Search

Among the existing circularly polarized multibeam transmitarray antennas, circularly or linearly-tocircularly polarized transmitarray units are always required. Naturally, designing circularly polarized units is more challenging than linear polarization. To simplify design and increase operation bandwidth, a novel method using linearly polarized transmitarray units and feeding sources is proposed for designing the circularly polarized multi-beam antenna. Broadband circular polarization is realized by utilizing sequential rotation technology and 1-bit phase compensation of linearly polarized transmitarray units. Meanwhile, beam scanning is achieved by using linearly polarized feeding sources offset. To validate the design, two multi-beam antenna samples are demonstrated. Simulated and measured results show that the designed multi-beam transmitarray antennas can realize beam scanning to 0°, ±10°, and ±20° in E-plane and H-plane. Moreover, two antennas maintain –10-dB impedance bandwidth and 3-dB axial ratio (AR) bandwidth at 8.5–10.4 GHz and 8.5–10.5 GHz, respectively. The proposed circularly polarized multi-beam transmitarray antennas have the advantages of broadband operation, simple design, and low cost. [ABSTRACT FROM AUTHOR]

Ship detection in synthetic aperture radar (SAR) images have important applications in military and civil fields. Nonetheless, SAR images usually suffer from the disadvantage of having limited labeled samples. This is undoubtedly a challenge for the deep learning based methods, which require a large number of samples for training. To solve this problem, many researchers have applied the domain adaptation (DA) methods for the SAR ship detection tasks, which use optical images as the source domain and transform optical images to SAR domain directly. However, there is large difference between SAR and optical images. Hence, the deep learning detector may not be able to learn the target features accurately when the transformed images are used for training. In order to solve above problem, a novel ship detection method with limited labeled samples is proposed, whose training and test process is mainly implemented in the optical domain. In the training stage, optical images are used to pre-train the model. Here, the transformed optical images from SAR images are used to further fine-tune the pre-trained model. Accordingly, in the test stage, SAR images are transformed to optical domain and input in the model to obtain the detection results. Experimental results based on the real dataset demonstrate the effectiveness of the proposed method for SAR ship detection. [ABSTRACT FROM AUTHOR]

In developing countries the growth in the number of motor vehicles is the most significant factor in the rise of road fatalities and injuries. It may be observed that 1.35 million people die every year owing to crashes on road. Most of the accidents can be prevented if the events are detected automatically 1-2 seconds in advance. Texas instruments has come up with a new evaluation board AWR2243 having a single chip operating at 76 to 81Ghz having a FMCW transceiver. This can be instrumental in adaptive cruise control, emergency braking and automated highway driving. A FMCW (frequency modulated continuous wave) obtains the range and velocity from a beat signal. Here millimeter-wave sensors use minimal power consumption to sense range and velocity and the required angle. The device is interfaced to an external DSP host processor which uses a SYNC_IN signal to start the radar frames. The periodicity of the frames is suitability programmed. The processing provides a high level of performance and flexibility. The signal has three parallel transmit chains and four parallel receive chains. Each receive channel has an LNA, mixer, IF filtering, A2D conversion and decimation. A two- dimensional FFT algorithm is implemented on the host DSP processor. [ABSTRACT FROM AUTHOR]

A dual port Cylindrical Dielectric Resonator Antenna (CDRA) has been demonstrated for point-to-point communication link in K band (22 GHz) applications in this work. The antenna offers polarization diversity which is introduced by degenerating HEjjg modes in a single CDRA. Orthogonal feed lines produce two modes which are perpendicular so they do not interfere with each other and offer excellent linear polarization diversity in orthogonal planes. Since the CDRA size is compact, the feed lines have been modified to ensure the generation of desired modes. A detailed investigation into the generation of resonant modes along with parametric analysis is presented. Measured results show fractional bandwidth of 9.5% and 18.18% for port 1 and port 2 respectively. Isolation of better than 32 dB has been measured between the two ports through transmission coefficient. Difference of about 20 dB between co-polarization and cross polarization powers in both planes for broadside direction has been measured which endorses the polarization diversity performance of the antenna. Different M1MO performance parameters including envelope correlation coefficient, total active reflection coefficient, channel capacity loss and mean effective gain have been measured to assess the performance of the design. [ABSTRACT FROM AUTHOR]

Copyright of Ciencia e Ingenieria Neogranadina is the property of Ciencia e Ingenieria Neogranadina and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Image stitching combines multiple overlapping scenes into a panorama. It can be applied in video stitching, superresolution, and medical imaging. Post-processing routines such as exposure compensation, seam line adjustment, and blending are often performed to increase its visual appeal. Our aim is to increase the registration accuracy between adjacent image pairs in a stitching algorithm. This is done by adding an area-based registration step, namely Enhanced Correlation Coefficient (ECC), which refines the original feature-based image registration. The performance of registrations in the stitching algorithm is evaluated using root-mean-squared error of control points, structural similarity index, and universal image quality index. The Boat and Graffiti datasets from the Oxford Robotics Database are used for experiments. It is found that ECC largely improves registrations in stitching except for a slight increase in root-mean-squared error of control points in the Boat dataset. In addition, ECC's enhancement makes the registration outperform the ground truth in one image of both datasets. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper proposes a method for augmenting learning data of road damage dataset considering the influence of the augmented data on classification accuracy. Data augmentation is a very important task in the field of machine learning because more learning data causes increasing the accuracy of classification accuracy in general. The quality of the augmented data influences the accuracy of the classification. Effective data augmentation method for increasing classification accuracy is needed. The proposed method generates learning data by selecting effective data augmentation methods depending on the class of road damage. The method uses You Only Look Once v3 (YOLOv3) for detection and classification of road damage in an image. It is tuned by data adding the data augmented by the proposed method to the road damage dataset presented to the public. The experimental results show that the proposed method can increase the accuracy efficiently and effectively. The proposed selection of data augmentation methods improves remarkably mean Average Precision (mAP) which is one of the accuracy indices. [ABSTRACT FROM AUTHOR]

