Search

International audience; IntroductionIn the vicinity ofold uranium mines, wetlands prove to be specific zones with significant amountsof accumulated U. At the center ofthe ancient mining district of Lachaux in France (45.994°N,3.596°E), the site of Rophin (within the ZATU: Uranium Working Zone = Long Term SocioEcological Research Tool ofCNRS) is characterized by awetland areawith high U concentrationsup to 3.6 g.kg-1. In this context, the main challenge is to describe the behavior ofU and relevantdecay products in the wetland using a predictive model that combines chemical speciation andtransport.MethodsThe overall adopted scientific approach is to propose a mechanistic description ofthe mobility ofthese elements, from the molecular scale (speciation) to in situ behavior (lability), by couplingfield and laboratory experiments with modelling. Batch desorption and column experiments werecarried out with in situ soil samples to assess the mobile fraction part of U and its distributioncoefficients (Kd). Labile behavior of U was examined directly on site by using the DGT/DETtechniques while U speciation was investigated by the combination ofseveral techniques (SEM,XAS). From laboratory data, predictive modelling (smart-Kd model) was implemented under sitespecific conditions.ResultsObservations by SEM, XANES and EXAFS confirmed the U transportin particulate form duringthe mining activities and the establishment of reducing conditions over time, implying thepresence of both U(IV) and U(VI). Labile quantity and Kd values of U were confirmed to behomogeneous at the scale of the Rophin wetland and consistent with in situ labile behaviordeduced from the DGT/DET approach, considering a kinetically controlled interaction.ConclusionsThanks to the combination of different techniques, a better understanding of what happened inthe wetland over 70 years can be achieved. All these data should now allow us to define the keyparameters to be integrated in the reactive part ofthe transport model ofthe Rophin site

Precise and accurate three-dimensional geospatial data has become increasingly available thanks to advances in both Terrestrial Laser Scanning (TLS) and Structure-from-Motion Photogrammetry (SfM). These tools provide valuable information for mapping geomorphological features and detect surface changes in mountainous environments. The exploitation of 3D point-clouds has been proven tremendously useful in the field of geosciences. It remains, however, controversial whether cost efficient photogrammetry can provide as accurate and reliable geospatial information as the significantly more expensive laser scanning or not. In this study, a rockfall case site in the territory of Obergurgl, Austria, is investigated in order to provide answers to the above question in a complex environment. The analysis includes different terrestrial photogrammetry configurations aiming to comprehensively define the strengths and limitations of terrestrial photogrammetry over TLS. The latter constitutes an optimized methodology that provides guidelines for costly future assessments as part of the site investigation phase in geohazard management. There are no doubts that compared to traditional and conventional surveying methods TLS and Photogrammetry both offer products much faster and with a much higher data density. In the current study, we show that when photogrammetry is applied following a well-defined optimized strategy, it can be potentially an adequate alternative to more costly TLS datasets for mass movement assessment and monitoring purposes.

One of the major challenges in precision viticulture in Europe is the detection and mapping of flavescence dorée (FD) grapevine disease to monitor and contain its spread. The lack of effective cures and the need for sustainable preventive measures are nowadays crucial issues. Insecticides and the plants uprooting are commonly employed to withhold disease infection, even if these solutions imply serious economic consequences and a strong environmental impact. The development of a rapid strategy to identify the disease is required to cover large portions of the crop and thus to limit damages in a time-effective way. This paper investigates the use of Unmanned Aerial Vehicles (UAVs), a cost-effective approach to early detection of diseased areas. We address this task with an object detection deep network, Faster R-CNN, instead of a traditional pixel-wise classifier. This work tests Faster R-CNN performance on this specific application through a comparative analysis with a pixel-wise classification algorithm (Random Forest). To take advantage of the full image resolution, the experimental analysis is performed using the original UAV imagery acquired in real conditions (instead of the derived orthomosaic). The first result of this paper is the definition of a new dataset for FD disease identification by UAV original imagery at the canopy scale. Moreover, we demonstrate the feasibility of applying Faster-R-CNN as a quasi-real-time alternative solution to semantic segmentation. The trained Faster-R-CNN achieved an average precision of 82% on the test set.

Dynamic Time Warping (DTW) has been successfully used for crops mapping due to its capability to achieve good classification results when a reduced number of training samples and irregular satellite image time series is available. Despite its recognized advantages, DTW does not account for the duration and seasonality of crops and local differences when assessing the similarity between two temporal sequences. In this study, we implemented a Weighted Derivative modification of DTW (WDDTW) and compared it with DTW and Time Weighted Dynamic Time Warping (TWDTW) for crops mapping. We show that WDDTW outperformed DTW achieving an overall accuracy of 67 %, whereas DTW obtained an accuracy of 57%. Yet, TWDTW performed better than both methods obtaining an accuracy of 88%.

