Spatio-temporal analysis of river morphological changes and erosion detection using very high resolution satellite image

Semantic segmentation of remote sensing images enables in particular land-cover map generation for a given set of classes. Very recent literature has shown the superior performance of deep convolutional neural networks (DCNN) for many tasks, from object recognition to semantic labelling, including the classification of Very High Resolution (VHR) satellite images. However, while plethora of works aim at improving object delineation on geographically restricted areas, few tend to solve this classification task at very large scales. New issues occur such as intra-class class variability, diachrony between surveys, and the appearance of new classes in a specific area, that do not exist in the predefined set of labels. Therefore, this work intends to (i) perform large scale classification and to (ii) expand a set of land-cover classes, using the off-the-shelf model learnt in a specific area of interest and adapting it to unseen areas.

Case instance segmentation of small farmland based on Mask R-CNN of feature pyramid network with double attention mechanism in high resolution satellite images

Assessment and monitoring of forest structure is frequently done with absolute density measures with field forest inventory data and expansion methods. The development of basal area and the number of trees estimation functions with data derived from very high spatial resolution satellite images enable their short-term and cost-effective evaluation, allowing also the estimation for the area not requiring extrapolation methods. The functions of basal area and the number of trees per hectare are based on crown cover obtained with very high spatial resolution satellite images for two evergreen oaks and umbrella pine. The three tree species are especially important in the agroforestry systems of the Mediterranean region. The linear functions fitted for pure stands of the three species and mixed stands of cork and holm oak and of cork oak and umbrella pine showed a better performance for basal area than for the number of trees per hectare. The inclusion of dummy variables for species composition improved the accuracy of the functions.

Agricultural intensification and efficient use and targeting of fertilizer inputs on smallholder farms is key to sustainably improve food security. The objective of this paper is to demonstrate how high-resolution satellite and unmanned aerial vehicle (UAV) images can be used to assess the spatial variability of yield, and yield response to fertilizer. The study included 48 and 50 smallholder fields monitored during the 2014 and 2015 cropping seasons south-east of Koutiala (Mali), cropped with the five major crops grown in the area (cotton, maize, sorghum, millet and peanuts). Each field included up to five plots with different fertilizer applications and one plot with farmer practice. Fortnightly, in-situ in each field data were collected synchronous with UAV imaging using a Canon S110 NIR camera. A concurrent series of very high-resolution satellite images was procured and these images were used to mask out trees. For each plot, we calculated vegetation index means, medians and coefficients of variation. Cross-validated general linear models were used to assess the predictability of relative differences in crop yield and yield response to fertilizer, explicitly accounting for the effects of fertility treatments, between-field and within-field variabilities. Differences between fields accounted for a much larger component of variation than differences between fertilization treatments.Vegetation indices from UAV images strongly related to ground cover (R2 = 0.85), light interception (R2 = 0.79) and vegetation indices derived from satellite images (R2 values of about 0.8). Within-plot distributions of UAV-derived vegetation index values were negatively skewed, and within-plot variability of vegetation index values was negatively correlated with yield. Plots on shallow soils with poor growing conditions showed the largest within-plot variability. GLM models including UAV derived estimates of light interception explained up to 78% of the variation in crop yield and 74% of the variation in fertilizer response within a single field. These numbers dropped to about 45% of the variation in yield and about 48% of the variation in fertilizer response when lumping all fields of a given crop, with Q2 values of respectively 22 and 40% respectively when tested with a leave-field-out procedure. This indicates that remotely sensed imagery doesn’t fully capture the influence of crop stress and management. Assessment of crop fertilizer responses with vegetation indices therefore needs a reference under similar management. Spatial variability in UAV-derived vegetation index values at the plot scale was significantly related to differences in yields and fertilizer responses. The strong relationships between light interception and ground cover indicate that combining vertical photographs or high-resolution remotely sensed vegetation indices with crop growth models allows to explicitly account for the spatial variability and will improve the accuracy of yield and crop production assessments, especially in heterogeneous smallholder conditions.

