IEEE Transactions on Geoscience and Remote Sensing

Accurate ranging and wideband tracking are treated as two independent and separate processes in traditional radar systems. As a result, limited by low data rate due to nonsequential processing, accurate ranging usually performs low efficiency in practical application. Similarly, without applying accurate ranging, the data after thresholding and clustering are used in wideband tracking, leading to a significant decrease in tracking accuracy. In this article, an integrated Kalman filter of accurate ranging and tracking is proposed using methods of phase-derived-ranging and Bayesian inference in wideband radar. Besides the motion state, in this integrated Kalman filter, the complex-valued high-resolution range profile (HRRP) is also introduced as a reference signal by coherent integration in a sliding window, which incorporates target’s scattering distribution and phase characteristics. Corresponding kinetic equations are derived to predict the motion state and the reference signal in the next moment. A ranging process is constructed based on the received signal and the predicted reference signal in order to estimate innovation using methods of phase-derived-ranging and Bayesian inference, and a sequential update for motion state can be accomplished with the Kalman filter as well. In every recursion, the complex-valued reference signal is also updated by coherently integrating the latest pulses. The integrated Kalman filter takes full use of high range resolution and phase information, improving both efficiency and precision compared with conventional approaches of ranging and wideband tracking. Implemented in a sequential manner, the integrated Kalman filter can be applied in a real-time application, realizing simultaneous ranging with high precision and wideband tracking. Finally, simulated and real-measured experiments confirm the remarkable performance.

Land surface temperature (LST) is a key parameter for many fields of study. Currently, LST retrieved from satellite thermal infrared (TIR) measurements is attainable with an accuracy of about 1 K for most natural flat surfaces. However, over urban areas, TIR measurements are influenced by 3-D structures and their radiation that could degrade the performance of existing LST retrieval algorithms. Therefore, quantitative models are needed to investigate such impact. Current 3-D radiative transfer models are generally based on time-consuming numerical integrations whose solutions are not analytical, and are therefore difficult to exploit in the methods of physical retrieval of LST in urban areas. This article proposes an analytical TIR radiative transfer model over urban (ATIMOU) areas that considers the impact of 3-D structures and their radiation. The magnitude of this impact on TIR measurements is investigated in detail, using ATIMOU, under various conditions. Simulations show that failure to acknowledge this impact can potentially introduce a 1.87-K bias to the ground brightness temperature for street canyon whose ratio “wall height/road width” is 2, wall and road temperature is 300 K, wall emissivity is 0.906, and road emissivity is 0.950. This bias reaches 4.60 K if road emissivity decreases to 0.921, and road temperature decreases to 260 K. ATIMOU is also compared to the discrete anisotropic radiative transfer (DART) model. Small mean absolute error of 0.10 K was found between the models regarding the simulated ground brightness temperatures, indicating that ATIMOU is in good agreement with DART.

The ground-based microwave radiometer (MWR) retrieves atmospheric profiles with a high temporal resolution for temperature and humidity up to a height of 10 km. Such profiles are critical for understanding the evolution of climate systems. To improve the accuracy of profile retrieval in MWR, we developed a deep learning approach called batch normalization and robust neural network (BRNN). In contrast to the traditional backpropagation neural network (BPNN), which has previously been applied for MWR profile retrieval, BRNN reduces overfitting and has a greater capacity to describe nonlinear relationships between MWR measurements and atmospheric structure information. Validation of BRNN with the radiosonde demonstrates a good retrieval capability, showing a root-mean-square error of 1.70 K for temperature, 11.72% for relative humidity (RH), and 0.256 g/m3 for water vapor density. A detailed comparison with various inversion methods (BPNN, extreme gradient boosting, support vector machine, ridge regression, and random forest) has also been conducted in this research, using the same training and test data sets. From the comparison, we demonstrated that BRNN significantly improves retrieval accuracy, particularly for the retrieval of temperature and RH near the surface.