Land use is an important variable in remote sensing which describes the functions carried out on a piece of land in order to obtain benefits and is especially useful to the personnel working in the fields of urban management and planning. The land use information is maintained by national mapping agencies in geo-spatial databases. Commonly, land use data is stored in the form of polygon objects; the label of the object indicates land use. The main goal of classification of land use objects is to update an existing database in an automatic process. Recently, Convolutional Neural Networks (CNN) have been widely used to tackle this task utilizing high resolution aerial images (and derived data such as digital surface model). One big challenge classifying polygons is to deal with the large variation in their geometrical extent. For this challenge, we adopt the method of Yang et al. (2019) to decompose polygons into regular patches of fixed size. The decomposition leads to two sets of polygons: small and large, where the former suffers from a lower identification rate. In this paper, we propose CNN methods which incorporate dense connectivity and integrate it with intermediate information via global average pooling to improve land use classification, mainly focusing on small polygons. We present different network variants by incorporating intermediate information via global average pooling from different stages of the network. We test our methods on two sites; our experiments show that the dense connectivity and integration of intermediate information has a positive effect not only on the classification accuracy on the whole but also on the identification of small polygons. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

Crop lodging – the bending of crop stems from the vertical – is a major yield-reducing factor in cereal crops and causes deterioration in grain quality. Accurate assessment of crop lodging is important for improving estimates of crop yield losses, informing insurance loss adjusters and influencing management decisions for subsequent seasons. The role of remote sensing data, particularly synthetic aperture radar (SAR) data has been emphasized in the recent literature for crop lodging assessment. However, the effect of lodging on SAR scattering mechanisms is still unknown. Therefore, this research aims to understand the possible change in scattering mechanisms due to lodging by investigating SAR image pairs before and after lodging. We conducted the study in 26 wheat fields in the Bonifiche Ferraresi farm, located in Jolanda di Savoia, Ferrara, Italy. We measured temporal crop biophysical (e.g. crop angle) parameters and acquired multi-incidence angle RADARSAT-2 (R-2 FQ8-27° and R-2 FQ21-41°) and Sentinel-1 (S-1 40°) images corresponding to the time of field observations. We extracted metrics of SAR scattering mechanisms from RADARSAT-2 and Sentinel-1 image pairs in different zones using the unsupervised H/α decomposition algorithm and Wishart classifier. Contrasting results were obtained at different incidence angles. Bragg surface scattering increased in the case of S-1 (6.8%), R-2 FQ8 (1.8%) while at R-2 FQ21, it decreased (8%) after lodging. The change in double bounce scattering was more prominent at low incidence angle. These observations can guide future use of SAR-based information for operational crop lodging assessment in particular, and sustainable agriculture in general.

Deforestation is a wide-reaching problem, responsible for serious environmental issues, such as biodiversity loss and global climate change. Containing approximately ten percent of all biomass on the planet and home to one tenth of the known species, the Amazon biome has faced important deforestation pressure in the last decades. Devising efficient deforestation detection methods is, therefore, key to combat illegal deforestation and to aid in the conception of public policies directed to promote sustainable development in the Amazon. In this work, we implement and evaluate a deforestation detection approach which is based on a Fully Convolutional, Deep Learning (DL) model: the DeepLabv3+. We compare the results obtained with the devised approach to those obtained with previously proposed DL-based methods (Early Fusion and Siamese Convolutional Network) using Landsat OLI-8 images acquired at different dates, covering a region of the Amazon forest. In order to evaluate the sensitivity of the methods to the amount of training data, we also evaluate them using varying training sample set sizes. The results show that all tested variants of the proposed method significantly outperform the other DL-based methods in terms of overall accuracy and F1-score. The gains in performance were even more substantial when limited amounts of samples were used in training the evaluated methods. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

With the rapid urbanization and the dynamics in land transactions, Turkish cadastre, as in many other countries, is facing challenges in the daily recording of sales, donations, taxations, and mortgages on land. Especially with the modern constructions and complex interrelationships of rights, restrictions, and responsibilities (RRR), the third dimension should not be forgotten. In this context, the design of a new cadastre data model for Turkey is essential. Inspired by this need, with this study, we aim in proposing a new cadastre model based on international standards such as Land Administration Data Model (LADM) and CityGML. LADM represents the legal and administrative aspects of the cadastral objects but does not show the semantic and 3D geometrical representation of physical cadastral objects which are required for the process of 3D cadastre. Therefore, in the paper, we propose an Application Domain Extension (ADE) for the cadastral objects that expands the integration of LADM and CityGML data model with the legal and administrative concepts defined in the Turkish Law. The study presents a detailed overview of the Turkish legal cadastre system and a proposal for its physical realization based on international standards. In addition, the developed ADE is also valuable for cadastral services undertaken by the General Directorate of Land Registry and Cadastre (GDLRC). It could also be used as a basis of a 3D national data standard for cadastral information systems.

