Search

This paper proposes a quasi-dense feature matching algorithm that combines image semantic segmentation and local feature enhancement networks to address the problem of the poor matching of image features because of complex distortions, considerable occlusions, and a lack of texture on large oblique stereo images. First, a small amount of typical complex scene data are used to train the VGG16-UNet, followed by completing the semantic segmentation of multiplanar scenes across large oblique images. Subsequently, the prediction results of the segmentation are subjected to local adaptive optimization to obtain high-precision semantic segmentation results for each planar scene. Afterward, the LoFTR (Local Feature Matching with Transformers) strategy is used for scene matching, enabling enhanced matching for regions with poor local texture in the corresponding planes. The proposed method was tested on low-altitude large baseline stereo images of complex scenes and compared with five classical matching methods. Results reveal that the proposed method exhibits considerable advantages in terms of the number of correct matches, correct rate of matches, matching accuracy, and spatial distribution of corresponding points. Moreover, it is well-suitable for quasi-dense matching tasks of large baseline stereo images in complex scenes with considerable viewpoint variations.

At present, reclamation—changing ocean areas into inland land cover type for human usage—is one of the major methods for expanding land area around the world to alleviate the problem of land shortage. Thus, reclamation activities play an important role in land area extension. In recent years, reclamation projects have been active in eastern China. However, research on how to determine the initiation of reclamation activity remains very limited. Thus, a method of tracking reclamation activities was proposed in this study to analyze the coastline change due to human activities in Shanghai Lingang New City and Hangzhou Bay area. First, the reclamation area was extracted and separated into sea filling and sea enclosing. Next, the “SEDIMENT” signal track method and the “Eight-Neighborhood” morphological method were used to track dissimilar reclamation types. The historical reclamation activities (including start time and end time) over the recent 30 years were also tracked and obtained. Experimental results indicated that the time tracker accuracy of reclamation activity can reach 83.8%. Thus, this study can provide a reference for tracking coastline change.

Deformation monitoring has been brought to the fore and extensively studied in recent years. Global Navigation Satellite System Reflectometry (GNSS-R) techniques have so far been developed in deformation estimation applications, which however, are subject to the influence of mobile satellites. Rather than compensating for the path delay variations caused by mobile satellites, adopting Beidou geostationary Earth orbit (GEO) satellites as transmitters directly eliminates the satellite-motion-induced phase error and thus provides access to stable phase information. This paper presents a novel deformation monitoring concept based on GNSS-R utilizing Beidou GEO satellites. The geometrical properties of the GEO-based bistatic GNSS radar system are explored to build a theoretical connection between deformation quantity and the echo carrier phases. A deformation retrieval algorithm is proposed based on the supporting software receiver, thus allowing echo carrier phases to be extracted and utilized in deformation retrieval. Two field validation experiments are conducted by constructing passive bistatic radars with reflecting plates and ground receiver. Utilizing the proposed algorithm, the experimental results suggested that the GEO-based GNSS reflectometry can achieve deformation estimations with an accuracy of around 1 cm when the extracted phases does not exceed one complete cycle, while better than 3 cm when considering the correct integer number of phase cycles. Consequently, based on the passive bistatic radar system, the potential of achieving continuous, low-cost deformation monitoring makes this novel technique noteworthy.

Using scattering signals of the global navigation satellite system (GNSS) for target detection has become one of the research hotspots. This technology faces the difficulty of low signal-to-noise ratio (SNR) target echoes. Since BeiDou geostationary orbit (GEO) satellites provide the opportunity to form a bistatic radar with some advantages, such as fixed coverage area and quasi monostatic configuration to avoid the interference from the direct signals, the target echoes may have regular phases that are beneficial to SNR enhancement. This study uses BeiDou GEO satellites and ground fixed receivers to form a bistatic radar and analyzes the phase changes in the reflected signal caused by the target, then gives two methods for SNR enhancement corresponding to two applications: deformation monitoring and ship detection. This paper first introduces the basic signal processing including the intermediate frequency (IF) signal collector and the range compression in the software receiver, then describes the basic SNR enhancement method, i.e., increasing coherence integration time (CIT), and shows its limitation by two target cases: static metal reflector on the land and ships in the water. After that, this study provides an improved SNR enhancement method based on Doppler and range compensation in the moving ship detection case. The experiment shows that by the SNR enhancement, the SNRs of target echo signals in range/Doppler domain increase more than 4 dB on average. This study also demonstrates the bistatic radar’s potential for monitoring surface deformation.

