused images to compute the normalized difference vegetation index (NDVI) of each stage. A three-band NDVI dataset along with 4000 training samples and 2000 random validation samples was finally used for sugarcane mapping. To assess the robustness of the three-band NDVI dataset with phenological characteristics for sugarcane mapping, this study employed five classifiers based on machine learning algorithms, including two support vector machine classifiers (Polynomial-SVM and RBF-SVM), a random forest classifier (RF), an artificial neural network classifier (ANN) and a decision tree classifier (CART-DT). Results showed that except for ANN classifier, Polynomial-SVM, RBF-SVM, RF and CART-DT classifiers displayed high accuracy sugarcane resultant maps with producer’s and user’s accuracies of greater than 91%. The ANN classifier tended to overestimate area of sugarcane and underestimate area of forests. Overall performances of five classifiers suggest Polynomial-SVM has the best potential to improve sugarcane mapping at the regional scale. Also, this study observed that most sugarcane (more than 75% of entire study area) tends to grow in flat regions with slope of less than 10°. This study emphasizes the importance of considering phenology in rapid sugarcane mapping, and suggests the potential of fine-resolution Sentinel-2 images and machine learning approaches in high-accuracy land use management and decision-making.

Spatio-Temporal Data Fusion for Satellite Images Using Hopfield Neural Network

Spatio-temporal data fusion refers to the technique of combining high temporal resolution from coarse satellite images and high spatial resolution from fine satellite images. However, data availability remains a major limitation in algorithm development. Existing spatio-temporal data fusion algorithms require at least one known image pair between the fine and coarse resolution image. However, data which come from two different satellite platforms do not necessarily have an overlap in their overpass times, hence restricting the application of spatio-temporal data fusion. In this paper, a new algorithm named Hopfield Neural Network SPatio-tempOral daTa fusion model (HNN-SPOT) is developed by utilizing the optimization concept in the Hopfield neural network (HNN) for spatio-temporal image fusion. The algorithm derives a synthesized fine resolution image from a coarse spatial resolution satellite image (similar to downscaling), with the use of one fine resolution image taken on an arbitrary date and one coarse image taken on a predicted date. The HNN-SPOT particularly addresses the problem when the fine resolution and coarse resolution images are acquired from different satellite overpass times over the same geographic extent. Both simulated datasets and real datasets over Hong Kong and Australia have been used in the evaluation of HNN-SPOT. Results showed that HNN-SPOT was comparable with an existing fusion algorithm, the spatial and temporal adaptive reflectance fusion model (STARFM). HNN-SPOT assumes consistent spatial structure for the target area between the date of data acquisition and the prediction date. Therefore, it is more applicable to geographical areas with little or no land cover change. It is shown that HNN-SPOT can produce accurate fusion results with >90% of correlation coefficient over consistent land covers. For areas that have undergone land cover changes, HNN-SPOT can still produce a prediction about the outlines and the tone of the features, if they are large enough to be recorded in the coarse resolution image at the prediction date. HNN-SPOT provides a relatively new approach in spatio-temporal data fusion, and further improvements can be made by modifying or adding new goals and constraints in its HNN architecture. Owing to its lower demand for data prerequisites, HNN-SPOT is expected to increase the applicability of fine-scale applications in remote sensing, such as environmental modeling and monitoring.

Persistent Scatterer Density by Image Resolution and Terrain Type

Persistent scatterer interferometry is a powerful time-series technique which uses the most temporally stable pixels (denoted persistent scatterers, or PS), to enable measurement of deformation in decorrelation-prone data sets. System performance depends heavily on the density of identified PS, which is influenced by two factors: image resolution and terrain type. In this work, we establish a quantitative link between PS density and these factors. First, we present a simple theoretical framework for predicting PS density by estimating the change in the pixel signal-to-clutter ratio (SCR) as a function of bandwidth for several different terrain types. Then, we analyze the behavior of PS density for three terrain types at different image resolutions. The model agrees with empirical results within 50% error, and rather closer for the high SCR points that form the desired network of PS points. Additionally, we find that the probability density functions of PS occurrence with respect to SCR for each region are approximately independent of system bandwidth. Thus, the increase in PS density is roughly proportional to increased bandwidth due to a higher pixel density in finer resolution images. We note that there is a slight increase in PS detectability with increasing bandwidth beyond the bandwidth scaling, but the gain is small compared to the bandwidth factor. These results form a model with a more quantitative understanding of the relationship between PS density and by extension, PS system performance, and image resolution and terrain.

Spatiotemporal Image Fusion in Remote Sensing

In this paper, we discuss spatiotemporal data fusion methods in remote sensing. These methods fuse temporally sparse fine-resolution images with temporally dense coarse-resolution images. This review reveals that existing spatiotemporal data fusion methods are mainly dedicated to blending optical images. There is a limited number of studies focusing on fusing microwave data, or on fusing microwave and optical images in order to address the problem of gaps in the optical data caused by the presence of clouds. Therefore, future efforts are required to develop spatiotemporal data fusion methods flexible enough to accomplish different data fusion tasks under different environmental conditions and using different sensors data as input. The review shows that additional investigations are required to account for temporal changes occurring during the observation period when predicting spectral reflectance values at a fine scale in space and time. More sophisticated machine learning methods such as convolutional neural network (CNN) represent a promising solution for spatiotemporal fusion, especially due to their capability to fuse images with different spectral values.