This study investigates the ongoing postseismic deformation induced by two moderate mainshocks of Mw 6.1 and Mw 6.0, 2017 Hojedk earthquake in Southern Iran. Available Sentinel-1 TOPS C-band Synthetic Aperture Radar (SAR) images over about one year after the earthquakes are used to analyze the postseismic activities. An adaptive method incorporating Independent Component Analysis (ICA) and multi-temporal Small BAseline Subset (SBAS) Interferometric SAR (InSAR) techniques is proposed and implemented to recover the rapid deformation. This method is applied to the series of interferograms generated in a fully constructed SBAS network to retrieve the postseismic deformation signal. ICA algorithm uses a linear transformation to decompose the input mixed signal to its source components, which are non-Gaussian and mutually independent. This analysis allows extracting the low rate postseismic deformation signal from a mixture of interferometric phase components. The independent sources recovered from the multi-temporal InSAR dataset are then analyzed using a group clustering test aiming to identify and enhance the undescribed deformation signal. Analysis of the processed interferograms indicates a promising performance of the proposed method in determining tectonic deformation. The proposed method works well, mainly when the tectonic signal is dominated by the undesired signals, including atmosphere or orbital/unwrapping noise that counts as temporally uncorrelated components.In contrast to the standard SBAS time series method, the ICA-based time series analysis estimates the cumulative deformation with no prior assumption about elevation dependence of the interferometric phase or temporal nature of the tectonic signal. Application of the method to 433 Sentinel-1 pairs within the dataset reports two distinct deformation patches corresponding to the postseismic deformation. Besides the performance of the ICA-based analysis, the proposed method automatically detects rapid or low rate tectonic processes in unfavorable conditions.

Recently, great progress has been made in formulating dense disparity estimation as a pixel-wise learning task to be solved by deep convolutional neural networks. However, most resulting pixel-wise disparity maps only show little detail for small structures. In this paper, we propose a two-stage architecture: we first learn initial disparities using an initial network, and then employ a disparity refinement network, guided by the initial results, which directly learns disparity corrections. Based on the initial disparities, we construct a residual cost volume between shared left and right feature maps in a potential disparity residual interval, which can capture more detailed context information. Then, the right feature map is warped with the initial disparity and a reconstruction error volume is constructed between the warped right feature map and the original left feature map, which provides a measure of correctness of the initial disparities. The main contribution of this paper is to combine the residual cost volume and the reconstruction error volume to guide training of the refinement network. We use a shallow encoder-decoder module in the refinement network and do learning from coarse to fine, which simplifies the learning problem. We evaluate our method on several challenging stereo datasets. Experimental results demonstrate that our refinement network can significantly improve the overall accuracy by reducing the estimation error by 30% compared with our initial network. Moreover, our network also achieves competitive performance compared with other CNN-based methods. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

Deep learning-based semantic segmentation models for building delineation face the challenge of producing precise and regular building outlines. Recently, a building delineation method based on frame field learning was proposed by Girard et al. (2020) to extract regular building footprints as vector polygons directly from aerial RGB images. A fully convolution network (FCN) is trained to learn simultaneously the building mask, contours, and frame field followed by a polygonization method. With the direction information of the building contours stored in the frame field, the polygonization algorithm produces regular outlines accurately detecting edges and corners. This paper investigated the contribution of elevation data from the normalized digital surface model (nDSM) to extract accurate and regular building polygons. The 3D information provided by the nDSM overcomes the aerial images’ limitations and contributes to distinguishing the buildings from the background more accurately. Experiments conducted in Enschede, the Netherlands, demonstrate that the nDSM improves building outlines’ accuracy, resulting in better-aligned building polygons and prevents false positives. The investigated deep learning approach (fusing RGB + nDSM) results in a mean intersection over union (IOU) of 0.70 in the urban area. The baseline method (using RGB only) results in an IOU of 0.58 in the same area. A qualitative analysis of the results shows that the investigated model predicts more precise and regular polygons for large and complex structures.