The development of an efficient and robust method for dense image-matching has been a technical challenge due to high variations in illumination and ground features of aerial images of large areas. In this paper, we propose a method for the dense matching of aerial images using an optical flow field and a fast-guided filter. The proposed method utilizes a coarse-to-fine matching strategy for a pixel-wise correspondence search across stereo image pairs. The pyramid Lucas−Kanade (L−K) method is first used to generate a sparse optical flow field within the stereo image pairs, and an adjusted control lattice is then used to derive the multi-level B-spline interpolating function for estimating the dense optical flow field. The dense correspondence is subsequently refined through a combination of a novel cross-region-based voting process and fast guided filtering. The performance of the proposed method was evaluated on three bases, namely, the matching accuracy, the matching success rate, and the matching efficiency. The evaluative experiments were performed using sets of unmanned aerial vehicle (UAV) images and aerial digital mapping camera (DMC) images. The results showed that the proposed method afforded the root mean square error (RMSE) of the reprojection errors better than ±0.5 pixels in image, and a height accuracy within ±2.5 GSD (ground sampling distance) from the ground. The method was further compared with the state-of-the-art commercial software SURE and confirmed to deliver more complete matches for images with poor-texture areas, the matching success rate of the proposed method is higher than 97% while SURE is 96%, and there is 47% higher matching efficiency. This demonstrates the superior applicability of the proposed method to aerial image-based dense matching with poor texture regions.

This paper improves van Zyl’s Nonnegative Eigenvalue Decomposition (NNED). Orientation angle compensation and helix scattering are introduced to the decomposition. The volume scattering parameters that explain the most cross-polarized power are selected. If volume scattering and helix scattering explain all cross-polarized power in the measured coherency matrix, then simply perform van Zyl decomposition to the remainder matrix; otherwise, the measured coherency matrix is decomposed into three components, i.e., helix scattering, volume scattering, and one ground scattering. The latter two scattering are all modeled by Neumann’s adaptive depolarizing model, according to which some cross-polarized power is attributed to ground scattering hence the orientation angle randomness of volume scattering and the dominant ground scattering are obtained. In this way, all cross-polarized power could be well explained. Experiments using UAVSAR data showed that more than 99.8% of total pixels are well fitted. Negative power is avoided. Compared with van Zyl decomposition, volume scattering power is reduced by up to 8.73% on average. The given volume scattering power is often lower than that by three latest NNED.

Carbon sink estimation and ecological assessment of forests require accurate forest type mapping. The traditional survey method is time consuming and labor intensive, and the remote sensing method with high-resolution, multi-spectral commercial satellite images has high cost and low availability. In this study, we explore and evaluate the potential of freely-available multi-source imagery to identify forest types with an object-based random forest algorithm. These datasets included Sentinel-2A (S2), Sentinel-1A (S1) in dual polarization, one-arc-second Shuttle Radar Topographic Mission Digital Elevation (DEM) and multi-temporal Landsat-8 images (L8). We tested seven different sets of explanatory variables for classifying eight forest types in Wuhan, China. The results indicate that single-sensor (S2) or single-day data (L8) cannot obtain satisfactory results; the overall accuracy was 54.31% and 50.00%, respectively. Compared with the classification using only Sentinel-2 data, the overall accuracy increased by approximately 15.23% and 22.51%, respectively, by adding DEM and multi-temporal Landsat-8 imagery. The highest accuracy (82.78%) was achieved with fused imagery, the terrain and multi-temporal data contributing the most to forest type identification. These encouraging results demonstrate that freely-accessible multi-source remotely-sensed data have tremendous potential in forest type identification, which can effectively support monitoring and management of forest ecological resources at regional or global scales.