Highlights • Used the newly constructed index to extract visible light remote sensing image. • Used the iterative threshold method of vegetation and none vegetation classification. • Extract vegetation information from greyscale images. Abstract Currently, many remote sensing images of the vegetation index being used have disadvantages, because of high cost, long cycles, and low resolution. Thus, it is difficult to extract and analyse vegetation information in the field. A vegetation index based on visible light images from an unmanned aerial vehicle (UAV) has the advantages of fast image acquisition and high ground resolution, which is superior to traditional remote sensing. However, the vegetation coverage in arid and semi-arid areas is low, and the soil background has a great impact on the common visible vegetation index. The real-time extraction and analysis of the index vegetation information can easily result in big errors. Therefore, according to the construction principle of the green-red vegetation index (GRVI) and modified green-red vegetation index (MGRVI), a new green-red vegetation index (NGRVI) is proposed in this study. First, the newly constructed index and several published indices are used to extract visible light images and generate greyscale images for each of the visible light vegetation indices. Then, the threshold of vegetation and non-vegetation pixel classification is established according to the method of iterative threshold, and the optimal threshold is used to extract the vegetation information from the greyscale images of each of the visible light vegetation indices. Finally, the accuracy difference in vegetation information extraction between the newly constructed and several published indices is compared. The results show that the precision of vegetation information extraction by NGRVI is higher than that of other visible light band vegetation indices; the kappa coefficient is 0.82, and the classification accuracy reaches near-complete consistency. To verify the accuracy of the NGRVI, one image from the same period was selected, and the vegetation information was extracted using the same method. The NGRVI based on UAV visible light images can accurately extract the vegetation information in arid and semi-arid areas, and the extraction accuracy can reach more than 90%. To summarize, NGRVI can accurately and effectively reflect the vegetation information in arid and semi-arid areas and become an important technical means for retrieving biological and physical parameters using visible light images. [ABSTRACT FROM AUTHOR]

Spectral imagery using micro-unmanned aerial vehicles is rapidly advancing. This study compared reflectance calibration methods for imagery acquired using the Parrot Sequoia imager, a commercial multispectral sensor package. For the study, two orthomosaics were calibrated using 1) a manufacturer-suggested AIRINOV standard correction using PIX4D software and 2) the Empirical Line Calibration (ELC) method using ground radiometric data on specific in-scene targets. Both scenes were analyzed for target spectral agreement by ground radiometric survey. Regression analysis demonstrated more favorable target correlation for the ELC imagery than the AIRI- NOV-calibrated imagery, with Root Mean Square Error (RMSE) analysis supporting these results. Finally, classification maps were produced between the data sets. Error analysis resulted in an overall accuracy of 24% for the AIRINOV map compared to ELC-based truth data, with a considerable number of pixels associated with brighter targets unclassified. These results demonstrate the need for standardized calibration procedures in the spectral correction of small-format remote sensor data. [ABSTRACT FROM AUTHOR]

Abstract It is already been testified that, with the help of corrugations, depolarizing trihedral corner reflectors can be applied in polarization stimulation of targets. However, how to choose the size of the reflector to stimulate a target is still indistinct. A method of choosing size of depolarizing trihedral corner reflector based on the target data is presented in this article, helping to find the suitable reflectors to realize the polarization stimulation of the target. [ABSTRACT FROM AUTHOR]

In many engineering domains, cognition is emerging to play vital role. Cognition will play crucial role in radar engineering as well for the development of next generation radars. In this paper, a cognitive architecture for radars is introduced, based on hybrid cognitive architectures. The paper proposes deep learning applications for integrated target classification based on high-resolution radar range profile measurements and target revisit time calculation as case studies. The proposed architecture is based on the artificial cognitive systems concepts and provides a basis for addressing cognition in radars, which is inadequately explored for radar systems. Initial experimental studies on the applicability of deep learning techniques under this approach provided promising results. [ABSTRACT FROM AUTHOR]

Motion blur in images usually distorts the information of objects, thus degrading the performance of semantic segmentation. However, there is no previous research on improving the segmentation performance by restoring the frontal-viewing vehicle-camera images taken under motion blur. Therefore, this study proposes a supervised dual attention network for multi-stage motion deblurring (SDAN-MD) for this task. In SDAN-MD, a supervised dual attention module (SDAM) is proposed, which adopts the supervised spatial and channel attention mechanisms to provide a supervisory signal of ground truth. In addition to Charbonnier loss and edge loss, we use perceptual loss utilizing Euclidean distance based on feature maps obtained from the segmentation network. Experiments were conducted with the motion blurred databases from the two open databases of road scene, Cambridge driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI).The results show that the proposed SDAN-MD achieves 92.89% and 87.27% pixel accuracies in semantic segmentation using these two databases, respectively, outperforming the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper describes the simulation and real data analysis results from the recently launched SAR satellites, ALOS-2, Sentinel-1 and Radarsat-2 for the purpose of monitoring subsidence induced by longwall mining activity using satellite synthetic aperture radar interferometry (InSAR). Because of the enhancement of orbit control (pairs with shorter perpendicular baseline) from the new satellite SAR systems, the mine subsidence detection is now mainly constrained by the phase discontinuities due to large deformation and temporal decorrelation noise. This paper investigates the performance of the three satellite missions with different imaging modes for mapping longwall mine subsidence. The results show that the three satellites perform better than their predecessors. The simulation results show that the Sentinel-1A/B constellation is capable of mapping rapid mine subsidence, especially the Sentinel-1A/B constellation with stripmap (SM) mode. Unfortunately, the Sentinel-1A/B SM data are not available in most cases and hence real data analysis cannot be conducted in this study. Despite the Sentinel-1A/B SM data, the simulation and real data analysis suggest that ALOS-2 is best suited for mapping mine subsidence amongst the three missions. Although not investigated in this study, the X-band satellites TerraSAR-X and COSMO-SkyMed with short temporal baseline and high spatial resolution can be comparable with the performance of the Radarsat-2 and Sentinel-1 C-band data over the dry surface with sparse vegetation. The potential of the recently launched satellites (e.g. ALOS-2 and Sentinel-1A/B) for mapping longwall mine subsidence is expected to be better than the results of this study, if the data acquired from the ideal acquisition modes are available. [ABSTRACT FROM AUTHOR]