Spatiotemporal Subpixel Geographical Evolution Mapping

In recent decades, spatiotemporal subpixel mapping (SSM) approaches have been extensively developed to deal with the mixed-pixel problem by incorporating fine spatial resolution images with the same field of view from different acquisition times. This is an alternative to the conventional subpixel mapping (SPM) method, which is based on only monotemporal images. SSM has become one of the state-of-the-art SPM approaches, and has been widely applied in urban management and ecological monitoring. However, in the traditional SSM methods, the spatial correlation within the multitemporal images is insufficiently exploited and is ignored in the spatiotemporal model construction. In addition, the contribution of the land covers' spatial distribution in the multitemporal images is incompletely considered, and the geographic variation during the time interval is ignored, which underutilizes the spatiotemporal information. In this paper, an SSM algorithm based on a geographically weighted regression (GWR) model and evolutionary algorithm theory, called spatiotemporal subpixel geographical evolution mapping (STGEM), is proposed for multitemporal remote sensing images. The proposed algorithm considers the spatiotemporal dependence not only between the current subpixel and the corresponding fine pixel, but also with the neighboring fine distribution patterns within the fine image. Moreover, the potential temporal information of the geospatial variation is fully realized by considering not only the time interval between the bitemporal images, but also the ratio of changed area between them, based on the GWR model. Two synthetic-image experiments with bitemporal Landsat 8 images and bitemporal QuickBird images were carried out to validate the proposed algorithm. Furthermore, a real-image experiment using a bitemporal pair of Gaofen-2 images and a Landsat 8 image was also undertaken. A comparison was made with several traditional SPM methods, as well as the state-of-the-art SSM approaches, and the experimental results confirmed the superiority of the proposed STGEM algorithm. The proposed STGEM achieves a fine spatial and temporal resolution thematic map, both qualitatively and quantitatively, and has great potential for fine-scale and frequent time-series observation and monitoring.

Axial scanning in lensless microscopy to achieve high resolution

The optical system is designed here, to miniaturize the mechanical scanning and number of phase patterns illumination in lensless microscopy. The random phase mask is positioned in vertical column before the sample, which encoded the sample information and resulted into a final image at the sensor plane. To improve the signal to noise ratio and resolution of final image, the axial direction scanning of sample and sensor (SS) is performed while keeping them mutually immovable. This operation gathered the lost information of sample in between the sample and sensor planes. This axial motion of SS is performed with periodic steps, which would help in the reconstruction process during post processing. The final image has resolution of about 4 µm and field of view of 15 mm2. There are numerous advantages of such type of techniques, including portability and fast processing of data.

Earth Observation and Machine Learning to Meet Sustainable Development Goal 8.7: Mapping Sites Associated with Slavery from Space

A large proportion of the workforce in the brick kilns of the Brick Belt of Asia are modern-day slaves. Work to liberate slaves and contribute to UN Sustainable Development Goal 8.7 would benefit from maps showing the location of brick kilns. Previous work has shown that brick kilns can be accurately identified and located visually from fine spatial resolution remote-sensing images. Furthermore, via crowdsourcing, it would be possible to map very large areas. However, concerns over the ability to maintain a motivated crowd to allow accurate mapping over time together with the development of advanced machine learning methods suggest considerable potential for rapid, accurate and repeatable automated mapping of brick kilns. This potential is explored here using fine spatial resolution images of a region of Rajasthan, India. A contemporary deep-learning classifier founded on region-based convolution neural networks (R-CNN), the Faster R-CNN, was trained to classify brick kilns. This approach mapped all of the brick kilns within the study area correctly, with a producer’s accuracy of 100%, but at the cost of substantial over-estimation of kiln numbers. Applying a second classifier to the outputs substantially reduced the over-estimation. This second classifier could be visual classification, which, as it focused on a relatively small number of sites, should be feasible to acquire, or an additional automated classifier. The result of applying a CNN classifier to the outputs of the original classification was a map with an overall accuracy of 94.94% with both low omission and commission error that should help direct anti-slavery activity on the ground. These results indicate that contemporary Earth observation resources and machine learning methods may be successfully applied to help address slavery from space.

A spatio-temporal fusion method for remote sensing data Using a linear injection model and local neighbourhood information

ABSTRACTThis paper presents a spatio-temporal fusion method for remote sensing images by using a linear injection model and local neighbourhood information. In this method, the linear injection model is first introduced to generate an initial fused image, the spatial details are extracted from the fine-resolution image at the base date, and are weighted by a proper injection gains. Then, the spatial details and the relative spectral information from the coarse-resolution images are blended to generate the fusion result. To further enhance its robustness to the noise, the local neighbourhood information, derived from the fine-resolution image and the fused result simultaneously, is introduced to refine the initial fused image to obtain a more accurate prediction result. The algorithm can effectively capture phenology change or land-cover-type change with minimum input data. Simulated data and two types of real satellite images with seasonal changes and land-cover-type changes are employed to test the performance of the proposed method. Compared with a spatial and temporal adaptive reflectance fusion model (STARFM) and a flexible spatio-temporal fusion algorithm (FSDAF), results show that the proposed approach improves the accuracy of fused images in phenology change area and effectively captures land-cover-type reflectance changes.