Implying the prosperity and development of the city, impervious surface area (ISA) is playing an increasingly important role in ecological processes, microclimate, material and energy flows, and urban flood. The free sub-meter resolution Google Earth image, which is integrated by several high spatial resolution data, appears to have potential for high-resolution ISA extraction, where present study is rare and performances remain to be improved. Due to the high spatial and spectral variation of the urban environment as well as confusion between ISA and soil, the accurate delineating of ISA with traditional (direct) methods can be costly and time-consuming, which is in a word resource-intensive. However, this paper presents a novel indirect ISA extraction conceptual model and a new detecting and masking background land cover (DMBLC) approach that: uses a freely available, high-resolution dataset; requires a reduced set of training samples; and consists of relatively simple, common, and feasible image processing steps. The key characteristic of DMBLC is to detect the background of ISA (vegetation, soil, and water) accurately and obtain the ISA by masking the background. The approach relies on background detection to avoid the predicaments of direct ISA extraction. Water can be directly gained by water body vector data, in DMBLC; mixture tuned matched filtering (MTMF) is exploited to detect vegetation and soil, image segmentation is used to mitigate the spectral variation problem within the same land cover, and segment rectangularity reduces the confusion between ISA and soil. From experiments in a core area of Fuzhou, China, the DMBLC approach reached high performance and outperformed the powerful traditional support vector machines (SVM) method (overall accuracy of 94.45% and Kappa coefficient of 0.8885, compared to 86.44% and 0.7329, respectively). From the comparison of different levels of complexity within the inner processing steps, it is confirmed that the DMBLC approach is a powerful and flexible changed framework for indirect ISA extraction, which can be improved by using more advanced inner methods.

The C-band radar instruments onboard the two-satellite GMES Sentinel-1 constellation provide global measurements with short revisit time (about six days) and medium spatial resolution (5 × 20 m), which are appropriate for watershed scale hydrological applications. This paper aims to explore the potential of Sentinel-1 for estimating surface soil moisture using a multi-temporal approach. To this end, a linear mixed effects (LME) model was developed over Poyang Lake ungauged zone, using time series Sentinel 1A and 1B images and soil moisture ground measurements from 15 automatic observation sites. The model assumed a linear relationship that varied with both time and space between soil moisture and backscattering coefficient (SM- σ 0 ). Results showed that three LME models developed with different polarized σ 0 images all meet the European Space Agency (ESA) accuracy requirement for GMES soil moisture product (≤5% in volume), with the vertical transmit and vertical receive (VV) polarized model achieving the best performance. However, the SM- σ 0 relationship was found to depend strongly on space, making it difficult to predict absolute soil moisture for each grid. Therefore, a relative soil moisture index was then proposed to correct for site effect. When compared with those of the linear fixed effects model, the soil moisture indices predicted by the LME model captured the temporal dynamics of measured soil moisture better, with the overall R2 and cross-validated R2 being 0.68 and 0.64, respectively. These results indicate that the LME model can be effectively applied to estimate soil moisture from multi-temporal Sentinel-1 images, which is useful for monitoring flood and drought disasters, and for improving stream flow prediction over ungauged zones.

Research efforts in land-use scene classification is growing alongside the popular use of High-Resolution Satellite (HRS) images. The complex background and multiple land-cover classes or objects, however, make the classification tasks difficult and challenging. This article presents a Multiscale Deeply Described Correlatons (MDDC)-based algorithm which incorporates appearance and spatial information jointly at multiple scales for land-use scene classification to tackle these problems. Specifically, we introduce a convolutional neural network to learn and characterize the dense convolutional descriptors at different scales. The resulting multiscale descriptors are used to generate visual words by a general mapping strategy and produce multiscale correlograms of visual words. Then, an adaptive vector quantization of multiscale correlograms, termed multiscale correlatons, are applied to encode the spatial arrangement of visual words at different scales. Experiments with two publicly available land-use scene datasets demonstrate that our MDDC model is discriminative for efficient representation of land-use scene images, and achieves competitive classification results with state-of-the-art methods.

