ALBERT

Description: The existing deep learning methods for point cloud classification are trained using abundant labeled samples and used to test only a few samples. However, classification tasks are diverse, and not all tasks have enough labeled samples for training. In this paper, a novel point cloud classification method for indoor components using few labeled samples is proposed to solve the problem of the requirement for abundant labeled samples for training with deep learning classification methods. This method is composed of four parts: mixing samples, feature extraction, dimensionality reduction, and semantic classification. First, the few labeled point clouds are mixed with unlabeled point clouds. Next, the mixed high-dimensional features are extracted using a deep learning framework. Subsequently, a nonlinear manifold learning method is used to embed the mixed features into a low-dimensional space. Finally, the few labeled point clouds in each cluster are identified, and semantic labels are provided for unlabeled point clouds in the same cluster by a neighborhood search strategy. The validity and versatility of the proposed method were validated by different experiments and compared with three state-of-the-art deep learning methods. Our method uses fewer than 30 labeled point clouds to achieve an accuracy that is 1.89–19.67% greater than existing methods. More importantly, the experimental results suggest that this method is not only suitable for single-attribute indoor scenarios but also for comprehensive complex indoor scenarios.

Description: Satellite Image Time Series (SITS) have recently been of great interest due to the emerging remote sensing capabilities for Earth observation. Trend and seasonal components are two crucial elements of SITS. In this paper, a novel framework of SITS decomposition based on Ensemble Empirical Mode Decomposition (EEMD) is proposed. EEMD is achieved by sifting an ensemble of adaptive orthogonal components called Intrinsic Mode Functions (IMFs). EEMD is noise-assisted and overcomes the drawback of mode mixing in conventional Empirical Mode Decomposition (EMD). Inspired by these advantages, the aim of this work is to employ EEMD to decompose SITS into IMFs and to choose relevant IMFs for the separation of seasonal and trend components. In a series of simulations, IMFs extracted by EEMD achieved a clear representation with physical meaning. The experimental results of 16-day compositions of Moderate Resolution Imaging Spectroradiometer (MODIS), Normalized Difference Vegetation Index (NDVI), and Global Environment Monitoring Index (GEMI) time series with disturbance illustrated the effectiveness and stability of the proposed approach to monitoring tasks, such as applications for the detection of abrupt changes.

Description: Merging satellite and rain gauge data by combining accurate quantitative rainfall from stations with spatial continuous information from remote sensing observations provides a practical method of estimating rainfall. However, generating high spatiotemporal rainfall fields for catchment-distributed hydrological modeling is a problem when only a sparse rain gauge network and coarse spatial resolution of satellite data are available. The objective of the study is to present a satellite and rain gauge data-merging framework adapting for coarse resolution and data-sparse designs. In the framework, a statistical spatial downscaling method based on the relationships among precipitation, topographical features, and weather conditions was used to downscale the 0.25° daily rainfall field derived from the Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA) precipitation product version 7. The nonparametric merging technique of double kernel smoothing, adapting for data-sparse design, was combined with the global optimization method of shuffled complex evolution, to merge the downscaled TRMM and gauged rainfall with minimum cross-validation error. An indicator field representing the presence and absence of rainfall was generated using the indicator kriging technique and applied to the previously merged result to consider the spatial intermittency of daily rainfall. The framework was applied to estimate daily precipitation at a 1 km resolution in the Qinghai Lake Basin, a data-scarce area in the northeast of the Qinghai-Tibet Plateau. The final estimates not only captured the spatial pattern of daily and annual precipitation with a relatively small estimation error, but also performed very well in stream flow simulation when applied to force the geomorphology-based hydrological model (GBHM). The proposed framework thus appears feasible for rainfall estimation at high spatiotemporal resolution in data-scarce areas.

Description: The performance of Day-1 Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) and its predecessor, the Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis 3B42 Version 7 (3B42V7), was cross-evaluated using data from the best-available hourly gauge network over the Tibetan Plateau (TP). Analyses of three-hourly rainfall estimates in the warm season of 2014 reveal that IMERG shows appreciably better correlations and lower errors than 3B42V7, though with very similar spatial patterns for all assessment indicators. IMERG also appears to detect light rainfall better than 3B42V7. However, IMERG shows slightly lower POD than 3B42V7 for elevations above 4200 m. Both IMERG and 3B42V7 successfully capture the northward dynamic life cycle of the Indian monsoon reasonably well over the TP. In particular, the relatively light rain from early and end Indian monsoon moisture surge events often fails to be captured by the sparsely-distributed gauges. In spite of limited snowfall field observations, IMERG shows the potential of detecting solid precipitation, which cannot be retrieved from the 3B42V7 products.