Fast and accurate estimation of rice yield plays a role in forecasting rice productivity for ensuring regional or national food security. Microwave synthetic aperture radar (SAR) data has been proved to have a great potential for rice monitoring and parameters retrieval. In this study, a rice canopy scattering model (RCSM) was revised and then was applied to simulate the backscatter of rice canopy. The combination of RCSM and genetic algorithm (GA) was proposed for retrieving two important rice parameters relating to grain yield, ear length and ear number density, from a C-band, dual-polarization (HH and HV) Radarsat-2 SAR data. The stability of retrieved results of GA inversion was also evaluated by changing various parameter configurations. Results show that RCSM can effectively simulate backscattering coefficients of rice canopy at HH and HV mode with an error of <1 dB. Reasonable selection of GA’s parameters is essential for stability and efficiency of rice parameter retrieval. Two rice parameters are retrieved by the proposed RCSM-GA technology with better accuracy. The rice ear length are estimated with error of <1.5 cm, and ear number density with error of <23 #/m 2 . Rice grain yields are effectively estimated and mapped by the retrieved ear length and number density via a simple yield regression equation. This study further illustrates the capability of C-band Radarsat-2 SAR data on retrieval of rice ear parameters and the practicability of radar remote sensing technology for operational yield estimation. [ABSTRACT FROM AUTHOR]

The goal of this research was to classify four wetland types in the Hudson Bay Lowlands in northern Canada using Radarsat-2 quad-polarization and Landsat-8 satellite sensor data and geomorphometric variables extracted from an airborne lidar digital elevation model. Segmentation was followed by object-based image classification implemented with a Random Forest machine learning algorithm. The classification accuracy was determined to be approximately 91 percent. This is a significant improvement over the accuracy that was obtained using the Radarsat-2 (80 percent) or Landsat-8 sensor data alone (84 percent). Variable importance (VI) was measured for geomorphometric measures related to the gravity-, wind- and solar-fields, which were developed to explain eco-hydrological differences and increase the separability of wetland classes. Further research will consider additional geomorphometric and spectral response variables that are useful in more detailed boreal wetland classifications and analysis of wetland characteristics over time. [ABSTRACT FROM AUTHOR]

The integrated use of multiple Synthetic Aperture Radar (SAR) platforms for the deformation monitoring via satellite radar interferometry offers several perspectives for investigation of the behaviour of new and ageing structures, such as buildings and infrastructures, under varying or hazardous environment. Spanning almost 24 years of space-borne radar observations, this study aims to perform classical PSInSAR (Persistent Scatterer Interferometric Synthetic Aperture Radar) analysis incorporating measurements of ERS, Envisat, TerraSAR-X, Sentinel-1A and Radarsat-2 satellites. The results from the processing of different sensing geometries over Bratislava (Slovakia) urban area are presented, focusing on the description of characteristics associated with the specifics of every satellite platform in use. The discussion over technical feasibility of infrastructure monitoring is accompanied by the outline of possible future needs for the utilisation of the wealth source of information provided by the satellite radar imagery. [ABSTRACT FROM AUTHOR]

This paper presents a novel method for supervised water-body extraction and water-body types identification from Radarsat-2 fully polarimetric (FP) synthetic aperture radar (SAR) data in complex urban areas. First, supervised water-body extraction using the Wishart classifier is performed, and the false alarms that are formed in built-up areas are removed using morphological processing methods and spatial contextual information. Then, the support vector machine (SVM), the classification and regression tree (CART), TreeBagger (TB), and random forest (RF) classifiers are introduced for water-body types (rivers, lakes, ponds) identification. In SAR images, certain other objects that are misclassified as water are also considered in water-body types identification. Several shape and polarimetric features of each candidate water-body are used for identification. Radarsat-2 PolSAR data that were acquired over Suzhou city and Dongguan city in China are used to validate the effectiveness of the proposed method, and the experimental results are evaluated at both the object and pixel levels. We compared the water-body types classification results using only shape features and the combination of shape and polarimetric features, the experimental results show that the polarimetric features can eliminate the misclassifications from certain other objects like roads to water areas, and the increasement of classification accuracy embodies at both the object and pixel levels. The experimental results show that the proposed methods can achieve satisfactory accuracies at the object level [89.4% (Suzhou), 95.53% (Dongguan)] and the pixel level [96.22% (Suzhou), 97.95% (Dongguan)] for water-body types classification, respectively. [ABSTRACT FROM AUTHOR]

Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis. However, its robustness may be questioned because of the small size of the training datasets. Though the issue could be solved by data augmentation, polarization modalities are subject to physical feasibility constraints unaddressed by classical data augmentation techniques. To address this issue, we propose to use CycleGAN, an image translation technique based on deep generative models that solely relies on unpaired data, to transfer large labeled road scene datasets to the polarimetric domain. We design several auxiliary loss terms that, alongside the CycleGAN losses, deal with the physical constraints of polarimetric images. The efficiency of this solution is demonstrated on road scene object detection tasks where generated realistic polarimetric images allow to improve performances on cars and pedestrian detection up to 9%. The resulting constrained CycleGAN is publicly released, allowing anyone to generate their own polarimetric images. • We propose the first framework for generating physical polarization-encoded. • We propose a technique for handling physical constraints in the generated images. • We show that these images help improving performances for an object-detection task. [ABSTRACT FROM AUTHOR]