Monitoring airports using remote sensing imagery require us to first detect the airports and then perform airplane detection. Detecting airports and airplanes with large-scale remote sensing imagery are significant and challenging tasks in the field of remote sensing. Although many detection algorithms have been developed for detecting airports and airplanes in remote sensing imagery, the efficiency of the processing does not meet the needs of real applications in large-scale remote sensing imagery. In recent years, deep learning techniques, such as deep convolutional neural networks (DCNNs), have achieved great progress in image recognition. However, training a DCNN needs a large number of training examples to accurately fit the data distribution. Annotating training examples in large-scale remote sensing imagery is time-consuming, which makes the pipeline inefficient. In this article, to overcome the above two weaknesses, we propose a novel cycling data-driven framework for efficient and robust airport localization and airplane detection. The proposed method consists of three modules: cycling by example refinement (C), offline learning (OL), and online representation (OR), namely cycling, offline learning, and online representation (COLOR). The OR module is a coarse-to-fine cascaded convolutional neural network, which is used to detect airports and airplanes. The example refinement (ER) module implements the cycling and makes use of the unlabeled remote sensing images and the corresponding predictions obtained by the OR module, to generate training examples. The OL module aims to use the training examples from the ER module to update the OR module, to further improve the performance. The whole workflow involves COLOR. The COLOR framework was used to detect airplanes and airports in 512 large-scale Gaofen-2 (GF-2) remote sensing images with 29 $200times27$ 620 pixels. The results showed that t- e proposed method obtained a mean average precision (mAP) of 88.32% for the airplane detection. In addition due to the proposed coarse-to-fine cascaded OR module the proposed method is much faster than the traditional approaches in real-world applications.

As a preprocessing step, hyperspectral image (HSI) restoration plays a critical role in many subsequent applications. Recently, based on the framework of subspace representation and low-rank matrix/tensor factorization (LRMF/LRTF), many single-factor-regularized methods add various regularizations on the spatial factor to characterize its spatial prior knowledge. However, these methods neglect the common characteristics among different bands and the spectral continuity of HSIs. To tackle this issue, this article establishes a bridge between the factor-based regularization and the HSI priors and proposes a double-factor-regularized LRTF model for HSI mixed noise removal. The proposed model employs LRTF to characterize the spectral global low rankness, introduces a weighted group sparsity constraint on the spatial difference images (SpatDIs) of the spatial factor to promote the group sparsity in the SpatDIs of HSIs, and suggests a continuity constraint on the spectral factor to promote the spectral continuity of HSIs. Moreover, we develop a proximal alternating minimization-based algorithm to solve the proposed model. Extensive experiments conducted on the simulated and real HSIs demonstrate that the proposed method has superior performance on mixed noise removal compared with the state-of-the-art methods based on subspace representation, noise modeling, and LRMF/LRTF.

Band selection is one of the most important technique in the reduction of hyperspectral image (HSI). Different from traditional feature selection problem, an important characteristic of it is that there is usually strong correlation between neighboring bands, that is, bands with close indexes. Aiming to fully exploit this prior information, a novel band selection method called optimal neighborhood reconstruction (ONR) is proposed. In ONR, band selection is considered as a combinatorial optimization problem. It evaluates a band combination by assessing its ability to reconstruct the original data, and applies a noise reducer to minimize the influence of noisy bands. Instead of using some approximate algorithms, ONR exploits a recurrence relation that underlies the optimization target to obtain the optimal solution in an efficient way. Besides, we develop a parameter selection approach to automatically determine the parameter of ONR, ensuring it is adaptable to different data sets. In experiments, ONR is compared with some state-of-the-art methods on six HSI data sets. The results demonstrate that ONR is more effective and robust than the others in most of the cases.