Point clouds serve as the raw material for various models, such as Building Information Models (BIM). In this work, we investigate the reconstruction steps needed to create models that can be utilized directly for agent-based simulations. The input data for the reconstruction is captured with an indoor mobile mapping system. To show the prominence of this idea, we run social distancing and evacuation simulations on the reconstructed models. The simulations are run with multiple agents using a vision-based pedestrian model and A∗-based path finding algorithm. The limitations of this approach are discussed. The video of the simulation is shared with the audience. Link to the video: https://youtu.be/r2D3IxXt7Ls

The coastline of the German Wadden Sea is constantly subjected to the tides and the tidal-induced environmental changes like erosion and accumulation of sediments need to be monitored constantly. This task requires digital elevation models (DEMs), which are derived from remote sensing data. To model those DEMs, a separation of data collected over landmasses and water bodies is required. In the GeoWAM project the potential of airborne SAR-data (F-SAR) is investigated for monitoring purposes in the Wadden Sea. As part of the project, this paper focuses on the suitability of F-SAR data regarding the derivation of water-land-boundaries (WLBs). Therefore, water-land-boundaries based on independent data sets are compared and evaluated. Analyzed data sets include data collected via F-SAR, airborne laserscanning (ALS), on site GNSS measured WLB points and sea-level data from two acoustic gauges. The algorithms were tested on a study site on Spiekeroog island. Our results show, that the accuracies of the derived WLBs mostly depend on the on-site topography and sediments. The spatial deviation between the reference data and the approximated WLBs is mostly less than 2 m horizontally and 0.15 m vertically. Identified challenges to overcome are mostly related to processing of F-SAR data in areas with highly water saturated sediments. Our results suggest, that F-SAR data in tidal flats is not necessarily dependent on further supplementing surveys, as one of the main advantages of the F-SAR data is the potential to derive DEMs and WLBs from the same data set.

Updated information on urban land use allows city planners and decision makers to conduct large scale monitoring of urban areas for sustainable urban growth. Remote sensing data and classification methods offer an efficient and reliable way to update such land use maps. Features extracted from land cover maps are helpful on performing a land use classification task. Such prior information can be embedded in the design of a deep learning based land use classifier by applying a multitask learning setup—simultaneously solving a land use and a land cover classification task. In this study, we explore a fully convolutional multitask network to classify urban land use from very high resolution (VHR) imagery. We experimented with three different setups of the fully convolutional network and compared it against a baseline random forest classifier. The first setup is a standard network only predicting the land use class of each pixel in the image. The second setup is a multitask network that concatenates the land use and land cover class labels in the same output layer of the network while the other setup accept as an input the land cover predictions, predicted by a subpart of the network, concatenated to the original input image patches. The two deep multitask networks outperforms the other two classifiers by at least 30% in average F1-score.

The classification of Mobile Laser Scanner (MLS) data is challenging due to the combination of high variation in point density with a high variation of object appearances. The way how objects appear in the MLS data highly depends on the speed and orientation of the mobile mapping platform and the occlusion by other vehicles. There have been many approaches dealing with the geometric and contextual appearance of MLS points, voxels and segments to classify the MLS data. We present a completely different strategy by fusing the MLS data with a large scale topographic map. Underlying assumption is that the map delivers a clear hint on what to expect in the MLS data, at its approximate location. The approach presented here first fuses polygon objects, such as road, water, terrain and buildings, with ground and non-ground MLS points. Non-ground MLS points above roads and terrain are further classified by segmenting and matching the laser points to corresponding map point objects. The segmentation parameters depend on the class of the map points. We show that the fusion process is capable of classifying MLS data and detecting changes between the map and MLS data. The segmentation algorithm is not perfect, at some occasions not all the MLS points are correctly assigned to the corresponding map object. However, it is without doubt that the proposed map fusion delivers a very rich labelled point cloud automatically, which in future work can be used as training data in deep learning approaches.

In recent years, the importance of indoor mapping increased in a wide range of applications, such as facility management and mapping hazardous sites. The essential technique behind indoor mapping is simultaneous localization and mapping (SLAM) because SLAM offers suitable positioning estimates in environments where satellite positioning is not available. State-of-the-art indoor mobile mapping systems employ Visual-based SLAM or LiDAR-based SLAM. However, Visual-based SLAM is sensitive to textureless environments and, similarly, LiDAR-based SLAM is sensitive to a number of pose configurations where the geometry of laser observations is not strong enough to reliably estimate the six-degree-of-freedom (6DOF) pose of the system. In this paper, we present different strategies that utilize the benefits of the inertial measurement unit (IMU) in the pose estimation and support LiDAR-based SLAM in overcoming these problems. The proposed strategies have been implemented and tested using different datasets and our experimental results demonstrate that the proposed methods do indeed overcome these problems. We conclude that IMU observations increase the robustness of SLAM, which is expected, but also that the best reconstruction accuracy is obtained not with a blind use of all observations but by filtering the measurements with a proposed reliability measure. To this end, our results show promising improvements in reconstruction accuracy.