The feasibility of monitoring lodging of wheat fields by exploiting fully polarimetric C-band radar images has been investigated in this paper. A set of backscattering intensity features and polarimetric features, derived by target decomposition techniques, was extracted from 5 consecutive Radarsat-2 images. The temporal evolutions of these features of lodging wheat fields were investigated as a function of DAS (day after sowing) during the entire growing season. The temporal behavior was compared between typical lodging fields and normal fields in different growing stages. It was found that polarimetric feature from synthetic aperture radar (SAR) data was very sensitive to wheat lodging. Then a method called polarimetric index, availing the sensitivity of polarimetry to the structure, was put forward to monitor wheat lodging. The method was validated by two sets of in situ data collected in Shangkuli Farmland area, Inner Mongolia, China, at heading and ripe stages of spring wheat. Almost all the lodging fields were successfully distinguished from normal fields. Furthermore, the result revealed that the polarimetric index can reflect the intrinsic feature of lodging wheat with good anti-inference ability such as wheat growth difference. While optical sensors relied on its spectral features to monitor crop lodging, the proposed method based on radar data utilized polarimetric features to monitor crop lodging. [ABSTRACT FROM AUTHOR]

The problem of optimal range-only localisation of a single target is of considerable interest in two-dimensional search radar networking. For coping with this problem, a range-only target localisation method using synchronous measurements from radars is presented in the real ellipsoidal earth model. In the relevant radar localisation scenario, geometric relationships between the target and three radars were formed. A set of localisation equations was derived on range error in such a scenario. Using these equations, the localisation task has been formulated as a nonlinear weighted least squares problem that can be performed using the Levenberg-Marquardt (LM) algorithm to provide the optimal estimate of the target's position. To avoid the double value solutions and to accelerate the convergence speed for the LM algorithm, the initial value was approximately given according to observations from two radars. In addition, the relative validity has been defined to evaluate the performance of the proposed method. The performance of the proposed approach is evaluated using two simulation experiments and a real-test experiment, and it has been found to possess higher localisation accuracy than the other conventional method. [ABSTRACT FROM AUTHOR]

Quantification of precipitation is currently an important factor for agriculture but also for flood forecasting. In meteorology there is a strong interest in automatic stations and in replacing manually operated precipitation gauges with automated ones. This article mainly deals with measuring precipitation using radar (Radio Detection and Ranging). Standard weather radars can measure precipitation in a large territory, but to measure the local precipitation a vertically pointing radar is more suited. These types of radars use the Doppler effect to measure the speed of falling drops. The article describes some existing radar units, which allow automatic measurement of the present local rainfall. The common principles and methods for measuring precipitation will also be shown. [ABSTRACT FROM AUTHOR]

Flooding is a particular hazard in urban areas worldwide due to the increased risks to life and property in these regions. Synthetic Aperture Radar (SAR) sensors are often used to image flooding because of their all-weather day–night capability, and now possess sufficient resolution to image urban flooding. The flood extents extracted from the images may be used for flood relief management and improved urban flood inundation modelling. A difficulty with using SAR for urban flood detection is that, due to its side-looking nature, substantial areas of urban ground surface may not be visible to the SAR due to radar layover and shadow caused by buildings and taller vegetation. This paper investigates whether urban flooding can be detected in layover regions (where flooding may not normally be apparent) using double scattering between the (possibly flooded) ground surface and the walls of adjacent buildings. The method estimates double scattering strengths using a SAR image in conjunction with a high resolution LiDAR (Light Detection and Ranging) height map of the urban area. A SAR simulator is applied to the LiDAR data to generate maps of layover and shadow, and estimate the positions of double scattering curves in the SAR image. Observations of double scattering strengths were compared to the predictions from an electromagnetic scattering model, for both the case of a single image containing flooding, and a change detection case in which the flooded image was compared to an un-flooded image of the same area acquired with the same radar parameters. The method proved successful in detecting double scattering due to flooding in the single-image case, for which flooded double scattering curves were detected with 100% classification accuracy (albeit using a small sample set) and un-flooded curves with 91% classification accuracy. The same measures of success were achieved using change detection between flooded and un-flooded images. Depending on the particular flooding situation, the method could lead to improved detection of flooding in urban areas. [ABSTRACT FROM AUTHOR]

Early and on-going crop production forecasts are important to facilitate food price stability for regions at risk, and for agriculture exporters, to set market value. Most regional and global efforts in forecasting rely on multiple sources of information from the field. With increased access to data from spaceborne Synthetic Aperture Radar (SAR), these sensors could contribute information on crop acreage. But these acreage estimates must be available early in the season to assist with production forecasts. This study acquired TerraSAR-X and RADARSAT-2 data over a region in eastern Canada dominated by economically important corn and soybean production. Using a supervised decision tree classifier, results determined that either sensor was capable of delivering highly accurate maps of corn and soybeans at the end of the growing season. Accuracies far exceeded 90%. Spatial and multi-temporal filtering approaches were compared and small improvements in accuracies were found by applying the multi-temporal filter to the RADARSAT-2 data. Of significant interest, this study determined that by using only three TerraSAR-X images corn could be accurately identified by the end of June, a mere six weeks after planting and at a vegetative growth stage (V6 – sixth leaf collar developed). However, soybeans required additional acquisitions given the variance in planting densities and planting dates in this region of Canada. In this case, accurate soybean classification required TerraSAR-X images until early August at the start of the reproductive stage (R5 – seed development is beginning). Also important, by applying a multi-temporal filter accurate mapping (close to 90%) of corn and soybeans from RADARSAT-2 could occur five weeks earlier (by August 19) than if a spatial filter was used. Thus application of this filtering approach could accelerate delivery of a crop inventory for this region of Canada. Corn and soybeans are important commodities both globally and within Canada. This study makes an important contribution as it demonstrates that TerraSAR-X can deliver acreage estimates of these two crops early enough to assist with in-season production forecasting. [ABSTRACT FROM AUTHOR]