Within-class spectral variation and between-class spectral confusion in remotely sensed imagery degrades the performance of built-up area detection when using planar texture, shape, and spectral features. Terrain slopes and building heights extracted from auxiliary data, such as Digital Surface Models (DSMs) however, can improve the results. Stereo imagery incorporates height information unlike single remotely sensed images. In this study, a new Stereo Pair Disparity Index (SPDI) for indicating built-up areas is calculated from stereo-extracted disparity information. Further, a new method of detecting built-up areas from stereo pairs is proposed based on the SPDI, using disparity information to establish the relationship between two images of a stereo pair. As shown in the experimental results for two stereo pairs covering different scenes with diverse urban settings, the SPDI effectively differentiates between built-up and non-built-up areas. Our proposed method achieves higher accuracy built-up area results from stereo images than the traditional method for single images, and two other widely-applied DSM-based methods for stereo images. Our approach is suitable for spaceborne and airborne stereo pairs and triplets. Our research introduces a new effective height feature (SPDI) for detecting built-up areas from stereo imagery with no need for DSMs.

Surface soil moisture is an important environment variable that is dominant in a variety of research and application areas. Acquiring spatiotemporal continuous soil moisture observations is therefore of great importance. Weather conditions can contaminate optical remote sensing observations on soil moisture, and the absence of remote sensors causes gaps in regional soil moisture observation time series. Therefore, reconstruction is highly motivated to overcome such contamination and to fill in such gaps. In this paper, we propose a novel image reconstruction algorithm that improved upon the Satellite and In situ sensor Collaborated Reconstruction (SICR) algorithm provided by our previous publication. Taking artificial neural networks as a model, complex and highly variable relationships between in situ observations and remote sensing soil moisture is better projected. With historical data for the network training, feedforward neural networks (FNNs) project in situ soil moisture to remote sensing soil moisture at better performances than conventional models. Consequently, regional soil moisture observations can be reconstructed under full cloud contamination or under a total absence of remote sensors. Experiments confirmed better reconstruction accuracy and precision with this improvement than with SICR. The new algorithm enhances the temporal resolution of high spatial resolution remote sensing regional soil moisture observations with good quality and can benefit multiple soil moisture-based applications and research. [ABSTRACT FROM AUTHOR]

With the widespread application of location-based services, the appropriate representation of indoor spaces and efficient indoor 3D reconstruction have become essential tasks. Due to the complexity and closeness of indoor spaces, it is difficult to develop a versatile solution for large-scale indoor 3D scene reconstruction. In this paper, an annotated hierarchical Structure-from-Motion (SfM) method is proposed for low-cost and efficient indoor 3D reconstruction using unordered images collected with widely available smartphone or consumer-level cameras. Although the reconstruction of indoor models is often compromised by the indoor complexity, we make use of the availability of complex semantic objects to classify the scenes and construct a hierarchical scene tree to recover the indoor space. Starting with the semantic annotation of the images, images that share the same object were detected and classified utilizing visual words and the support vector machine (SVM) algorithm. The SfM method was then applied to hierarchically recover the atomic 3D point cloud model of each object, with the semantic information from the images attached. Finally, an improved random sample consensus (RANSAC) generalized Procrustes analysis (RGPA) method was employed to register and optimize the partial models into a complete indoor scene. The proposed approach incorporates image classification in the hierarchical SfM based indoor reconstruction task, which explores the semantic propagation from images to points. It also reduces the computational complexity of the traditional SfM by avoiding exhausting pair-wise image matching. The applicability and accuracy of the proposed method was verified on two different image datasets collected with smartphone and consumer cameras. The results demonstrate that the proposed method is able to efficiently and robustly produce semantically and geometrically correct indoor 3D point models.