The PolSAR calibration ensures that the relationship between the SAR observations and the target characteristics on the ground are consistent and resembles the theoretical estimation which in turn improves the overall data quality. Essentially, calibration prevents the propagation of uncertainty into further analysis to characterise the target. In this study, the UAVSAR L-Band data of Rosamond dry lake bed has been calibrated. The calibration of amplitude and phase are carried out with the help of the corner reflector array present in the Rosamond site. The dataset is further calibrated for the crosstalk and channel imbalance using the Quegan’s distortion model. Since the crosstalk distortion model requires an accurate estimation of the covariance matrix, the optimal kernel size for the its computation is selected based on the distortion model behaviour with varying window sizes. Furthermore, the effectiveness of the calibration process has been studied using polarimetric signatures and other statistical measures.

With the development of LiDAR and photogrammetric techniques, more and more point clouds are available with high density and in large areas. Point cloud interpretation is an important step before many real applications like 3D city modelling. Many supervised machine learning techniques have been adapted to semantic point cloud segmentation, aiming to automatically label point clouds. Current deep learning methods have shown their potentials to produce high accuracy in semantic point cloud segmentation tasks. However, these supervised methods require a large amount of labelled data for proper model performance and good generalization. In practice, manual labelling of point clouds is very expensive and time-consuming. Active learning can iteratively select unlabelled samples for manual annotation based on current statistical models and then update the labelled data pool for next model training. In order to effectively label point clouds, we proposed a segment based active learning strategy to assess the informativeness of samples. Here, the proposed strategy uses 40% of the whole training dataset to achieve a mean IoU of 75.2% which is 99.1% of the accuracy in mIoU obtained from the model trained on the full dataset, while the baseline method using same amount of data only reaches 69.6% in mIoU corresponding to 90.9% of the accuracy in mIoU obtained from the model trained on the full dataset.

Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust method has been found yet that can transfer and generalize well over a variety of geographic locations and typologies of damages. Since damages can be seen as anomalies, occurring sparingly over time and space, we propose to use an anomaly detecting Generative Adversarial Network (GAN) to detect damages. The main advantages of using GANs are that only healthy unannotated images are needed, and that a variety of damages, including the never before seen damage, can be detected. In this study we aimed to investigate 1) the ability of anomaly detecting GANs to detect degradation (potholes and cracks) in asphalt road infrastructures using Mobile Mapper imagery and building damage (collapsed buildings, rubble piles) using post-disaster aerial imagery, and 2) the sensitivity of this method against various types of pre-processing. Our results show that we can detect damages in urban scenes at satisfying levels but not on asphalt roads. Future work will investigate how to further classify the found damages and how to improve damage detection for asphalt roads.

Mobile mapping systems MMS equipped with cameras and laser scanners are widely used nowadays for different geospatial applications with centimetric accuracy either in project wise or national wise scales. The achieved positioning accuracy is very much related to the navigation unit, namely the GNSS and IMU onboard. Accordingly, in GNSS denied and degraded environments, the absolute positioning accuracy is worsened to few meters in some cases. Frequently, ground control points GCPs of a high positioning accuracy are used to align the MMS trajectories and to improve the accuracy when needed. The best way to integrate the MMS trajectories to the GCPs is by measuring them on the MMS images where the positioning accuracy is dropped. MMS images are mostly spherical panoramic (equirectangular) images and sometimes perspective and, in both types, it is required to precisely determine the images orientation in what is called as space resection or camera pose determination. For perspective images, the pose is conventionally determined by collinearity equations or by using projection and fundamental matrices. Whereas for equirectangular panoramic images it is based on resecting vertical and horizontal angles. However, there is still a challenge in the state–of–the–art of image pose determination because of the model nonlinearity and the sensitivity to proper initialization and spatial distribution of the points. In this research, a generic method is presented to solve the pose resection problem for the perspective and equirectangular images using oblique angles. The oblique angles are derived from the measured image coordinates and based on spherical trigonometry rules and vector geometry. The developed algorithm has proven to be highly stable and steadily converge to the global minimum. This is related to the robust geometric constraint offered by the oblique angles that are enclosed between the object points and the camera. As a result, the MMS trajectories are realigned accurately to the GCPs and the absolute accuracy is highly refined. Four experimental tests are presented where the results show the efficiency of the proposed angular based model in different cases of simulated and real data with different image types

The application of UAV-based aerial imagery has advanced exponentially in the past two decades. This can be attributed to UAV operational flexibility, ultra-high spatial resolution, inexpensiveness, and UAV-based sensors enhancement. Nonetheless, the application of multitemporal series of multispectral UAV imagery still suffers significant misregistration errors, and therefore becoming a concern for applications such as precision agriculture. Direct image georeferencing and co-registration is commonly done using ground control points; this is usually costly and time consuming. This research proposes a novel approach for automatic co-registration of multitemporal UAV imagery using intensity-based keypoints. The Speeded Up Robust Features (SURF), Binary Robust Invariant Scalable Keypoints (BRISK), Maximally Stable Extremal Regions (MSER) and KAZE algorithms, were tested and parameters optimized. Image matching performance of these algorithms informed the decision to pursue further experiments with only SURF and KAZE. Optimally parametrized SURF and KAZE algorithms obtained co-registration accuracies of 0.1 and 0.3 pixels for intra-epoch and inter-epoch images respectively. To obtain better intra-epoch co-registration accuracy, collective band processing is advised whereas one-to-one matching strategy is recommended for inter-epoch co-registration. The results were tested using a maize crop monitoring case and the; comparison of spectral response of vegetation between the UAV sensors, Parrot Sequoia and Micro MCA was performed. Due to the missing incidence sensor, spectral and radiometric calibration of Micro MCA imagery is observed to be key in achieving optimal response. Also, the cameras have different specifications and thus differ in the quality of their respective photogrammetric outputs.