Description: Unmanned Aerial Vehicles (UAVs) are being increasingly used to monitor topographic changes in coastal areas. Compared to Light Detection And Ranging (LiDAR) data or Terrestrial Laser Scanning data, this solution is low-cost and easy to use, while allowing the production of a Digital Surface Model (DSM) with a similar accuracy. Three campaigns were carried out within a three-month period at a lagoon-inlet system (Bonne-Anse Bay, La Palmyre, France), with a flying wing (eBee) combined with a digital camera. Ground Control Points (GCPs), surveyed by the Global Navigation Satellite System (GNSS) and post-processed by differential correction, allowed georeferencing DSMs. Using a photogrammetry process (Structure From Motion algorithm), DSMs and orthomosaics were produced. The DSM accuracy was assessed against the ellipsoidal height of a GNSS profile and Independent Control Points (ICPs) and the root mean square discrepancies were about 10 and 17 cm, respectively. Compared to traditional topographic surveys, this solution allows the accurate representation of bedforms with a wavelength of the order of 1 m and a height of 0.1 m. Finally, changes identified between both main campaigns revealed erosion/accretion areas and the progradation of a sandspit. These results open new perspectives to validate detailed morphological predictions or to parameterize bottom friction in coastal numerical models.

Description: Due to the limited accuracy of exterior orientation parameters, ground control points (GCPs) are commonly required to correct the geometric biases of remotely-sensed (RS) images. This paper focuses on an automatic matching technique for the specific task of georeferencing RS images and presents a technical frame to match large RS images efficiently using the prior geometric information of the images. In addition, a novel matching approach using online aerial images, e.g., Google satellite images, Bing aerial maps, etc., is introduced based on the technical frame. Experimental results show that the proposed method can collect a sufficient number of well-distributed and reliable GCPs in tens of seconds for different kinds of large-sized RS images, whose spatial resolutions vary from 30 m to 2 m. It provides a convenient and efficient way to automatically georeference RS images, as there is no need to manually prepare reference images according to the location and spatial resolution of sensed images.

Description: The concentration, type, and extent of sea ice in the Arctic can be estimated based on measurements from satellite active microwave sensors, passive microwave sensors, or both. Here, data from the Advanced Scatterometer (ASCAT) and the Special Sensor Microwave Imager/Sounder (SSMIS) are employed to broadly classify Arctic sea ice type as first-year (FY) or multiyear (MY). Combining data from both active and passive sensors can improve the performance of MY and FY ice classification. The classification method uses C-band σ0 measurements from ASCAT and 37 GHz brightness temperature measurements from SSMIS to derive a probabilistic model based on a multivariate Gaussian distribution. Using a Gaussian model, a Bayesian estimator selects between FY and MY ice to classify pixels in images of Arctic sea ice. The ASCAT/SSMIS classification results are compared with classifications using the Oceansat-2 scatterometer (OSCAT), the Equal-Area Scalable Earth Grid (EASE-Grid) Sea Ice Age dataset available from the National Snow and Ice Data Center (NSIDC), and the Canadian Ice Service (CIS) charts, also available from the NSIDC. The MY ice extent of the ASCAT/SSMIS classifications demonstrates an average difference of 282 thousand km - + from that of the OSCAT classifications from 2009 to 2014. The difference is an average of 13.6% of the OSCAT MY ice extent, which averaged 2.19 million km2 over the same period. Compared to the ice classified as two years or older in the EASE-Grid Sea Ice Age dataset (EASE-2+) from 2009 to 2012, the average difference is 617 thousand km2 . The difference is an average of 22.8% of the EASE-2+ MY ice extent, which averaged 2.79 million km2 from 2009 to 2012. Comparison with the Canadian Ice Service (CIS) charts shows that most ASCAT/SSMIS classifications of MY ice correspond to a MY ice concentration of approximately 50% or greater in the CIS charts. The addition of the passive SSMIS data appears to improve classifications by mitigating misclassifications caused by ASCAT's sensitivity to rough patches of ice which can appear similar to, but are not, MY ice.