Quantification of rice biophysical properties is important not only for rice growth monitoring and cropping management, but for understanding carbon cycle in agricultural ecosystems. In this study, a rice canopy scattering model (RCSM) was firstly utilized to simulate rice backscatter with a root mean square error (RMSE) <1 dB in comparison with the C-band, HH-polarization Radarsat-2 images. And then, by integrating the model with a generic algorithm optimization tools (GOAT), canopy height and density were separately retrieved from Radarsat-2 images acquired in three rice growth stages (elongation stage, heading stage and yellow ripening stage). Accuracy analysis showed that the two parameters could be retrieved with the RMSE of 5.4 cm in height, and 26 (#/m 2 ) in density. The study demonstrated the potential of Radarsat-2 SAR data for quantitative mapping of biophysical parameters of paddy rice. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) data are often used to determine the physical properties of the soil surface, such as soil moisture and surface roughness. Although these analyses are commonly applied in agricultural environments, there has been limited application in more natural environments, particularly at high latitudes. For the research reported here, an artificial neural network (ANN) is developed to model surface roughness in the Canadian High Arctic. This research represents the first phase of the overall goal of developing an operational methodology for estimating surface roughness, vegetation cover and soil moisture using SAR and limited field measurements. Multiple incidence angle data and fully polarimetric data from RADARSAT-2 are combined with long and short profile in situ surface roughness measurements from 134 sample locations located across two distinct High Arctic study sites. Multiple ANN models were developed using various backscatter, textural, and polarimetric variables. The ANN models exhibited a moderate to strong agreement to field-measured surface roughness. This study demonstrates that operational surface roughness modeling in the Canadian High Arctic is feasible with RADARSAT-2 polarimetric data. [ABSTRACT FROM AUTHOR]

Navigation in polar sea regions requires special attention to the sea ice condition because it is a major barrier for an icebreaker to break the drift ice or fast ice, allowing the vessel to keep moving forward. The advancement of remote sensing imagery pro-vides an effective means to classify and identify various features, including different types of sea ice. Hence, it permits fuel and time saving for the entire voyage, especially when drift ice or fast ice becomes a barrier for the icebreaker. In this study, we exploit the potential usage of high-resolution synthetic aperture radar (SAR) imageries from Radarsat-2 to identify sea ice conditions for precise navigation of China's icebreaker vessel (Xuelong) during the 29th Chinese Antarctic Research Expedition in December 2012. Different features on the fast ice were identified from horizontal-transmit and horizontal-receive polarized imagery. The potential usage of SAR imagery for precise navigation was confirmed by an expert witness on the Xuelong vessel at that time. The final voyage route has validated our analysis of fast ice and navigation of the Xuelong ssel. The predicted regions for unloading locations were also found to be matching well with the actual vessel unloading locations after the final voyage route. [ABSTRACT FROM AUTHOR]

New optical and microwave integrated vegetation indices (VIs) were designed based on observations from both field experiments and satellite (HJ-1 and RADARSAT-2) data. It was found that these VIs perform better in estimating the structure parameters of maize, such as Leaf Area Index (LAI), height and biomass, than the original ones. This investigation focused on the difference of interaction between the multispectral reflectance and microwave backscattering signatures with the maize growth variables. Because the maize was near the heading stage with large vegetation coverage in the experiment, the reflectance of the near-infrared band of HJ-1 was much less sensitive to the structure variables than that of the visible-light band. Thus, the optical VIs formulated using those bands were saturated to estimate the structure parameters. With respect to the RADARSAT-2 data, there was a relatively strong relationship between the HV cross-polarization and the volume scattering of the maize, which was mostly determined by the crown structure. The modified VIs were designed using both the VIs of HJ-1 and the HV cross-polarization of RADARSAT-2 to overcome the saturation limitation. The validation showed that this integrated method of determining VIs is a good alternative to that using only the optical or microwave observation. [ABSTRACT FROM AUTHOR]

