In this letter, we proposed a novel deep feature manifold embedding method to improve feature extraction ability of traditional deep learning methods. This method first obtains deep features of hyperspectral image (HSI) from a trained autoencoder. Then, an intrinsic graph and a penalty graph are constructed to discover the discriminant manifold structure of deep features. Finally, the deep features

The instrument used for ocean colour remote-sensing works in the visible wavelengths, and the presence of clouds frequently lead to invalid observations. The formation of clouds is known to be influenced by mesoscale oceanic processes (e.g., eddies and temperature fronts), but these influences are often overlooked in missing data reconstructions. By analysing more than 10 years of chlorophyll-a (chl-a)

This paper describes an approach to forest growing stock volume (GSV) estimation based on remotely sensed optical data in red and near-infrared (NIR) bands collected during the period of persistent snow cover. The approach was applied to Sentinel-2 reflectance measurements over forest with snow-covered understory in the north-eastern part of Russian Kostroma region. An in-house dataset with a forest

Detecting the water surface area and its temporal changes is essential in water resource management. Multispectral satellite data are applied extensively to monitor the surface water dynamics because of their repeated coverage. This letter monitors waterbody dynamics in a high temporal resolution from Sentinel-2 and Landsat 8 images by using the Google Earth Engine (GEE) platform. Water index, automatic

For radar network, each radar can obtain the two-dimensional (2D) inverse synthetic aperture radar (ISAR) image from the corresponding observation angle independently. Taking advantage of the multi-view observation via radar network and the projection relationship in ISAR imaging, the three-dimensional (3D) image of the target can be reconstructed by the inverse-projection principle. However, it is

The angle of repose and volume of granular piles are important measures in many fields. This letter presents a new method for rapid estimation of the angle of repose and volume of grain piles using terrestrial laser scanning data acquired from a single site. Compared with some existing methods that require point cloud registration and surface reconstruction, the proposed method is simple and easy to

(2020). Editorial: A new start with motto 'festina lente' Remote Sensing Letters: Vol. 11, No. 7, pp. 609-610.

The study of sea surface temperature (SST) in coastal water is of great significance for navigation, aquaculture and military. Numerous studies have been conducted to predict this parameter in recent years. The fluctuation of SST is periodic, and it shows different changing patterns over different timescales. At present, most investigations on SST ignore the influence of multiscale features on the

Urban villages are a characteristic settlement type characterized by preserving their morphological characteristics embedded in sharp contrast in modern, high-rise developments found especially in fast growing urban agglomerations of China. They serve very important socioeconomic functions in terms of the provision of cheap housing for rural-urban migrants, but they are also considered controversial

Morphological building indexes (MBI) have proven to be effective tools for automated building spatial-feature-extraction tasks in images from urban areas. However, owing to the intrinsic shortcomings of MBI, commission and omission errors occur in regions with spectral properties similar to those of buildings and dark heterogeneous roofs, respectively. Some targets (such as bright bare land or roads)

After an attack the by pine wood nematode, pine tree needles turn red. Using convolutional neural networks (CNNs) based object detection methods, machines can detect red-attacked trees. However, most deep learning object detection algorithms (such as Faster R-CNN and YOLO among others) often require a large number of labelled training datasets, where in each image every object must be given a bounding

Disparity map quality assessment is crucial to evaluate the accuracies of stereo matching algorithms. Several widely used measures such as root mean square (RMS), mean absolute error (MAE) and bad matching pixels (BMP) have been proposed to evaluate the similarity between disparity map and ground truth (GT) map. These measures are based on grey-scale errors while ignoring the structural similarity

Unsupervised representation learning plays an important role in remote sensing image applications. Generative adversarial network (GAN) is the most popular unsupervised learning method in recent years. However, due to poor data augmentation, many GAN-based methods are often difficult to carry out. In this paper, we propose an improved unsupervised representation learning model called multi-layer feature

The United Arab Emirates (UAE) has seen an increase in oil extraction and oil refining processes. Toxic pollutants such as sulphur dioxide (SO2), black carbon (BC), carbon monoxide (CO) and organic carbon (OC) are released during oil refinery processes. These toxic pollutants have severe negative impacts on the climate, environment and human health. In this study we investigate the trends of BC, CO

In this paper, the zlog(z) based estimator for constant false alarm rate (CFAR) detection in Weibull clutter is proposed. This estimation method is obtained in terms of the digamma function where the estimates of the shape parameter are determined by the interpolation tool. The non-integer order moments estimator (NIOME) is also given and coincides the zlog(z) estimation results for low values of the