Knowledge of tree species mapping and of dead wood in particular is fundamental to managing our forests. Although individual tree-based approaches using lidar can successfully distinguish between deciduous and coniferous trees, the classification of multiple tree species is still limited in accuracy. Moreover, the combined mapping of standing dead trees after pest infestation is becoming increasingly important. New deep learning methods outperform baseline machine learning approaches and promise a significant accuracy gain for tree mapping. In this study, we performed a classification of multiple tree species (pine, birch, alder) and standing dead trees with crowns using the 3D deep neural network (DNN) PointNet++ along with UAV-based lidar data and multispectral (MS) imagery. Aside from 3D geometry, we also integrated laser echo pulse width values and MS features into the classification process. In a preprocessing step, we generated the 3D segments of single trees using a 3D detection method. Our approach achieved an overall accuracy (OA) of 90.2% and was clearly superior to a baseline method using a random forest classifier and handcrafted features (OA = 85.3%). All in all, we demonstrate that the performance of the 3D DNN is highly promising for the classification of multiple tree species and standing dead trees in practice.

Modern machine learning, especially deep learning, which is used in a variety of applications, requires a lot of labelled data for model training. Having an insufficient amount of training examples leads to models which do not generalize well to new input instances. This is a particular significant problem for tasks involving aerial images: often training data is only available for a limited geographical area and a narrow time window, thus leading to models which perform poorly in different regions, at different times of day, or during different seasons. Domain adaptation can mitigate this issue by using labelled source domain training examples and unlabeled target domain images to train a model which performs well on both domains. Modern adversarial domain adaptation approaches use unpaired data. We propose using pairs of semantically similar images, i.e., whose segmentations are accurate predictions of each other, for improved model performance. In this paper we show that, as an upper limit based on ground truth, using semantically paired aerial images during training almost always increases model performance with an average improvement of 4.2% accuracy and .036 mean intersection-over-union (mIoU). Using a practical estimate of semantic similarity, we still achieve improvements in more than half of all cases, with average improvements of 2.5% accuracy and .017 mIoU in those cases.

Land use (LU) is an important information source commonly stored in geospatial databases. Most current work on automatic LU classification for updating topographic databases considers only one category level (e.g. residential or agricultural) consisting of a small number of classes. However, LU databases frequently contain very detailed information, using a hierarchical object catalogue where the number of categories differs depending on the hierarchy level. This paper presents a method for the classification of LU on the basis of aerial images that differentiates a fine-grained class structure, exploiting the hierarchical relationship between categories at different levels of the class catalogue. Starting from a convolutional neural network (CNN) for classifying the categories of all levels, we propose a strategy to simultaneously learn the semantic dependencies between different category levels explicitly. The input to the CNN consists of aerial images and derived data as well as land cover information derived from semantic segmentation. Its output is the class scores at three different semantic levels, based on which predictions that are consistent with the class hierarchy are made. We evaluate our method using two test sites and show how the classification accuracy depends on the semantic category level. While at the coarsest level, an overall accuracy in the order of 90% can be achieved, at the finest level, this accuracy is reduced to around 65%. Our experiments also show which classes are particularly hard to differentiate. © 2020 Copernicus GmbH. All rights reserved.

Depth is an essential component for various scene understanding tasks and for reconstructing the 3D geometry of the scene. Estimating depth from stereo images requires multiple views of the same scene to be captured which is often not possible when exploring new environments with a UAV. To overcome this monocular depth estimation has been a topic of interest with the recent advancements in computer vision and deep learning techniques. This research has been widely focused on indoor scenes or outdoor scenes captured at ground level. Single image depth estimation from aerial images has been limited due to additional complexities arising from increased camera distance, wider area coverage with lots of occlusions. A new aerial image dataset is prepared specifically for this purpose combining Unmanned Aerial Vehicles (UAV) images covering different regions, features and point of views. The single image depth estimation is based on image reconstruction techniques which uses stereo images for learning to estimate depth from single images. Among the various available models for ground-level single image depth estimation, two models, 1) a Convolutional Neural Network (CNN) and 2) a Generative Adversarial model (GAN) are used to learn depth from aerial images from UAVs. These models generate pixel-wise disparity images which could be converted into depth information. The generated disparity maps from these models are evaluated for its internal quality using various error metrics. The results show higher disparity ranges with smoother images generated by CNN model and sharper images with lesser disparity range generated by GAN model. The produced disparity images are converted to depth information and compared with point clouds obtained using Pix4D. It is found that the CNN model performs better than GAN and produces depth similar to that of Pix4D. This comparison helps in streamlining the efforts to produce depth from a single aerial image.