Topographic correction is a prerequisite for generating radiometrically consistent Landsat 8 OLI vegetation reflectances in support of temporally continuous and spatially mosaicked applications. Path length correction (PLC) is a physically solid topographic correction method that avoids the involvement of any empirical parameter and is therefore suitable for reproducing the inherent reflectance of vegetation. This article compared two different implementation pathways of PLC, i.e., the explicit method (EM) and the implicit method (IM), which are based on the numerical inverse and analytical approximation of the PLC model, respectively. The results show that both EM and IM can obviously reduce the topographic effects on Landsat 8 OLI vegetation reflectances. EM performed slightly better than IM in eliminating the correlation between the topographic characteristics and the vegetation reflectances: the coefficient of determination between the green/red/near-infrared (Nir) band reflectance and the local illumination was reduced from 0.257/0.148/0.467 for the uncorrected (UNCORR) case to 0.016/0.004/0.012 and 0.027/0.014/0.094 for the EM and IM corrected results, respectively. The coefficient of variation of the three band reflectances across different aspects was reduced from 16.5%/18.5%/18.7% for the UNCORR case to 3.2%/1.8%/0.9% and 5.3%/7.1%/7.3% for the EM and IM corrected results, respectively. In addition, the intraclass reflectance variability was also reduced after both the EM and IM corrections. Nevertheless, due to the ill-posed nature of the numerical inverse process, EM cannot fully reproduce the inherent vegetation reflectances, and the reflectances after topographic correction overestimated the inherent vegetation values. In contrast, the IM can achieve an appropriate tradeoff between topographic effect elimination and vegetation inherent reflectance preservation. In addition, IM is computationally very efficient compared to EM: using an ordinary laptop, - M can finish the topographic correction for a Landsat OLI image within several seconds, while this would take more than 20 h for EM. This article highlights the potential of using IM for generating radiometrically consistent Landsat 8 OLI vegetation reflectances.

Cloud detection, as an important preprocessing operation for remote sensing (RS) image analysis, has received increasing attention in recent years. Most of the previous cloud detection methods consider the detection as a pixel-wise image classification problem (cloud versus background), which inevitably leads to a category-ambiguity when dealing with the detection of thin clouds. In this article, starting from the RS imaging mechanism on cloud images, we re-examine the cloud detection under a totally different point of view, i.e., to formulate cloud detection as a mixed energy separation between foreground and background images. This process can be further equivalently implemented under a deep learning-based image matting framework with a clear physical significance. More importantly, the proposed method is capable to deal with three different but related tasks, i.e., “cloud detection,” “cloud removal,” and “cloud cover assessment,” under a unified framework. The experimental results on the three satellite image data sets demonstrate the effectiveness of our method, especially for those hard but common examples in RS images, such as the thin and wispy cloud.

Hyperspectral anomaly detection is one of the most active topics in hyperspectral image (HSI) analysis. The fine spectral information of HSIs allows us to uncover anomalies with very high accuracy. Recently, an intrinsic image decomposition (IID) model has been introduced for low-rank IID (LRIID) in multispectral images. Inspired by the LRIID, which is able to effectively recover the reflectance and shading components of the multispectral image, this article adapts the LRIID for obtaining the reflectance component of HSIs (which is the key feature for the discrimination of different objects). In order to exploit the reflectance component, we also propose a new dual window density (DWD)-based detector for anomaly detection, which is based on the idea that anomalies are usually rare pixels and, thus, exhibit low density in the image. The density analysis of DWD is intended not only to circumvent the Gaussian assumption regarding the distribution of HSI data, but also to mitigate the contamination of background statistics caused by anomalies. The dual window operation of our DWD is specifically designed to adaptively calculate the density of each pixel under test, so as to identify anomalies with nonspecific sizes. Our experimental results, obtained on a database of real HSIs including Airport, Beach, and Urban scenes, demonstrate the superiority of the proposed method in terms of detection performance when compared to other widely used anomaly detection methods.

Geosynchronous synthetic aperture radar (GEO SAR)-related technologies are being mature, and the first GEO SAR satellite is expected to launch in the next ten years. Under this circumstance, some equivalent experiments should be conducted at the current stage to validate some key characteristics or parameters, which could significantly increase the success possibility of the GEO SAR project. To validate the feasibility of GEO SAR imaging with long integration time, which is the most important and fundamental characteristic of GEO SAR, the first helicopter platform-based equivalent GEO SAR experiment with long integration time was performed in Qianxi County of China on May 22, 2019. The integration time of it is 80 s, which is carefully designed to maintain the consistence between itself and the integration time of the GEO SAR. Furthermore, the azimuth signal-to-noise ratio gain with long synthetic aperture time is analyzed. Moreover, the 2-D space-variant motion error introduced by the complex helicopter trajectory and the performances of different imaging algorithms are analyzed to choose the proper imaging algorithms; to overcome the flaws and unclarities of existing algorithms, some improvements are proposed to obtain the well-focused SAR image. What is more, the equivalence of this experiment is also analyzed detailedly to demonstrate the effectiveness of this experiment. At last, the imaging result with synthetic aperture time of 100 s and the comparison between itself and the optic photograph validate the success of this equivalent experiment and the feasibility of GEO SAR imaging with long integration time.