The sound speed profile (SSP) is a key dynamic factor affecting underwater acoustic propagation, and it is crucial to obtain SSP accurately in real time. A new scheme to improve the reconstruction performance of sound speed profile with multi-source observations using self-organizing map (SOM) method was proposed in this study. Given that the inverted echo sounder (IES) data and mix layer depth (MLD)

Learning discriminative and robust features is crucial in remote sensing image processing. Many of the currently used approaches are based on Convolutional Neural Networks (CNNs). However, such approaches may not effectively capture various different semantic objects of remote sensing images. To overcome this limitation, we propose a novel end-to-end deep multi-feature fusion network (DMFN). DMFN combines

Satellite-derived sea surface temperature (SST) presents discrepancies in both magnitude and temporal variability in the wind-driven coastal upwelling region off the Cape Frio (23°S) in Southeastern Brazil. Level 2 (L2) data from the Moderate Resolution Imaging Spectroradiometer (MODIS) Terra and Aqua, and Level 4 (L4) SST products are compared with in situ measurements. Strong positive biases up to

In this letter, we focus on the high-resolution imaging of ship targets under sparse aperture condition and its application in three-dimensional (3D) imaging. A bi-static high-resolution algorithm dealing with the sparse echo condition is proposed, which consists of the following processing steps: (1) A side-lobe apodization–multiple orthogonal least-square method is proposed to recover the complete

ABSTRACT There are a wide range of satellite sensors used for water quality measures with various spatial resolutions. Here, we focus on spatial resolution because some estuaries are smaller than the satellite nadir pixel width, and multiple pixels within an estuary are required for quality assurance . We used the United States Environmental Protection Agency’s (US EPA) Estuarine Data Mapper polygon

Internal waves represent an important mechanism of energy exchange influencing primary production through the turbulent transport of nutrients and changes in the intensity of light available for photosynthesis. Internal solitary waves (internal solitons) appear in packages and retain their shape and speed even after interacting with other internal waves. We detected solitons in the inner Patagonian

Since the conditional random field (CRF) model can integrate spectral and spatial-contextual information of high spatial resolution (HSR) remote sensing images in a unified framework, it becomes an effective approach to optimize the classification results. However, the results of traditional classification methods based on the CRF are sensitive to the parameters. In this paper, an adaptive conditional

In most remote sensing-based soil moisture (SM) retrieval methods, in-situ SM measurements are commonly used for validation purposes. Few studies have investigated whether such measurements can be used for calibration. In this paper, an observation-driven optimization method was proposed to estimate SM from remote sensing observations. Specifically, the optimization method was developed within the

A recent revision of the NASA global ocean colour record shows changes in global ocean chlorophyll trends. This new 18-year time series now includes three global satellite sensors, the Sea-viewing Wide Field of view Sensor (SeaWiFS), Moderate Resolution Imaging Spectroradiometer (MODIS-Aqua), and Visible Infrared Imaging Radiometer Suite (VIIRS). The major changes are radiometric drift correction,

On 26 December 2004, a magnitude 9.2 earthquake off the west coast of the northern Sumatra, Indonesia resulted in 160,000 Indonesians killed. We examine the Defense Meteorological Satellite Program-Operational Linescan System (DMSP-OLS) nighttime light imagery brightness values for 307 communities in the Study of the Tsunami Aftermath and Recovery (STAR), a household survey in Sumatra from 2004 to

The ability to predict an occurrence of cholera, a water-related disease, offers a significant public health advantage. Satellite based estimates of chlorophyll, a surrogate for plankton abundance, have been linked to cholera incidence. However, cholera bacteria can survive under a variety of coastal ecological conditions, thus constraining the predictive ability of the chlorophyll, since it provides

Irrigation along the Nile River has resulted in dramatic changes in the biophysical environment of Upper Egypt. In this study we used a combination of MODIS 250 m NDVI data and Landsat imagery to identify areas that changed from 2001-2008 as a result of irrigation and water-level fluctuations in the Nile River and nearby water bodies. We used two different methods of time series analysis -- principal

The effect of using spectral transform images as input data on segmentation quality and its potential effect on products generated by object-based image analysis are explored in the context of land cover classification in Accra, Ghana. Five image data transformations are compared to untransformed spectral bands in terms of their effect on segmentation quality and final product accuracy. The relationship