This paper presents a two-level Active Learning (AL) classification method for the interactive detection of earthquake-induced debris via the synergetic use of post-disaster Very High Resolution (VHR) satellite and local decimeter-resolution aerial images. The proposed method is performed by interactively guiding the human expert in the collection of labeled training samples from aerial images and optimally planning further aerial surveys. A label propagation mechanism is adopted to reliably propagate the labeled pixels annotated by the user on the aerial image by visual photointerpretation to the (lower resolution) satellite image. The experimental analysis is carried out using post-disaster images of the 2010 Yushu earthquake in China. The obtained results confirm that the proposed method can significantly reduce the user annotation effort and the cost for acquiring additional aerial images leading to more accurate and timely debris detection maps.

Satellite imagery has been used to improve scientific research worldwide. In this study, the southern right whale (Eubalaena australis) was chosen to test the use of medium, high, and very high resolution (VHR) satellite images, on the Brazilian breeding ground. These images were used to identify the whales and were compared to aerial survey data collected in the same area. The VHR satellite images from the Pleiades‐1A satellite, available on Google Earth, displayed the best results when compared to those from Sentinel 2, Landsat 8, Rapid Eye, and Planet Scope. No significant differences were observed (Mann‐Whitney U test) between the possible whales recorded in the satellite images and of real whales recorded in situ by aerial surveys, while considering either the number of groups (p = .841, n = 5) or the total number of animals (p = .222, n = 5). Further, when using VHR images, the geographical positions of the whales recorded in situ had a positive correlation with the positions generated from the satellite images (Mantel test: r = 0.52, p = .001, n = 13). This technique may represent an important tool for detecting right whales, especially in countries where research funding is scarce.

As the acquisition of very high resolution (VHR) satellite images becomes easier owing to technological advancements, ever more stringent requirements are being imposed on automatic image interpretation. Moreover, per-pixel classification has become the focus of research interests in this regard. However, the efficient and effective processing and the interpretation of VHR satellite images remain a critical task. Convolutional neural networks (CNNs) have recently been applied to VHR satellite images with considerable success. However, the prevalent CNN models accept input data of fixed sizes and train the classifier using features extracted directly from the convolutional stages or the fully connected layers, which cannot yield pixel-to-pixel classifications. Moreover, training a CNN model requires large amounts of labeled reference data. These are challenging to obtain because per-pixel labeled VHR satellite images are not open access. In this paper, we propose a framework called the unsupervised-restricted deconvolutional neural network (URDNN). It can solve these problems by learning an end-to-end and pixel-to-pixel classification and handling a VHR classification using a fully convolutional network and a small number of labeled pixels. In URDNN, supervised learning is always under the restriction of unsupervised learning, which serves to constrain and aid supervised training in learning more generalized and abstract feature. To some degree, it will try to reduce the problems of overfitting and undertraining, which arise from the scarcity of labeled training data, and to gain better classification results using fewer training samples. It improves the generality of the classification model. We tested the proposed URDNN on images from the Geoeye and Quickbird sensors and obtained satisfactory results with the highest overall accuracy (OA) achieved as 0.977 and 0.989, respectively. Experiments showed that the combined effects of additional kernels and stages may have produced better results, and two-stage URDNN consistently produced a more stable result. We compared URDNN with four methods and found that with a small ratio of selected labeled data items, it yielded the highest and most stable results, whereas the accuracy values of the other methods quickly decreased. For some categories with fewer training pixels, accuracy for categories from other methods was considerably worse than that in URDNN, with the largest difference reaching almost 10%. Hence, the proposed URDNN can successfully handle the VHR image classification using a small number of labeled pixels. Furthermore, it is more effective than state-of-the-art methods.

ABSTRACTAutomatic building extraction from High-Resolution Satellite (HRS) image has been an important field of research in the area of remote sensing. Different techniques related to radiometric, geometric, edge detection and object based have already been discussed and used by various researchers for building extraction. However, faithfulness of extraction is highly dependent on user intervention. This study proposes a novel morphological based automatic approach for extraction of buildings using HRS image. Moreover, using such an automatic approach, buildings can be detected having different size and shape. The proposed technique integrates morphological Top-hat filter, and K-means algorithm to extract buildings having bright and dark rooftops. Further, extracted bright and dark rooftop building segments have been combined together to obtain the final output that contains final extracted building segments. In order to eliminate false-detected buildings, different parameters like area, eccentricity, and axis ratio (major/minor axis) have been used. The suitability of the technique has been judged using different indicators such as completeness, correctness and quality.