Environmental trace gas monitoring instrument (EMI) onboard GaoFen-5 was launched in May 2018 and has successfully operated on-orbit for more than a year. EMI contains four grating spectrometers, covering wavelengths in the range 240-710 nm with a spectral resolution of 0.3-0.5 nm, and enables one-day global coverage. For EMI on-orbit calibration, two onboard solar diffusers (SD), one surface reflectance aluminum diffuser, and one quartz volume diffuser (QVD) are used to measure solar spectra. The solar spectra are used to perform accurate spectral and radiometric calibrations. EMI on-orbit spectral calibration contains wavelength calibration and instrument spectral response function (ISRF), both of which are the key quantities in trace gas retrievals based on differential optical absorption spectroscopy (DOAS) analysis. The wavelength calibration is performed using the Fraunhofer lines in the solar spectrum, and the ISRF parameters are obtained by fitting high-resolution and EMI-measured solar spectra. Based on the known solar irradiation and characteristic of SD, SD radiance can be calculated and is used for EMI on-orbit radiometric calibration. The radiometric calibration also determines the absolute Earth reflectance spectra that are used as inputs for atmospheric retrieval algorithms. For EMI on-orbit radiometric monitoring, aluminum diffuser is used as reference SD to monitor QVD degradation. An internal white light source is used to detect pixel performance and monitor radiometric throughput.

Satellite-based microwave sensors that respond to the vertical distribution of hydrometeors have been continuously employed in the investigation of precipitation systems characteristics. Rain/no-rain classification (RNC) methods often are either applied before retrieving precipitation information from a number of algorithms based on passive microwave measurements or adopted to build the precipitation event-based databases. As a simple rain indicator, the polarized corrected temperature (PCT) at 89-GHz (PCT89) method using the global precipitation measurement (GPM) microwave imager (GMI) has been employed by many researchers, because it can estimate the scattering intensity while minimizing the effects of the surface emissivity at high resolution. This article presents a new consideration using the PCT89-based RNC method through statistical verification. Precipitating clouds were subdivided into 11 types (three stratiform types and four convective types) by the GPM dual frequency precipitation radar (DPR) precipitation classification algorithm. Quantitative comparison of verification results was performed in the tropics from January to December 2015 and major sources of uncertainty were analyzed from the perspective of the precipitation mechanism. Results showed a tendency of false identification for stratiform types except for those located near the convective core, and thus the method was susceptible to failure in the identification of convective types. Consequently, this method leads to an increase of 70% and 54% in the number of two significant stratiform types compared to DPR, while the convective types decreased by up to 53%. This article suggests that the precipitations identified by the PCT89 have features that enhance the bias toward the stratiform type.

This article introduces the task of visual question answering for remote sensing data (RSVQA). Remote sensing images contain a wealth of information, which can be useful for a wide range of tasks, including land cover classification, object counting, or detection. However, most of the available methodologies are task-specific, thus inhibiting generic and easy access to the information contained in remote sensing data. As a consequence, accurate remote sensing product generation still requires expert knowledge. With RSVQA, we propose a system to extract information from remote sensing data that is accessible to every user: we use questions formulated in natural language and use them to interact with the images. With the system, images can be queried to obtain high-level information specific to the image content or relational dependencies between objects visible in the images. Using an automatic method introduced in this article, we built two data sets (using low- and high-resolution data) of image/question/answer triplets. The information required to build the questions and answers is queried from OpenStreetMap (OSM). The data sets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task. We report the results obtained by applying a model based on convolutional neural networks (CNNs) for the visual part and a recurrent neural network (RNN) for the natural language part of this task. The model is trained on the two data sets, yielding promising results in both cases.

