Search

The increased use of UAVs (Unmanned Aerial Vehicles) has heightened demands for an automated landing system intended for a variety of tasks and emergency landings. A key challenge of this system is finding a safe landing site in an unknown environment using on-board sensors. This paper proposes a method to generate a heat map for safety evaluation using images from a single on-board camera. The proposed method consists of the classification of ground surface by CNNs (Convolutional Neural Networks) and the estimation of surface flatness from optical flow. We present the results of applying this method to a video obtained from an on-board camera and discuss ways of improving the method.

Topological data analysis tools enjoy increasing popularity in a wide range of applications, such as Computer graphics, Image analysis, Machine learning, and Astronomy for extracting information. However, due to computational complexity, processing large numbers of samples of higher dimensionality quickly becomes infeasible. This contribution is twofold: We present an efficient novel sub-sampling strategy inspired by Coulomb's law to decrease the number of data points in d-dimensional point clouds while preserving its homology. The method is not only capable of reducing the memory and computation time needed for the construction of different types of simplicial complexes but also preserves the size of the voids in d-dimensions, which is crucial e.g. for astronomical applications. Furthermore, we propose a technique to construct a probabilistic description of the border of significant cycles and cavities inside the point cloud. We demonstrate and empirically compare the strategy in several synthetic scenarios and an astronomical particle simulation of a dwarf galaxy for the detection of superbubbles (supernova signatures). (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).

International audience; Among approaches for automated generalization of vector data, we focus on the multi-agent paradigm: cartographic objects are modeled as agents (autonomous objects) that apply generalization algorithms to themselves to satisfy cartographic constraints. Several agent levels are considered, for example, individual agents, such as a building, and agents representing a group of agents, such as an urban block composed of the surrounding roads and contained buildings. Several multi-agent models were proposed to automate the orchestration of map generalization processes. Existing multi-agent generalization models have different approaches to manage the relations between agent levels. In this paper, we unify existing models, adapting a multi-level simulation model, to simplify interactions between agents in different levels. We propose the DIOGEN model, in which the principle of interactions between agents of different levels is adapted to constraint-driven cartographic generalization. DIOGEN unifies three existing multi-agent generalization models (AGENT, CartACom and GAEL), combine their behaviors and take advantage of their skills. Our proposal is evaluated on different use cases: instances of topographic mapping, and mapping of hiking routes over topographic data as an example of thematic mapping.; Nous nous intéressons aux approches dédiées à la généralisation automatique basées sur le paradigme multi-agents: les objets cartographiques sont modélisés comme des agents (objets autonomes) qui s'appliquent des algorithmes de généralisation pour satisfaire des contraintes cartographiques. Plusieurs niveaux d'agents sont considérés, par exemple des agents individuels, comme un bâtiment, et des agents représentant un groupe d'agents, comme un îlot urbain composé des routes qui l'entourent et des bâtiments qu'il contient. Plusieurs modèles multi-agents ont été proposés pour automatiser l'orchestration d'un processus de généralisation. Les modèles existants gèrent différemment les relations entre les niveaux d'agents. Dans cet article, nous travaillons sur l'unification des modèles existants. Nous simplifions les interactions entre agents des différents niveaux en adaptant un modèle agent récemment défini pour la simulation, et qui met l'accent sur la modélisation du multi-niveau. La modélisation des interactions entre niveaux issue de ce modèle est adaptée au cas de la généralisation cartographique guidée par des contraintes. Le modèle résultant s'appelle DIOGEN. Il unifie trois modèles de génralisation existants (AGENT, CartACom et GAEL), permettant de combiner leurs comportements et leurs capacités. Notre proposition est évaluée sur des cas concrets de cartographie topographique, ainsi que sur de la cartographie conjointe d'itinéraires de randonnée et de données topographiques qui constitue un exemple de cartographie thématique.