In recent years, the determination of global image orientation, i.e. global SfM, has gained a lot of attentions from researchers, mainly due to its time efficiency. Most of the global methods take relative rotations and translations as input for a two-step strategy comprised of global rotation averaging and global translation averaging. This paper by contrast presents a hybrid approach that aims to solve global rotations and translations simultaneously, but hierarchically. We first extract an optimal minimum cover connected image triplet set (OMCTS) which includes all available images with a minimum number of triplets, all of them with the three related relative orientations being compatible to each other. For non-collinear triplets in the OMCTS, we introduce some basic characterizations of the corresponding essential matrices and solve for the image pose parameters by averaging the constrained essential matrices. For the collinear triplets, on the other hand, the image pose parameters are estimated by relative orientation using the depth of object points from individual local spatial intersection. Finally, all image orientations are estimated in a common coordinate frame by traversing every solved triplet using a similarity transformation. We show results of our method on different benchmarks and demonstrate the performance and capability of the proposed approach by comparing with other global SfM methods.

Large-scale mapping of the Brazilian Savanna (Cerrado) vegetation using remote sensing images is still a challenge due to the high spatial variability and spectral similarity of the different characteristic vegetation types (physiognomies). In this paper, we report on semantic segmentation of the three major groups of physiognomies in the Cerrado biome (Grasslands, Savannas and Forests) using a fully convolutional neural network approach. The study area, which covers a Brazilian conservation unit, was divided into three regions to enable testing the approach in regions that were not used in the training phase. A WorldView-2 image was used in cross validation experiments, in which the average overall accuracy achieved with the pixel-wise classifications was 87.0%. The F-1 score values obtained with the approach for the classes Grassland, Savanna and Forest were of 0.81, 0.90 and 0.88, respectively. Visual assessment of the semantic segmentation outcomes was also performed and confirmed the quality of the results. It was observed that the confusion among classes occurs mainly in transition areas, where there are adjacent physiognomies if a scale of increasing density is considered, which agrees with previous studies on natural vegetation mapping for the Cerrado biome.

Many countries were the target of air strikes during World War II. Numerous unexploded bombs still exist in the ground. These duds can be tracked down with the help of bomb craters, indicating areas where unexploded bombs may be located. Such areas are documented in so-called impact maps based on detected bomb craters. In this paper, a stochastic approach based on marked point processes (MPPs) for the automatic detection of bomb craters in aerial images taken during World War II is presented. As most areas are covered by multiple images, the influence of redundant image information on the object detection result is investigated: we compare the results generated based on single images with those obtained by our new approach that combines the individual detection results of multiple images covering the same location. The object model for the bomb craters is represented by circles. Our MPP approach determines the most likely configuration of objects within the scene. The goal is reached by minimizing an energy function that describes the conformity with a predefined model by Reversible Jump Markov Chain Monte Carlo sampling in combination with simulated annealing. Afterwards, a probability map is generated from the automatic detections via kernel density estimation. By setting a threshold, areas around the detections are classified as contaminated or uncontaminated sites, respectively, which results in an impact map. Our results show a significant improvement with respect to its quality when redundant image information is used.

Deep learning classification models require large amounts of labeled training data to perform properly, but the production of reference data for most Earth observation applications is a labor intensive, costly process. In that sense, transfer learning is an option to mitigate the demand for labeled data. In many remote sensing applications, however, the accuracy of a deep learning-based classification model trained with a specific dataset drops significantly when it is tested on a different dataset, even after fine-tuning. In general, this behavior can be credited to the domain shift phenomenon. In remote sensing applications, domain shift can be associated with changes in the environmental conditions during the acquisition of new data, variations of objects' appearances, geographical variability and different sensor properties, among other aspects. In recent years, deep learning-based domain adaptation techniques have been used to alleviate the domain shift problem. Recent improvements in domain adaptation technology rely on techniques based on Generative Adversarial Networks (GANs), such as the Cycle-Consistent Generative Adversarial Network (CycleGAN), which adapts images across different domains by learning nonlinear mapping functions between the domains. In this work, we exploit the CycleGAN approach for domain adaptation in a particular change detection application, namely, deforestation detection in the Amazon forest. Experimental results indicate that the proposed approach is capable of alleviating the effects associated with domain shift in the context of the target application. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