Third-dimension information is of a great importance for several remote sensing applications, such as building detection. The main data-source for these applications is very high resolution (VHR) satellite images which allow detailed mapping of complex environments. Stereo VHR satellite images allow the extraction of two correlated types of third-dimension information: disparity and elevation information. While the disparity is measured directly, the elevation information is derived computationally. To measure the disparity information, two overlapped images are matched. However, for the backward and forward off-nadir VHR stereo images, building facades occlude areas and hence create many data gaps. When the disparity is required to represent only the off-terrain objects, interpolation and normalization techniques are typically used. However, in dense urban environments, these techniques destroy the quality of the generated data. Therefore, this paper proposes a registration-based technique to measure the disparity of the above-ground objects. The technique includes constructing epipolar images and registering them using common terrain- level features to allow direct disparity mapping for the off-terrain objects. After the implementation, the negative effects of occlusion in the off-nadir VHR stereo images are mitigated through direct disparity mapping of the above-ground objects and bypassing the interpolation and normalization steps.

OpenStreetMap(OSM) provides extensive coverage of road network that can be a source to prepare training samples for automated road mapping using very high resolution(VHR) satellite images and machine learning. However, several studies have shown that the pervasive spatial misalignment between OSM vector data and VHR images yields poor quality training samples and thereby compromises the performance of models. In this study, we undertake to address this shortcoming and develop an automated line segment shifting workflow to yield OSM vector data that aligns with VHR road features to generate high quality training samples. The approach leverages the standard deviation differences of road pixels and background information to guide the transformations. By taking into account trees, shadows, cars and water body on or beside the road when STD was calculated, our method is robust to various road obstacles. Experimental validations are conducted to confirm the correctness of aligned OSM data showing up to 338% improvement compared with original OSM. Finally, based on visual inspection, the road map generated by aligned OSM also presents obvious quality improvement in comparison with map created by original OSM.

China-Pakistan Economic Corridor (CPEC) is a framework of regional connectivity, which will not only benefit China and Pakistan but will have positive impact on Iran, Afghanistan, India, Central Asian Republic, and the region. The surrounding area in CPEC is prone to frequent disruption by geological hazards mainly landslides in northern Pakistan. Comprehensive landslide inventory and susceptibility assessment are rarely available to utilize for landslide mitigation strategies. This study aims to utilize the high-resolution satellite images to develop a comprehensive landslide inventory and subsequently develop landslide susceptibility maps using multiple techniques. The very high-resolution (VHR) satellite images are utilized to develop a landslide inventory using the visual image classification techniques, historic records and field observations. A total of 1632 landslides are mapped in the area. Four statistical models i.e., frequency ratio, artificial neural network, weights of evidence and logistic regression were used for landslide susceptibility modeling by comparing the landslide inventory with the topographic parameters, geological features, drainage and road network. The developed landslides susceptibility maps were verified using the area under curve (AUC) method. The prediction power of the model was assessed by the prediction rate curve. The success rate curves show 93%, 92.8%, 92.7% and 87.4% accuracy of susceptibility maps for frequency ratio, artificial neural network, weights of evidence and logistic regression, respectively. The developed landslide inventory and susceptibility maps can be used for land use planning and landslide mitigation strategies.

When a high-resolution satellite is imaging on orbit, the relative motion between the sensory optical elements inside the camera may be caused by micro-vibration, which results in degraded images. In order to study the effect of micro-vibration on high resolution satellite imaging, a micro-vibration analysis method of space camera based on target image is proposed in this paper. Firstly, the different factors of micro-vibration which will affect the image quality in different degrees are introduced. Then, the method which can realize the direct measurement of image motion in the image is proposed. The method can analyze the impact of micro-vibration on the space camera directly and get the accuracy number of the image motion, which can provide the basis for the influence analysis of the satellite image quality and the final correction. Finally, we take a factual space camera for example to calculate and analyze the test data by using this model on the condition of the satellite. We get the image motion set by the micro-vibration on focal plane and accomplish the influence analysis method of micro-vibration on high resolution satellite imaging. It is concluded that the proposed method is reasonable and practical. The method proposed by this paper can be referred to for improved design and vibration suppression.