Summary iBioProVis is an interactive tool for visual analysis of the compound bioactivity space in the context of target proteins, drugs and drug candidate compounds. iBioProVis tool takes target protein identifiers and, optionally, compound SMILES as input, and uses the state-of-the-art non-linear dimensionality reduction method t-Distributed Stochastic Neighbor Embedding (t-SNE) to plot the distribution of compounds embedded in a 2D map, based on the similarity of structural properties of compounds and in the context of compounds’ cognate targets. Similar compounds, which are embedded to proximate points on the 2D map, may bind the same or similar target proteins. Thus, iBioProVis can be used to easily observe the structural distribution of one or two target proteins’ known ligands on the 2D compound space, and to infer new binders to the same protein, or to infer new potential target(s) for a compound of interest, based on this distribution. Principal component analysis (PCA) projection of the input compounds is also provided, Hence the user can interactively observe the same compound or a group of selected compounds which is projected by both PCA and embedded by t-SNE. iBioProVis also provides detailed information about drugs and drug candidate compounds through cross-references to widely used and well-known databases, in the form of linked table views. Two use-case studies were demonstrated, one being on angiotensin-converting enzyme 2 (ACE2) protein which is Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Spike protein receptor. ACE2 binding compounds and seven antiviral drugs were closely embedded in which two of them have been under clinical trial for Coronavirus disease 19 (COVID-19). Availability and implementation iBioProVis and its carefully filtered dataset are available at https://ibpv.kansil.org/ for public use. Contact vatalay@metu.edu.tr Supplementary information Supplementary data are available at Bioinformatics online.

This paper proposes an efficient approach to the multiple source localization and contour mapping problem of radiation fields using Unmanned Aerial Vehicles (UAVs). A typical radiation field originating from a single hotspot can be generated by three spatial distributions of sources; scattered, clustered and biased. Of these, the clustered sources are relatively easy to localize, because the sources are located in a close proximity to the center of distribution. In other cases, it is not very straightforward, because, when multiple radiating sources generate a hotspot in a cumulative manner, sources do not coincide with the hotspot position. Regardless of our knowledge about the hotspot position, we attempt to solve the multiple radiation localization problem in two steps: the Region Of Interest (ROI) selection and the source localization. Existing algorithms eventually explore whole area, causing the problem of excessive use of UAV resources. We therefore propose a framework to reduce ROI in a radiation field that not only optimizes the resources but also increases the localization accuracy. For the source localization process, two different methods are employed interchangeably. Those methods are called the Hough Transform and the Variational Bayesian, adaptively selected with a switching technique and the overall performance is evaluated by balancing between the localization accuracy and the required exploration. In favor of the optimization, the prediction model defines the type of sources in a way that the adaptive switching methodology can converge to an optimal solution by selecting an appropriate method. Thus, the proposed framework enables the UAV to accurately localize the radiation sources in a fast manner. In order to verify the validity and the performance of the proposed strategies, we performed extensive numerical experiments with different numbers of sources and their positions. Our empirical results clearly show that the proposed approach outperforms existing individual approaches. A framework is proposed that enables a single UAV to accurately localize the radiation sources in a fast manner.In an unknown radiation field, we attempt to solve the multiple radiation localization problem in two steps.By reducing the ROI in a radiation field, we not only optimize the resources but also are able to increase the localization accuracy.By employing two different methods interchangeably, we are able to balance between the localization accuracy and exploration constraints.

Complex landscapes with high topographic relief and intricate geometry present challenges for complete and accurate mapping of both lateral (x, y) and vertical (z) detail without deformation. Although small uninhabited/unmanned aerial vehicles (UAVs) paired with structure-from-motion (SfM) image processing has recently emerged as a popular solution for a range of mapping applications, common image acquisition and processing strategies can result in surface deformation along steep slopes within complex terrain. Incorporation of oblique (off-nadir) images into the UAV⁻SfM workflow has been shown to reduce systematic errors within resulting models, but there has been no consensus or documentation substantiating use of particular imaging angles. To address these limitations, we examined UAV⁻SfM models produced from image sets collected with various imaging angles (0⁻35°) within a high-relief ‘badland’ landscape and compared resulting surfaces with a reference dataset from a terrestrial laser scanner (TLS). More than 150 UAV⁻SfM scenarios were quantitatively evaluated to assess the effects of camera tilt angle, overlap, and imaging configuration on the precision and accuracy of the reconstructed terrain. Results indicate that imaging angle has a profound impact on accuracy and precision for data acquisition with a single camera angle in topographically complex scenes. Results also confirm previous findings that supplementing nadir image blocks with oblique images in the UAV⁻SfM workflow consistently improves spatial accuracy and precision and reduces data gaps and systematic errors in the final point cloud. Subtle differences among various oblique camera angles and imaging patterns suggest that higher overlap and higher oblique camera angles (20⁻35°) increased precision and accuracy by nearly 50% relative to nadir-only image blocks. We conclude by presenting four recommendations for incorporating oblique images and adapting flight parameters to enhance 3D mapping applications with UAV⁻SfM in high-relief terrain.