Description: To facilitate the advances in Sentinel-2A products for land cover from Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat imagery, Sentinel-2A MultiSpectral Instrument Level-1C (MSIL1C) images are investigated for large-scale vegetation mapping in an arid land environment that is located in the Ili River delta, Kazakhstan. For accurate classification purposes, multi-resolution segmentation (MRS) based extended object-guided morphological profiles (EOMPs) are proposed and then compared with conventional morphological profiles (MPs), MPs with partial reconstruction (MPPR), object-guided MPs (OMPs), OMPs with mean values (OMPsM), and object-oriented (OO)-based image classification techniques. Popular classifiers, such as C4.5, an extremely randomized decision tree (ERDT), random forest (RaF), rotation forest (RoF), classification via random forest regression (CVRFR), ExtraTrees, and radial basis function (RBF) kernel-based support vector machines (SVMs) are adopted to answer the question of whether nested dichotomies (ND) and ensembles of ND (END) are truly superior to direct and error-correcting output code (ECOC) multiclass classification frameworks. Finally, based on the results, the following conclusions are drawn: 1) the superior performance of OO-based techniques over MPs, MPPR, OMPs, and OMPsM is clear for Sentinel-2A MSIL1C image classification, while the best results are achieved by the proposed EOMPs; 2) the superior performance of ND, ND with class balancing (NDCB), ND with data balancing (NDDB), ND with random-pair selection (NDRPS), and ND with further centroid (NDFC) over direct and ECOC frameworks is not confirmed, especially in the cases of using weak classifiers for low-dimensional datasets; 3) from computationally efficient, high accuracy, redundant to data dimensionality and easy of implementations points of view, END, ENDCB, ENDDB, and ENDRPS are alternative choices to direct and ECOC frameworks; 4) surprisingly, because in the ensemble learning (EL) theorem, “weaker” classifiers (ERDT here) always have a better chance of reaching the trade-off between diversity and accuracy than “stronger” classifies (RaF, ExtraTrees, and SVM here), END with ERDT (END-ERDT) achieves the best performance with less than a 0.5% difference in the overall accuracy (OA) values, but is 100 to 10000 times faster than END with RaF and ExtraTrees, and ECOC with SVM while using different datasets with various dimensions; and, 5) Sentinel-2A MSIL1C is better choice than the land cover products from MODIS and Landsat imagery for vegetation species mapping in an arid land environment, where the vegetation species are critically important, but sparsely distributed.

Description: For the planning and sustainable management of forest resources, well-managed plantations are of great significance to mitigate the decrease of forested areas. Monitoring these planted forests is essential for forest resource inventories. In this study, two ALOS PALSAR-2 quad-polarimetric synthetic aperture radar (SAR) images and ground measurements were employed to estimate growing stem volume (GSV) of Chinese fir plantations located in a hilly area of southern China. To investigate the relationships between forest GSV and polarization characteristics, single and fused variables were derived by the Yamaguchi decomposition and the saturation value of GSV was estimated using a semi-exponential empirical model as a base model. Based on the estimated saturation values and relative root mean square error (RRMSE), the single and fused characteristics and corresponding models were selected and integrated, which led to a novel saturation-based multivariate method used to improve the GSV estimation and mapping of Chinese fir plantations. The new findings included: (1) All the original polarimetric characteristics, statistically, were not significantly correlated with the forest GSV, and their logarithm and ratio transformation fused variables greatly improved the correlations, thus the estimation accuracy of the forest GSV. (2) The logarithm transformation of surface scattering resulted in the greatest saturation, value but the logarithm transformation of double-bounce scattering resulted in the smallest RRMSE of the GSV estimates. (3) Compared with the single transformations, the fused variables led to more reasonable saturation values and obviously reduced the values of RRMSE. (4) The saturation-based multivariate method led to more accurate estimates of the forest GSV than the univariate method, with the smallest value (29.64%) of RRMSE achieved using the set of six variables. This implied that the novel saturation-based multivariate method provided greater potential to improve the estimation and mapping of the forest GSV.

Description: Image registration is a core technology of many different image processing areas and is widely used in the remote sensing community. The accuracy of image registration largely determines the effect of subsequent applications. In recent years, phase correlation-based image registration has drawn much attention because of its high accuracy and efficiency as well as its robustness to gray difference and even slight changes in content. Many researchers have reported that the phase correlation method can acquire a sub-pixel accuracy of 1 / 10 or even 1 / 100 . However, its performance is acquired only in the case of translation, which limits the scope of the application of the method. However, there are few reports on the estimation of scales and angles based on the phase correlation method. To take advantage of the high accuracy property and other merits of phase correlation-based image registration and extend it to estimate the similarity transform, we proposed a novel algorithm, the Multilayer Polar Fourier Transform (MPFT), which uses a fast and accurate polar Fourier transform with different scaling factors to calculate the log-polar Fourier transform. The structure of the polar grids of MPFT is more similar to the one of the log-polar grid. In particular, for rotation estimation only, the polar grid of MPFT is the calculation grid. To validate its effectiveness and high accuracy in estimating angles and scales, both qualitative and quantitative experiments were carried out. The quantitative experiments included a numerical simulation as well as synthetic and real data experiments. The experimental results showed that the proposed method, MPFT, performs better than the existing phase correlation-based similarity transform estimation methods, the Pseudo-polar Fourier Transform (PPFT) and the Multilayer Fractional Fourier Transform method (MLFFT), and the classical feature-based registration method, Scale-Invariant Feature Transform (SIFT), and its variant, ms-SIFT.