The development of automated and autonomous vehicles requires highly accurate long-term maps of the environment. Urban areas contain a large number of dynamic objects which change over time. Since a permanent observation of the environment is impossible and there will always be a first time visit of an unknown or changed area, a map of an urban environment needs to model such dynamics. In this work, we use LiDAR point clouds from a large long term measurement campaign to investigate temporal changes. The data set was recorded along a 20 km route in Hannover, Germany with a Mobile Mapping System over a period of one year in bi-weekly measurements. The data set covers a variety of different urban objects and areas, weather conditions and seasons. Based on this data set, we show how scene and seasonal effects influence the measurement likelihood, and that multi-temporal maps lead to the best positioning results. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

Pixel-based land cover classification of aerial images is a standard task in remote sensing, whose goal is to identify the physical material of the earth’s surface. Recently, most of the well-performing methods rely on encoder-decoder structure based convolutional neural networks (CNN). In the encoder part, many successive convolution and pooling operations are applied to obtain features at a lower spatial resolution, and in the decoder part these features are up-sampled gradually and layer by layer, in order to make predictions in the original spatial resolution. However, the loss of spatial resolution caused by pooling affects the final classification performance negatively, which is compensated by skip-connections between corresponding features in the encoder and the decoder. The most popular ways to combine features are element-wise addition of feature maps and 1x1 convolution. In this work, we investigate skip-connections. We argue that not every skip-connections are equally important. Therefore, we conducted experiments designed to find out which skip-connections are important. Moreover, we propose a new cosine similarity loss function to utilize the relationship of the features of the pixels belonging to the same category inside one mini-batch, i.e. these features should be close in feature space. Our experiments show that the new cosine similarity loss does help the classification. We evaluated our methods using the Vaihingen and Potsdam dataset of the ISPRS 2D semantic labelling challenge and achieved an overall accuracy of 91.1% for both test sites.

At 48 years of age CORONA-KH-4B images are important for actual urban planning in Bangladesh, where no old maps or aerial images exist, indicating locations of former water courses that are no longer visible, but causing problems for the stability of building ground. CORONA KH-4B images are available for very low cost or even free of charge. A forward and a backward-looking panoramic camera with a nadir angle of approximately 15° enabled a stereoscopic coverage. Taken from a height of 154km, an image covers approximately 220km × 14km up to 17km with a height to base relation of 1:1.85. The ground sampling distance (GSD) varies with the incidence angle from 1.77m in the centre of the image up to 2.18m in Y-direction and 2.69m in the X-direction at the ends of the images. These nice conditions of the old images are affected by geometric problems of the panoramic images. A geometric bending can be improved by a correction based on the available sidelines, nevertheless deformations dominantly in the longitudinal direction only can be determined based on ground control points. A group of neighboured images have similar deformations, allowing the determination of a correction grid, describing the systematic image errors. This improved the geometry strongly, but could not eliminate all individual and local geometric problems. The high morphologic quality of the CORONA images, but limited absolute height accuracy has been improved by merging with the highly accurate TDM90 height model. For ortho images a fitting of neighboured images was required. © 2020 Copernicus GmbH. All rights reserved.

The goal of this paper is to use transfer learning for semi supervised semantic segmentation in 2D images: given a pretrained deep convolutional network (DCNN), our aim is to adapt it to a new camera-sensor system by enforcing predictions to be consistent for the same object in space. This is enabled by projecting 3D object points into multi-view 2D images. Since every 3D object point is usually mapped to a number of 2D images, each of which undergoes a pixelwise classification using the pretrained DCNN, we obtain a number of predictions (labels) for the same object point. This makes it possible to detect and correct outlier predictions. Ultimately, we retrain the DCNN on the corrected dataset in order to adapt the network to the new input data. We demonstrate the effectiveness of our approach on a mobile mapping dataset containing over 10'000 images and more than 1 billion 3D points. Moreover, we manually annotated a subset of the mobile mapping images and show that we were able to rise the mean intersection over union (mIoU) by approximately 10% with Deeplabv3+, using our approach. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

The 3rd edition of the international summer school “Close-range Sensing Techniques in Alpine terrain” took place in Obergurgl, Austria, in June 2019. This article reports on results from the training and seminar activities and the outcome of student questionnaire survey. Comparison between the recent edition and the past edition in 2017 shows no significant differences on the level of satisfaction on organizational and training aspects. Gender balance was present both in candidates and in the outcome of selections. Selection was based on past research activities and on topic relevance. The majority of trainees were therefore doctoral candidates and postdoctoral researchers, but also motivated master students participated. The training took place through keynotes, lectures, seminars, in the field with hands-on surveys followed by data analysis in the lab, and teamwork for preparing a final team presentation over different assignments.