The use of classification results as topographic map data requires cartographic enhancement and checking of the geometric accuracy. Urban areas are of special interest. The conversion of the classification result into topographic map data of high thematic and geometric quality is subject of this contribution. After reviewing the existing literature on this topic, a methodology is presented. The extraction of point clouds belonging to line segments is solved by the Hough transform. The mathematics for deriving polygons of orthogonal, parallel and general line segments by least squares adjustment is presented. A unique solution for polylines, where the Hough parameters are optimized, is also given. By means of two data sets land cover maps of six classes were produced and then enhanced by the proposed method. The classification used the decision tree method applying a variety of attributes including object heights derived from imagery. The cartographic enhancement is carried out with two different levels of quality. The user’s accuracies for the classes “impervious surface” and “building” were above 85% in the “Level 1” map of Example 1. The geometric accuracy of building corners at the “Level 2” maps is assessed by means of reference data derived from ortho-images. The obtained root mean square errors (RMSE) of the generated coordinates (x, y) were RMSEx = 1.2 m and RMSEy = 0.7 m (Example 1) and RMSEx = 0.8 m and RMSEy = 1.0 m (Example 2) using 31 and 62 check points, respectively. All processing for Level 1 (raster data) could be carried out with a high degree of automation. Level 2 maps (vector data) were compiled for the classes “building” and “road and parking lot”. For urban areas with numerous classes and of large size, universal algorithms are necessary to produce vector data fully automatically. The recent progress in sensors and machine learning methods will support the generation of topographic map data of high thematic and geometric accuracy.

One of the key roles in map creation belongs to terrain representation. Relief shading is a traditional manual technique allowing users to perceive the terrain in an intuitive and naturalistic way. With the advent of digital elevation models (DEM), analytical relief shading came into a wider use, since it is faster, requires less effort and delivers reproducible results. In contrast to manual relief shading, it often lacks clarity when representing heterogeneous landscapes with diverse landforms though. The goal of this ongoing project is to identify which relief shading techniques are suitable for depicting specific landforms. Techniques developed over time to surmount this limitation mainly include (but not limited to) terrain generalisation, light direction adjustments, contrast enhancement and terrain segmentation. Each of numerous methods is usually applied and performs better in a particular landscape and does not consider possible landscape diversity within an area hillshading is generated for. Thus, it is necessary to detect the right combination of tools and parameters providing the best results regarding the visual quality in each landscape type and to find a correlation between those methods and landforms they are applied to. In the frame of this project, existing methods to automatically perform relief shading are initially tested on sample areas. Having miscellaneous landforms within sample areas and rendering them in the best possible way leads us to understanding which features analytical hillshading has to inherit from the manual one. It is planned to generate shaded reliefs using different techniques and to show them to cartographers and laymen worldwide via an online survey to define which combination of tools and methods consistently provides better results in terms of visual quality in each landscape type. A large number of participants should minimise the subjectivity peculiar to relief shading depiction. As the project involves both laymen and specialists, the survey is complemented with an extra section of questions for specialists with a higher weight in the final feedback evaluation based on their deeper knowledge of the subject. Analysis of participants’ feedback is meant for creation of a series of rules to be applied to specific landform or landscape type. For landscape features the range of qualitative and quantitative parameters is used (e.g. DEM derivatives). Besides, the resulting shaded reliefs are also compared with the Swiss Federal Office of Topography manual shaded reliefs at different scales. As a result, a direct correlation between the values of landscape features and visual quality of relief shading is provided. Finally, it can be seen that a particular combination of tools and methods is ideal for a landscape type based on the level of its geomorphological complexity. This should give users a possibility to improve the automatically produced relief shading as a whole, to adjust its parts if different landforms are present, or to bring more focus to those landscape features that were not revealed by automatic hillshading.

In this paper, a simulation tool for modeling axon guidance is presented. A mathematical framework in which a wide range of models can been implemented has been developed together with efficient numerical algorithms. In our framework, models can be defined that consist of concentration fields of guidance molecules in combination with finite-dimensional state vectors. These vectors can characterize migrating growth cones, target neurons that release guidance molecules, or other cells that act as sources of membrane-bound or diffusible guidance molecules. The underlying mathematical framework is presented as well as the numerical methods to solve them. The potential applications of our simulation tool are illustrated with a number of examples, including a model of topographic mapping. © 2006 Society for Mathematical Biology.