Buildings are one of the main objects in urban remote sensing and photogrammetric computer vision applications using satellite data. In this paper a superpixel-based approach is presented to refine 3D building models from stereo satellite imagery. First, for each epoch in time, a multispectral very high resolution (VHR) satellite image is segmented using an efficient superpixel, called edge-based simple linear iterative clustering (ESLIC). The ESLIC algorithm segments the image utilizing the spectral and spatial information, as well as the statistical measures from the gray-level co-occurrence matrix (GLCM), simultaneously. Then the resulting superpixels are imposed on the corresponding 3D model of the scenes taken from each epoch. Since ESLIC has high capability of preserving edges in the image, normalized digital surface models (nDSMs) can be modified by averaging height values inside superpixels. These new normalized models for epoch 1 and epoch 2, are then used to detect the 3D change of each building in the scene.

The orthorectification of very high resolution (VHR) satellite images is a fundamental process to ensure the interoperability of the spatial information obtained from them. Therefore, previous studies have used different types of inputs, including multiple sources of control points and digital elevation models (DEM) of all kinds, in addition to testing different optimization methods. This research aims to jointly use and evaluate the use of the evolutionary algorithm Particle Swarm Optimization (PSO), stereoscopic points from photogrammetric blocks and DEM from different sources, to obtain cartographic products of scale 1:10.000 comparing their results with those obtained by ordinary least squares from previous experiments. The methodological proposal includes the entire procedure for the estimation and selection of the coefficients of the Rational Functional Model (RFM) spatial arrangement model using Particle Swarm Optimization and the Feature Condition Analysis method together with all the flow necessary for the generation of the final orthoimage. As a result, it is observed that the use of the PSO improves on average by 3% the positional accuracy of the orthoimage, however its use requires high computational resources and also this type of optimization method is not available yet in specialized software, being difficult for massive implementation in cartographic production processes.

The number of high and very high resolution (VHR) optical satellite sensors, as well as the number of medium resolution satellites is continuously growing. However, not all high-resolution optical satellite imaging cameras have a sufficient and stable calibration in time. Due to their high agility in rotation, a quick change in viewing direction can lead to satellite attitude oscillation, causing image distortions and thus affecting image geometry and geo-positioning accuracy. This paper presents an approach based on re-projection of regularly distributed 3D ground points from object in image space, to detect and estimate the periodic distortions of Pléiades tri-stereo imagery caused by satellite attitude oscillations. For this, a hilly region was selected as a test site. Consequently, we describe a complete processing pipeline for computing the systematic height errors (deformations, waves) of the satellite-based digital elevation model by using a Lidar high resolution terrain model. Ground points with fixed positions, but with two elevations (actual and corrected) are then re-projected to the satellite images with the aid of the Rational Polynomial Coefficients (RPCs) provided with the imagery. Therefore, image corrections (displacements) are determined by computing the differences between the distinct positions of corresponding points in image space. Our experimental results in Allentsteig (Lower Austria) show that the systematic height errors of satellite-based elevation models cannot be compensated with an usual or even high number of Ground Control Points (GCPs) for RPC bias correction, due to insufficiently known image orientations. In comparison to a reference Lidar Digital Terrain Model (DTM), the computed elevation models show undulation effects with a maximum height difference of 0.88 m in along-track direction. With the proposed method, image distortions in-track direction with amplitudes of less than 0.15 pixels were detected. After applying the periodic distortion compensation to all three images, the systematic elevation discrepancies from the derived elevation models were successfully removed and the overall accuracy in open areas improved by 33% in the RMSE. Additionally, we show that a coarser resolution reference elevation model (AW3D30) is not feasible for improving the geometry of the Pléiades tri-stereo satellite imagery.