查看更多>>摘要：Due to severe speckle noise in synthetic aperture radar (SAR) images and the large nonlinear intensity differences between SAR and optical images, the registration of SAR and optical images is a challenging problem that remains to be solved. In this paper, an improved nonlinear scale-invariant feature transform (SIFT)-framework-based algorithm that combines spatial feature detection with local frequency-domain description for the registration of SAR and optical images is proposed. First, multiscale representations of the SAR and optical images are constructed based on nonlinear diffusion to better preserve edges and obtain consistent edge information. The ratio of exponentially weighted averages (ROEWA) operator and the Sobel operator are utilized in the process of scale space construction to calculate consistent gradient information. Then, a new feature detection strategy based on the Harris-Laplace ROEWA and Harris-Laplace Sobel techniques is proposed to detect stable and repeatable keypoints in the scale space. Finally, a novel descriptor, called the rotation-invariant amplitudes of log-Gabor orientation histograms (RI-ALGH), and a simplified version, ALGH, are proposed. The proposed descriptors are built based on the amplitudes of multiscale and multiorientation log-Gabor responses and utilize an improved spatial structure of the gradient location and orientation histogram (GLOH) descriptor, which is robust to local distortions. The experimental results on both simulated and real images demonstrate that the proposed method can achieve better results than other state-of-the-art methods in terms of registration accuracy.
查看更多>>摘要：Automatic detection and recognition of traffic signs have many applications. However, some problems can affect the accuracy of the existing algorithms, such as changes in environmental light conditions, shadows, the presence of objects of the same colour, significant changes in scale and rotation, as well as obstacles in front of the traffic signs. To overcome these difficulties, a reference image database is usually used that includes different modes of appearing the traffic signs in the images. In order to overcome the effects of scale and rotation, in this paper a new method is presented in which only one reference image is needed for each sign to recognise the traffic sign in an image. In the proposed method, imaging is done in stereo. Using the captured image pair, a virtual image is generated which is then used to recognise the sign. As a result, the recognition is carried out with a minimum number of reference images. Experiments show that the proposed algorithm significantly improves recognition results. The traffic signs are recognised with 93.1% accuracy that enjoys a 4.9% improvement over traditional methods.
查看更多>>摘要：In temperate forests, autumn leaf phenology signals the end of leaf growing season and shows large variability across tree-crowns, which importantly mediates photosynthetic seasonality, hydrological regulation, and nutrient cycling of forest ecosystems. However, critical challenges remain with the monitoring of autumn leaf phenology at the tree-crown scale due to the lack of spatially explicit information for individual tree-crowns and high (spatial and temporal) resolution observations with nadir view. Recent availability of the PlanetScope constellation with a 3 m spatial resolution and near-daily nadir view coverage might help address these observational challenges, but remains underexplored. Here we developed an integration of PlanetScope with drone observations for improved monitoring of crown-scale autumn leaf phenology in a temperate forest in Northeast China. This integration includes: 1) visual identification of individual tree-crowns (and species) from drone observations; 2) extraction of time series of PlanetScope vegetation indices (VIs) for each identified tree-crown; 3) derivation of three metrics of autumn leaf phenology from the extracted VI time series, including the start of fall (SOF), middle of fall (MOF), and end of fall (EOF); and 4) accuracy assessments of the PlanetScope-derived phenology metrics with reference from local phenocams. Our results show that (1) the PlanetScopedrone integration captures large inter-crown phenological variations, with a range of 28 days, 25 days, and 30 days for SOF, MOF, and EOF, respectively, (2) the extracted crown-level phenology metrics strongly agree with those derived from local phenocams, with a root-mean-square-error (RMSE) of 4.1 days, 3.0 days and 5.4 days for SOF, MOF, and EOF, respectively, and (3) PlanetScope maps large variations in autumn leaf phenology over the entire forest landscape with spatially explicit information. These results demonstrate the ability of our proposed method in monitoring the large spatial heterogeneity of crown-scale autumn leaf phenology in the temperate forest, suggesting the potential of using high-resolution satellites to advance crown-scale phenology studies over large geographical areas.
查看更多>>摘要：Line segment matching in two or multiple views is helpful to 3D reconstruction and pattern recognition. To fully utilize the geometry constraint of different features for line segment matching, a novel graph-based algorithm denoted as GLSM (Graph-based Line Segment Matching) is proposed in this paper, which includes: (1) the employment of three geometry types, i.e., homography, epipolar, and trifocal tensor, to constrain line and point candidates across views; (2) the method of unifying different geometry constraints into a line-point association graph for two or multiple views; and (3) a set of procedures for ranking, assigning, and clustering with the linepoint association graph. The experimental results indicate that GLSM can obtain sufficient matches with a satisfactory accuracy in both two and multiple views. Moreover, GLSM can be employed with large image datasets. The implementation of GLSM will be available soon at https://skyearth.org/research/.