One of the routes for thick, multi-year sea ice (MYI) exiting the Arctic Ocean is through the Queen Elizabeth Islands (QEI) in the Canadian Arctic. Quantifying the volume of MYI that passes through the QEI and the associated transit times is important for assessing changes in Arctic-wide MYI amount. It is also important because MYI eventually invades the Northwest Passage and affects Arctic shipping. One of the main gateways through which Arctic sea ice enters the QEI is the Prince Gustaf Adolf Sea. In this study, sea-ice influx events into the Prince Gustaf Adolf Sea during the 2010 mobile-ice season were investigated. Sea-ice motion was derived from RADARSAT imagery using the Canadian Ice Service-Automated Sea Ice Tracking System (CIS-ASITS) and validated using data from two CIS satellite-tracked beacons. Ice motion results indicate that major ice influxes through the Prince Gustaf Adolf Sea occur as a series of wind-driven pulses and that ice drift rates are approximately 1–2% of the wind speed. During intervals of southward ice drift in 2010, the drift speed along the eastern side of the Prince Gustaf Adolf Sea was up to twice as fast as that along the western side. This east–west gradient may reflect a pattern of ocean circulation in the Prince Gustaf Adolf Sea that has not yet been delineated. RÉSUMÉ [Traduit par la rédaction] Les îles de la Reine-Élizabeth dans l'Arctique canadien sont l'un des chemins qu'emprunte la glace de mer épaisse de plusieurs années quand elle sort de l'océan Arctique. Il est important de mesurer le volume de glace de plusieurs années qui traverse les îles de la Reine-Élizabeth de même que les temps de parcours pour évaluer les changements dans la quantité de glace de plusieurs années dans l'ensemble de l'Arctique. Ceci est aussi important parce que celle-ci envahit éventuellement le passage du Nord-Ouest et nuit à la navigation dans l'Arctique. L'un des principaux passages par où transite la glace de l'Arctique entre les îles de la Reine-Élizabeth est la mer du Prince-Gustaf-Adolf. Dans cette étude, nous avons examiné les événements d'afflux de glace de mer dans la mer du Prince-Gustaf-Adolf durant la saison de glace mobile de 2010. Le mouvement de la glace de mer a été dérivé des images RADARSAT au moyen du système automatisé de poursuite des glaces de mer du Service canadien des glaces (CIS-ASITS) et validé à l'aide des données de deux radiophares du Service canadien des glaces suivis par satellite. Les résultats sur le mouvement des glaces indiquent que les afflux importants de glace à travers la mer du Prince-Gustaf-Adolf se produisent comme une série d'impulsions sous l'effet du vent et que les vitesses de dérive de la glace sont approximativement de 1 à 2% de la vitesse du vent. Durant les périodes de dérive de la glace vers le sud en 2010, la vitesse de dérive le long du côté est de la mer du Prince-Gustaf-Adolf était jusqu’à deux fois plus élevée que le long du côté ouest. Ce gradient est–ouest peut être le reflet d'une circulation océanique dans la mer du Prince-Gustaf-Adolf qui n'a pas encore été délinéée. [ABSTRACT FROM AUTHOR]

In recent years, the use of synthetic aperture radar (SAR) for iceberg detection has been increasing thanks to the greater availability and coverage of SAR data, particularly polarimetric data. Greater amounts of polarimetric information can increase detection performance, preventing false alarms and missed detections. However, quad-polarization (quad-pol) SAR systems have increased data rate and power usage requirements, causing quad-pol modes to have generally half the swath width of dual-polarization (dual-pol) modes. Compact polarimetry is a compromise that allows the approximation of quad-pol information (referred to as “pseudo quad-pol”) using a dual-pol SAR. In this paper, using compact polarimetric data simulated from RADARSAT-2 quad-pol imagery, we show how pseudo-quad-pol data can be used for iceberg detection using the likelihood ratio test method. We show that use of the pseudo-quad-pol HV intensity can augment the detection performance of a compact polarimetric SAR system. We also compare the performance of the various compact polarimetric configurations to linearly polarized dual-pol and quad-pol data. [Traduit par la rédaction] Ces dernières années, le radar à synthèse d'ouverture (RSO) a été de plus en plus utilisé pour la détection des icebergs grâce à une meilleure disponibilité et une meilleure couverture des données RSO, en particulier des données polarimétriques. De plus grandes quantités d'informations polarimétiques peuvent améliorer la performance de détection, ce qui évite les fausses alarmes et les détections manquées. Cependant, les systèmes RSO à quadruple polarisation (quad-pol) exigent des débits binaires et une consommation d’énergie plus élevés, de telle sorte que les modes quad-pol utilisent généralement une largeur de couloir la moitié moindre que celle des modes à double polarisation (dual-pol). La polarimétrie compacte est un compromis qui permet d'approximer l'information quad-pol (alors appelée « pseudo-quad-pol ») au moyen d'un RSO dual-pol. Dans cet article, en utilisant des données de polarimétrie compacte simulées à partir de l'imagerie RADARSAT-2 quad-pol, nous montrons comment les données pseudo-quad-pol peuvent servir à la détection des icebergs au moyen de la méthode du test du rapport des vraisemblances. Nous montrons que l'utilisation de l'intensité HV pseudo-quad-pol peut augmenter la performance de détection d'un système RSO polarimétrique compact. Nous comparons aussi la performance des diverses configurations polarimétriques compactes aux données dual-pol et quad-pol linéairement polarisées. [ABSTRACT FROM AUTHOR]

A novel method which integrates polarimetric decomposition, object-oriented image analysis, and decision tree algorithms is presented for land-use and land-cover (LULC) classification using RADARSAT-2 polarimetric SAR (POLSAR) data. Polarimetric decomposition which is aimed at extracting polarimetric parameters related to the physical scattering mechanisms of the observed objects can be used to support the classification of POLSAR data. The main purposes of object-oriented image analysis are delineating image objects as well as extracting various textural and spatial features from image objects to improve classification accuracy. A decision tree algorithm provides on efficient way to select features and implement classification. Compared with the Wishart supervised classification which is based on the coherency matrix, the proposed method can significantly improve the overall accuracy and kappa value of LULC classification by 17.45 percent and 0.24, respectively. Further investigation was carried out on the contribution of polarimetric decomposition, object-oriented image analysis, and decision tree algorithms to the improvement achieved by the proposed method. The investigation shows that all these three methods contribute to the improvement achieved by the proposed method. [ABSTRACT FROM AUTHOR]

Abstract: As an important resource, water has a far-reaching impact on various economic activities. In agriculture, water controls the distribution of crops. In this paper, RADARSAT SAR and Landsat ETM+ imagery were used for the extraction of water information. First, radar image was preprocessed by the radar image calibration and filtering. K-T transformation was applied to Landsat ETM+ data for wetness index and NDVI was derived. Finally, the two classification results are compared. The results show that the complementary information of RADARSAT SAR and Landsat ETM+ image can quickly and accurately extract the water information. [Copyright &y& Elsevier]