Nowadays, the number and capacity of very high resolution optical satellites grows permanently, so the access to very high resolution space images is not any more a problem. The use of Geographic Information Systems (GISs) together with Remote Sensing became important. With the increased ground resolution a competition to aerial images exist. For the generation of topographic maps, today available as GIS, the accuracy and the information content - what elements can be identified in the image - are important. Both may limit the presentation scale of topographic maps. As horizontal accuracy 0.25mm up to 0.3mm in the map scale are accepted. The required information content is more complicate. The object details to be presented in topographic maps vary from area to area which is based on the planned and unplanned areas. In this study, images from IRS-1C, Kompsat-1, SPOT 5, OrbView-3, IKONOS, QuickBird and WorldView-1 have been used for topographic mapping. For this reason, Zonguldak test fields are an important area for applications of the high resolution imageries. The details which can be identified in the space images dominantly depends upon the ground resolution, available as ground sampling distance (GSD). In this study, high resolution imageries have been tested depending on the GSD and corresponding to the map scales for updating GIS database. © 2015 SPIE.

Highlights? We evaluate neural network methods for learning one-to-many mapping. ? We map particular facial attributes to the overall facial appearance. ? Visual and quantitative results are demonstrated. ? We apply neural network approach to the face image synthesis problem. This paper investigates the performance of neural network-based techniques applied to the problem of defining the relationship between a particular type of variation in face images and the multivariate data distributions of these images. In this respect the problem of defining a mapping associating a quantified facial attribute and the overall typical facial appearance is addressed. In particular the applicability of formulating a mapping function using neural network-based methods like Multilayer Perceptrons (MLPs), Radial Basis Functions (RBFs), Mixture Density Networks (MDNs) and a latent variable method, the General Topographic Mapping (GTM) is investigated. Quantitative and visual results obtained during the experimental investigation, suggest that for one-to-many problems, where the entire variance of the distribution is not required, the RBFs are the best options when compared to MLPs, MDNs and GTM. The proposed techniques can be applied to applications involving face image synthesis and other applications that require one-to-many mapping transformations.

The Italian Space Agency (ASI Agenzia Spaziale Italiana) funded 27 scientific projects in the framework of COSMO-SkyMed (CSK) program. A subset of them focused on the improvements of the quality and quantity of information which can be extracted from X-SAR data if integrated with other independent techniques (GPS, data and imagery in other bands and wavelengths). The paper summarizes the results obtained from same of these projects and, in particular, regarding: - the use of GPS observations and Numerical Weather Models (NWM) to remove atmospheric artifacts from InSAR imagery so improving the CSK potentialities in the field of topographic mapping; - the integration of SAR data in X, L and C bands to improve snow cover monitoring and glaciers detection; - the use of X-SAR data to retrieve rain precipitation and its validation with C-band radar observations; - the improvements of the focusing techniques.

An investigation of the applicability of neural network-based methods in predicting the values of multiple parameters, given the value of a single parameter within a particular problem domain is presented. In this context, the input parameter may be an important source of variation that is related with a complex mapping function to the remaining sources of variation within a multivariate distribution. The definition of the relationship between the variables of a multivariate distribution and a single source of variation allows the estimation of the values of multiple variables given the value of the single variable, addressing in that way an ill-conditioned one-to-many mapping problem. As part of our investigation, two problem domains are considered: predicting the values of individual stock shares, given the value of the general index, and predicting the grades received by high school pupils, given the grade for a single course or the average grade. With our work, the performance of standard neural network-based methods and in particular multilayer perceptrons (MLPs), radial basis functions (RBFs), mixture density networks (MDNs) and a latent variable method, the general topographic mapping (GTM), is compared. According to the results, MLPs and RBFs outperform MDNs and the GTM for these one-to-many mapping problems. © 2010 Springer-Verlag London Limited. 20 6 775 785 Cited By :5

In developing brain, axons and dendrites are capable of connecting to each other with high precision. Recent advances in imaging have allowed for the monitoring of axonal, dendritic, and synapse dynamics in vivo. It is observed that the majority of axonal and dendritic branches are formed 'in error', only to be retracted later. The functional significance of the overproduction of branches is not clear. In this study, we use a computational model to investigate the speed and efficiency of different branching strategies. We show that branching itself allows for substantial acceleration in the identification of appropriate targets through the use of a parallel search. We also show that the formation of new branches in the vicinity of existing synapses leads to the formation of target connectivity with a decreased number of erroneous branches. This finding allows us to explain the high correlation between the branch points and synapses observed in the Xenopus laevis retinotectal system. We also suggest that the most efficient branching rule is different for axons and dendrites. The optimal axonal strategy is to form new branches in the vicinity of existing synapses, whereas the optimal rule for dendrites is to form new branches preferentially in the vicinity of synapses with correlated pre- and postsynaptic electric activity. Thus, our studies suggest that the developing neural system employs a set of sophisticated computational strategies that facilitate the formation of required circuitry, so that it may proceed in the fastest and most frugal way., 13 pages

We propose and evaluate an operational algorithm, capable of obtaining a mosaic DEM from a wide area from several interferometric data sets.