查看更多>>摘要：Motivated by the need to identify erroneous disparity estimates, various methods for the estimation of aleatoric uncertainty in the context of dense stereo matching have been presented in recent years. Especially, the introduction of deep learning based methods and the accompanying significant improvement in accuracy have greatly increased the popularity of this field. Despite this remarkable development, most of these methods rely on features learned from disparity maps only, neglecting the corresponding 3-dimensional cost volumes. However, conventional hand-crafted methods have already demonstrated that the additional information contained in such cost volumes are beneficial for the task of uncertainty estimation. In this paper, we combine the advantages of deep learning and cost volume based features and present a new Convolutional Neural Network (CNN) architecture to directly learn features for the task of aleatoric uncertainty estimation from volumetric 3D data. Furthermore, we discuss and apply three different uncertainty models to train our CNN without the need to provide ground truth for uncertainty. In an extensive evaluation on three datasets using three common dense stereo matching methods, we investigate the effects of these uncertainty models and demonstrate the generality and state-of-the-art accuracy of the proposed method.
查看更多>>摘要：Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies because of data shift issues. In this paper, we propose the use of active learning to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing the classification performance. The adaptation consists in actively adding to the initial local model new relevant training samples from other areas in a cascade that iteratively improves the generalisation capabilities of the classifier leading to a global model tailored to these different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series revealed their high capacity to identify poplar plantations at a local scale with an average F-score ranging from 89.5% to 99.3%. For large area adaptation, the results showed that when the same number of training samples was used, active learning outperformed random sampling by up to 5% of the overall accuracy and up to 12% of the class F-score. Additionally, and depending on the class considered, the random sampling model required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for a national scale mapping in an operational context.
查看更多>>摘要：Pan-sharpening methods are commonly used to synthesize multispectral and panchromatic images. Selecting an appropriate algorithm that maintains the spectral and spatial information content of input images is a challenging task. This review paper investigates a wide range of algorithms, including 41 methods. For this purpose, the methods were categorized as Component Substitution (CS-based), Multi-Resolution Analysis (MRA), Variational Optimization-based (VO), and Hybrid and were tested on a collection of 21 case studies. These include images from WorldView-2, 3 & 4, GeoEye-1, QuickBird, IKONOS, KompSat-2, KompSat-3A, TripleSat, Pleiades-1, Pleiades with the aerial platform, and Deimos-2. Neural network-based methods were excluded due to their substantial computational requirements for operational mapping purposes. The methods were evaluated based on four Spectral and three Spatial quality metrics. An Analysis Of Variance (ANOVA) was used to statistically compare the pan-sharpening categories. Results indicate that MRA-based methods performed better in terms of spectral quality, whereas most Hybrid-based methods had the highest spatial quality and CS-based methods had the lowest results both spectrally and spatially. The revisited version of the Additive Wavelet Luminance Proportional Pan-sharpening method had the highest spectral quality, whereas Generalized IHS with Best Trade-off Parameter with Additive Weights showed the highest spatial quality. CS-based methods generally had the fastest run-time, whereas the majority of methods belonging to MRA and VO categories had relatively long run times.
查看更多>>摘要：Terrestrial laser scanners (TLS) record a large number of points within a short time. Temporal correlations between observations are unavoidable but often neglected in stochastic modelling. The main consequences are an overestimated precision of the point clouds and potential wrong test decisions when used for deformation analysis with rigorous statistical procedures. Regarding physical considerations, a fractional Gaussian noise, defined by a so-called Hurst exponent, or a combination of fractional Gaussian noises could be used to model the noise of range measurements from a sensor perspective; Temporal correlations are expected to have a long-range dependency due to the high recording rate of the TLS. Scanning settings and configurations can affect the global correlation parameters. These effects can be quantified from the residuals of a least-squares surface approximation from the TLS point cloud. Based on simulation results, real data correlation analysis from indoor and outdoor experiments can be better understood which makes the identification of the dominant correlating noise source possible. Our methodology combines two Hurst-estimators: the Whittle maximum likelihood and the generalised Hurst estimator; It paves the way for a simple and global model for describing the temporal noise of TLS range correlations, usable in point clouds analysis independently of the object under consideration.
查看更多>>摘要：With the launch of Sentinel-2 new opportunities for large scale urban mapping arise. However, the spectral information embedded in the Sentinel-2 20 m spatial resolution bands cannot yet be fully explored in heterogeneous urban landscapes. The 20 m image pixels are often composed of different land covers, resulting in a difficult to interpret mixed pixel spectrum. Here, we propose an unmixing-based image fusion algorithm (UnFuSen2) that self-adapts to the spectral variability of varying land covers and improves the image fusion accuracy by constraining the unmixing equations on the basis of spectral mixing models and the correlation between spectral bands of coarse and fine spatial resolution, respectively. When compared to alternative state-of-the-art downscaling methods UnFuSen2 consistently showed the highest accuracy when applied across test sites in three different European cities (RMSEuuruseu2 203 vs RMSEalternatives [252, 337]). In a next step, we applied Multiple Endmember Spectral Mixture Analysis (MESMA) on the downscaled Sentinel-2 image cube (i.e. ten 10 m bands) to generate subpixel urban land cover fractions. We compared our MESMA results against the traditional MESMA output as applied on the original Sentinel-2 image cube (i.e. four 10 m bands and six 20 m bands) and tested its robustness against reference data obtained over all three study sites. Results revealed an average decrease in RMSE of respectively 18% and 8% for impervious surface and vegetation fractions when our approach was compared to the traditional MESMA outcomes.
NETL
NSTL
Elsevier