Abstract: Due to some limitations of the visible and near infrared bands in remote sensing, radar remote sensing technology, which is capable in all-time, all-weather, and penetrating to some degree and so forth, has become a new technology and new method in rapid, large-scale information extraction. In this paper, the feasibility of using radar image as data source in terms of information extraction of Hongze Lake reclamation area is discussed. Firstly, based on RADARSAT-1 data, radar image was calibrated, geometrically corrected and filtered. Secondly, classification was carried out on SAR data and ETM+ data by using thresholds with the help of groundtruth data. Then, the ETM+ data was classified into the categories of aquaculture, open water, rice paddy and wetland vegetation by using wetness and spectral characteristics. Finally, the categories extracted from two different data sources were combined together. The results show that the methods used in this research are practical and efficient. The overall accuracy of classification is 93% with high Kappa Coefficient of 0.87. [Copyright &y& Elsevier]

The study of the urban microclimate requires detailed information that is not available in most cities. The monitoring of climate parameters is reduced to a limited number of stations that are useful for urban climate studies at local or zonal scales. Detailed information is generally obtained through field work and fixed sensors. There are some climate parameters that can be obtained from remote sensors, such as the surface emission temperature, however, this information is only available in medium or low-resolution images from satellite images. Currently, it is possible to generate detailed information with Unmanned Aerial Vehicles (UAV). There are not many UAVs that can capture information on the surface emission temperature and those that can are, in general, prohibitively expensive. Only a few years ago a low-cost drone became available, the Mavic 2 dual, equipped with a thermal sensor, which qualitatively captures information from the thermal field. This article proposes the study of the urban microclimate of two mid-size Chilean cities using thermal images captured with the Mavic 2 dual drone, for which it was first necessary to process the images and convert their values to degrees Celsius. The values obtained are compared with those derived from Modis and Landsat satellite images, evaluating the correlation of the information. • Calculation of the surface temperature from UAV contribute to study at microscale. • From UAV temperature it observes the relation with urban design parameters. • There are similarities in the spatial pattern between LST and UAV temperature. [ABSTRACT FROM AUTHOR]

We propose a learning-based multi-view stereo (MVS) method in scattering media, such as fog or smoke, with a novel cost volume, called the dehazing cost volume. Images captured in scattering media are degraded due to light scattering and attenuation caused by suspended particles. This degradation depends on scene depth; thus, it is difficult for traditional MVS methods to evaluate photometric consistency because the depth is unknown before three-dimensional (3D) reconstruction. The dehazing cost volume can solve this chicken-and-egg problem of depth estimation and image restoration by computing the scattering effect using swept planes in the cost volume. We also propose a method of estimating scattering parameters, such as airlight, and a scattering coefficient, which are required for our dehazing cost volume. The output depth of a network with our dehazing cost volume can be regarded as a function of these parameters; thus, they are geometrically optimized with a sparse 3D point cloud obtained at a structure-from-motion step. Experimental results on synthesized hazy images indicate the effectiveness of our dehazing cost volume against the ordinary cost volume regarding scattering media. We also demonstrated the applicability of our dehazing cost volume to real foggy scenes. • A novel cost volume for learning-based multi-view stereo in scattering media. • Airlight and scattering coefficient estimation with our dehazing cost volume. • Demonstrating depth estimation on synthetic and actual foggy images. [ABSTRACT FROM AUTHOR]

Eleven Radarsat scenes imaged between 22 September 1996 and 28 February 1998 were analyzed to delineate flood inundation in the forests of the Roanoke River floodplain, North Carolina. Threshold δ0 values distinguishing flooded from nonflooded forests were identified using classification trees. Data from 13 U.S. Geological Survey IUSGS) wells located throughout the floodplain were used to validate the flood mapping with an overall accuracy of 93.5 percent. Images from both leaf-on and leaf-off periods were acceptable for detectingflooding, although the leaf-off scenes were classifed with higher accuracy than were the leaf-on scenes (98.1 percent versus 89.1 percent). In addition, threshold u0 values were lower for leaf-on scenes. The results also indicate that Radarsat data can be used to detect minimal flood levels-sites with water stages between 10 cm below and 10 cm above the forest floor were classified with 90.6 percent accuracy, Radarsat data are effective and appropriate for flood inundation mapping in forests, regardless of season or water level. [ABSTRACT FROM AUTHOR]

The identification and counting of grassland degradation indicator ground objects is an important component of grassland ecological monitoring. These steps are also an important basis for developing ecological restoration and management programs for degraded grasslands. Compared with a traditional human survey, the use of remote sensing images can not only achieve dynamic monitoring of a large area, but also improve the efficiency. Recently, most studies regarding ground object classification based on remote sensing images address the development and optimization of classification models for features in several widely used datasets. For the remote sensing of desertified grasslands, remote sensing images with high spatial resolutions are used for studies on small and sparse features in degraded grasslands. The spatial resolution of the above mentioned datasets yields difficulties when attempting to classify small and sparse indicator features for desertified grasslands because generalization becomes limited. Therefore, establishing a lightweight classification model suitable for degraded grassland features with high spatial resolution is important. In this study, a low altitude unmanned aerial vehicle (UAV) hyperspectral remote sensing platform was constructed to collect high spatial resolution remote sensing images of degraded grasslands. The GDIF-3D-CNN classification model was used to classify the pure pixels and all pixels datasets, whose accuracy and efficiency were further improved by optimizing the eight parameters of the model. This study explores the remote sensing ground object classification of thin small plants and a large number of mixed pixels, realizing high precision classification among desertification degradation indicating plant populations of a species, and provides key quantitative data for grassland degradation research. [ABSTRACT FROM AUTHOR]