Despite the successful applications of probabilistic collaborative representation classification (PCRC) in pattern classification, it still suffers from two challenges when being applied on hyperspectral images (HSIs) classification: 1) ineffective feature extraction in HSIs under noisy situation; and 2) lack of prior information for HSIs classification. To tackle the first problem existed in PCRC, we impose the sparse representation to PCRC, i.e., to replace the 2-norm with 1-norm for effective feature extraction under noisy condition. In order to utilize the prior information in HSIs, we first introduce the Euclidean distance (ED) between the training samples and the testing samples for the PCRC to improve the performance of PCRC. Then, we bring the coordinate information (CI) of the HSIs into the proposed model, which finally leads to the proposed locality regularized robust PCRC (LRR-PCRC). Experimental results show the proposed LRR-PCRC outperformed PCRC and other state-of-the-art pattern recognition and machine learning algorithms.

In this article, the terrain classifications of polarimetric synthetic aperture radar (PolSAR) images are studied. A novel semi-supervised method based on improved Tri-training combined with a neighborhood minimum spanning tree (NMST) is proposed. Several strategies are included in the method: 1) a high-dimensional vector of polarimetric features that are obtained from the coherency matrix and diverse target decompositions is constructed; 2) this vector is divided into three subvectors and each subvector consists of one-third of the polarimetric features, randomly selected. The three subvectors are used to separately train the three different base classifiers in the Tri-training algorithm to increase the diversity of classification; and 3) a help-training sample selection with the improved NMST that uses both the coherency matrix and the spatial information is adopted to select highly reliable unlabeled samples to increase the training sets. Thus, the proposed method can effectively take advantage of unlabeled samples to improve the classification. Experimental results show that with a small number of labeled samples, the proposed method achieves a much better performance than existing classification methods.

The surface mass balance (SMB) of West Antarctica is an important glaciological input to understanding polar climate and sea-level rise but with historically poor in situ data coverage. Previous studies demonstrate the utility of frequency-modulated continuous-wave radar to image subsurface layering in ice sheets, providing an additional source of data with which to estimate SMB. Traditional methods, however, require time-intensive manual oversight. Here, we present a probabilistic, fully automated approach to estimate annual SMB and uncertainties from radar echograms using successive peak-finding and weighted neighborhood search algorithms with the Monte Carlo simulations based on annual-layer likelihood scores. We apply this method to ground-based and airborne radar in a 175-km transect of the West Antarctic interior and compare the results to traditional manual methods and independent estimates from firn cores. The method demonstrates an automated estimation of SMB across a range of accumulation rates (100-450-mm water equivalent per year) and layer gradients up to 2 m/km. Based on likelihood-weighted F-scores, automated layer picks have a success rate between 64% and 84.6% compared with manually picked layers for three validation sites dispersed across the region. Comparisons between the automated SMB estimates and independent firn cores show a bias of 24 ± 70-mm water equivalent per year (12% ± 35% water equivalent of the in situ mean accumulation rate) although individual core site biases differ. This new approach permits the fully automated extraction of annual SMB rates and should be broadly and readily applicable to previously collected and ongoing radar data sets across polar regions.

Infrared (IR) information is fundamental to global precipitation estimation. Although researchers have developed numerous IR-based retrieval algorithms, there is still plenty of scope for promoting their accuracy. This article develops a novel deep learning-based algorithm entitled infrared precipitation estimation using a convolutional neural network (IPEC). Based on the five-channel IR data, the IPEC first identifies the precipitation occurrence and then estimates the precipitation rates at hourly and 0.04° × 0.04° resolutions. The performance of the IPEC is validated using the Stage-IV radar-gauge-combined data and compared to the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) in three subregions over the continental United States (CONUS). The results show that the five-channel input is more efficient in precipitation estimation than the commonly used one-channel input. The IPEC estimates based on the five-channel input show better statistical performance than the PERSIANN-CCS with 34.9% gain in Pearson's correlation coefficient (CC), 38.0% gain in relative bias (BIAS), and 45.2% gain in mean squared error (MSE) during the testing period from June to August 2014 over the central CONUS. Furthermore, the optimized IPEC model is applied in totally independent periods and regions, and still achieves significantly better performance than the PERSIANN-CCS, indicating that the IPEC has a stronger generalization capability. On the whole, this article proves the effectiveness of the convolutional neural network (CNN) combined with the physical multichannel inputs in IR precipitation retrieval. This end-to-end deep learning algorithm shows the potential for serving as an operational technique that can be applied globally and provides a new perspective for the future development of satellite precipitation retrievals.