• A novel feature extraction scheme for drivers' stress level detection is proposed. • Subspace decomposition of the features is realized in the proposed scheme. • An accuracy of 100 % is attained by the proposed scheme. • 100 % accuracy is achieved by using only 2-dimensional features by the proposed scheme. The automotive industry has accelerated the utilization of Intelligent Transport Systems (ITS) in vehicles for increased driving safety. In this paper, a novel and well-done subspace feature extraction scheme on the physiological signals acquired by wearable sensors, for drivers' distress level detection to be introduced as an ITS is proposed and verified on the publicly available MIT-BIH PhysioNet Multi-parameter Database. The proposed scheme includes two phases where time-domain statistical feature extraction is first realized on the electrocardiogram (ECG), hand galvanic skin response (hand GSR), foot galvanic skin response (foot GSR), electromyogram (EMG), and respiration (RESP) signals, and secondly subspace feature vector construction is appreciated by applying Discriminative Common Vector (DCV) decomposition on the statistical feature vectors. The distress levels of the drivers are determined as low, moderate, and high by utilizing both the statistical and the subspace feature vectors using Support Vector Machines (SVM) classifier by 2-fold cross-validation technique. A maximum of 88.89 % classification accuracy is achieved using statistical features in 7384 s while it is increased to 100 % in 3,421 s when subspace features are employed. The increased classification accuracy in decreased time consumption evidently shows the success of the proposed feature extraction scheme. [ABSTRACT FROM AUTHOR]

Road detection in very-high-resolution remote sensing imagery is a hot research topic. However, the high resolution results in highly complex data distributions, which lead to much noise for road detection--for example, shadows and occlusions caused by disturbance on the roadside make it difficult to accurately recognize road. In this article, a novel edge-reinforced convolutional neural network, combined with multiscale feature extraction and edge reinforcement, is proposed to alleviate this problem. First, multiscale feature extraction is used in the center part of the proposed network to extract multiscale context information. Then edge reinforcement, applying a simplified U-Net to learn additional edge information, is used to restore the road information. The two operations can be used with different convolutional neural networks. Finally, two public road data sets are adopted to verify the effectiveness of the proposed approach, with experimental results demonstrating its superiority. [ABSTRACT FROM AUTHOR]

Urban forests are dynamic and change in response to both human and natural forces. To effectively monitor and manage urban forests, periodic inventories are needed to ensure that information about them is current and comprehensive. This task has traditionally been accomplished by manual ground-based field surveys, or more recently using GIS techniques utilizing remote sensing products, especially lidar. Low-cost Unmanned Aerial Vehicles (UAVs) employing Structure from Motion (SfM) techniques have the potential to augment these sources for urban forest inventories. We present the results of an analysis of approximately 1000 urban trees and compare accuracy in the measurement of tree heights and diameters from manual measurements, lidar, and Structure from Motion (SfM) from UAV-based imaging. Results indicate that in an urban environment, the SfM method produces estimates of tree height (R2 = 0.96; RMSE =1.91 m) and diameter (R2 = 0.98; RMSE =3 cm) comparable to manual field measurement, and better than those derived from conventional aerial lidar. In addition, the gains in accuracy from SfM come largely from younger, smaller trees that are often poorly imaged with lidar. [ABSTRACT FROM AUTHOR]

• Driver's Cognitive load classification. • Physiological parameter and vehicular parameters have been used. • Physiological Parameters have been extracted using non-contact based approach (i.e. camera). • Two separate studies have been conducted where the classification accuracy is 94% in study 1 and 82% in study 2. • Four machine learning algorithms have been used for classification cognitive load. Classification of cognitive load for vehicular drivers is a complex task due to underlying challenges of the dynamic driving environment. Many previous works have shown that physiological sensor signals or vehicular data could be a reliable source to quantify cognitive load. However, in driving situations, one of the biggest challenges is to use a sensor source that can provide accurate information without interrupting diverging tasks. In this paper, instead of traditional wire-based sensors, non-contact camera and vehicle data are used that have no physical contact with the driver and do not interrupt driving. Here, four machine learning algorithms, logistic regression (LR), support vector machine (SVM), linear discriminant analysis (LDA) and neural networks (NN), are investigated to classify the cognitive load using the collected data from a driving simulator study. In this paper, physiological parameters are extracted from facial video images, and vehicular parameters are collected from controller area networks (CAN). The data collection was performed in close collaboration with industrial partners in two separate studies, in which study-1 was designed with a 1-back task and study-2 was designed with both 1-back and 2-back task. The goal of the experiment is to investigate how accurately the machine learning algorithms can classify drivers' cognitive load based on the extracted features in complex dynamic driving environments. According to the results, for the physiological parameters extracted from the facial videos, the LR model with logistic function outperforms the other three classification methods. Here, in study-1, the achieved average accuracy for the LR classifier is 94% and in study-2 the average accuracy is 82%. In addition, the classification accuracy for the collected physiological parameters was compared with reference wire-sensor signals. It is observed that the classification accuracies between the sensor and the camera are very similar; however, better accuracy is achieved with the camera data due to having lower artefacts than the sensor data. [ABSTRACT FROM AUTHOR]

The article reports on the announcement of Mobile Data Association's (MDA) Information Systems group that it will release RADARSAT-2 information products and analysis from the major earthquake in Nepal. It notes on the extra-fine mode imaging feature of the products which provide an unprecedented ability to capture exceptional resolution imagery over large areas. It notes on the device's capability to collect images through all weather conditions, 24 hours a day.

The article offers information on photogrammetric and remote sensing products, including Altavian's Nova F6500 unmanned aerial system (UAS) and the Extra-Fine imaging mode for the RADARSAT-2 satellite from MDA.