Synchrosqueezing transform (SST) is an effective time–frequency analysis (TFA) approach for the processing of nonstationary signals. The SST shows a satisfactory ability of the TF localization of the nonlinear signal with a slowly time-varying instantaneous frequency (IF). However, for the signal of which ridge curves in the TF domain are fast varying, or even almost parallel to the frequency axis, the SST will provide a blurred TF representation (TFR). To solve this issue, the transient-extracting transform (TET) was recently put forward. The TET can effectively characterize and extract transient features in the much concentrated TFR for the strongly frequency-modulated (FM) signal, especially the impulse-like signal. However, contrary to the SST, it is not suitable for weak FM modes. In this study, we propose a TFA method called the time-synchroextracting general chirplet transform (TEGCT). The TEGCT can achieve a highly concentrated TFR for strong FM signals as well as weak FM ones. Quantized indicators, the concentration measurement and the peak signal-to-noise ratio, are used to analyze the performances of the proposed method compared with those of other methods. The comparisons show that the TEGCT can provide a result with better TF localization. Then, the proposed method was applied to the spectrum analysis of the seismic data for oil reservoir characteristics. The horizontal slices of the offshore 3-D seismic data show that the TEGCT delineates more distinct and continuous subsurface channels in a fluvial-delta deposition system. All the results illustrate that our proposed method is a good potential tool for seismic processing and interpretation in the geoscience.

Powerline inspection is an important task for electric power management. Corridor mapping, i.e., the task of surveying the surroundings of the line and detecting potentially hazardous vegetation and objects, is performed by aerial light detection and ranging (LiDAR) survey. To this purpose, the main tasks are automatic extraction of the wires and measurement of the distance of objects close to the line. In this article, we present a new fully automated solution, which does not use time-consuming line fitting method, but is based on simple geometrical assumptions and relies on the fact that wire points are isolated, sparse and widely separated from all other points in the data set. In particular, we detect and classify pylons by local-maxima strategy. Then, a new reference system, having its origin on the first pylon and $y$ -axis toward the second one, is defined. In this new reference system, transverse sections of the raw point cloud are extracted; by iterating such procedure for all detected pylons, we are able to detect the wire bundle. Obstacles are then automatically detected according to corridor mapping requirements. The algorithm is tested on two relevant data sets.

Longwave infrared (LWIR) spectroscopy is useful for detecting and identifying hazardous clouds by passive remote sensing technology. Gaseous constituents are usually assumed to be thin plumes in a three-layer model, from which the spectral signatures are linearly superimposed on the brightness temperature spectrum. However, the thin-plume model performs poorly in cases of thick clouds. A modification to this method is made using synthetic references as target spectra, which allow linear models to be used for thick clouds. The prior background, which is generally unknown in most applications, is reconstructed through a regression method using predefined references. However, large residuals caused by fitting errors may distort the extracted spectral signatures and identification results if the predefined references are not consistent with the real spectral shapes. A group of references are generated to represent the possible spectral shapes, and the least absolute shrinkage and selection operator (LASSO) method is used to select the most appropriate reference for spectral fitting. Small residuals and adaptive identification are achieved by automatically selecting the reference spectrum. Two experiments are performed to verify the algorithm proposed in this article. Ethylene is adaptively detected during an indoor release process, and the spectral shape varies with the amount released. In addition, ammonia is measured under different humidity conditions, and the background is adaptively removed using the LASSO method. Based on this research, LWIR remote sensing technology can be applied in various target-detection scenarios, and adaptive identification is achieved to promote hazardous cloud detection.