Terrain Image Research Articles

Development of a two-stage method for segmenting the color images of urban terrain acquired from space optic-electronic observation systems based on the ant algorithm and the hough algorithm

The object of this study is the high level of errors of the first and second kind in the segmentation of images of urbanized areas acquired from space optoelectronic surveillance systems. The method of image segmentation of urbanized areas implies two stages and, unlike known ones: – takes into account each channel of brightness of the color space of the original image; – at the first stage, an ant algorithm is used; – image segmentation at the first stage is reduced to the calculation of the objective function, the areas of movement of ants, and the concentration of pheromone on the routes of ant movement. – at the second stage, the brightness and geometric shape of the elements of objects are taken into account; – contours and geometric primitives are defined in the Hough parameter space; – the objects of interest of the urbanized area in the space of the original image are determined. An experimental study into the segmentation of images of urbanized terrain acquired from space optoelectronic observation systems was carried out based on the ant algorithm and the Hough algorithm. The quality of image segmentation of the urbanized area was assessed. It was found that the error of the first kind when using the improved method of segmentation is reduced by 2.75 %. The error of the second kind is reduced by 3.91 % when using the improved method of segmentation. This reduction became possible due to the use of an improved method of segmenting the image of an urbanized area by the ant algorithm at the first stage. Compared to Canny's algorithm, the error of the first kind decreased by 8.9 %, and the error of the second kind decreased by 11.0 %. Methods for segmenting images of urbanized areas acquired from space optoelectronic surveillance systems can be implemented in software and hardware systems of image processing

Exploiting Deep Matching and Underwater Terrain Images to Improve Underwater Localization Accuracy

Underwater terrain image (UTI) matching provides a new idea for terrain-aided localization technology. However, the diversity of UTIs makes it very difficult to accurately match real-time terrain images (RTTIs) with reference terrain images (RTIs). To improve the localization accuracy of UTIs, this letter describes how UTI matching can be modeled as a deep learning problem based on supervised algorithms. Specifically, we propose a hierarchical matching strategy for the diverse features of UTIs by combining the deep and shallow feature characteristics of a convolutional neural network (CNN) to improve the localization accuracy. We also propose a sample-generation strategy based on candidate area quality index classification, and develop a data enhancement method by simulating the underwater terrain environment to overcome the lack of network training data. Simulations prove that the proposed method achieves accurate and stable localization results.

A Shadow Simulation Scheme for SAR Images of Undulating Terrain Based on Facet Cell Fitting and Elevation Angle Comparison

Shadow simulation is a key part of SAR raw data and image simulation for undulated terrain, which will directly determine the accuracy of SAR simulation and will also affect the accuracy of subsequent shadow-based SAR image processing applications. In this paper, a shadow simulation scheme for undulated terrain SAR images based on facet cell fitting and elevation angle comparison is proposed. In the scheme, the height information of each grid point on the same line of sight within the beam irradiation range is obtained firstly with the facet cell fitting, and the elevation angle of each grid point can be computed and compared to determine whether the occlusion happens. Then, all grid points in the illumination range are traversed to obtain the shadow judgment result at a certain azimuth moment, and the SAR shadows are obtained by superimposing the judgment results at all azimuth moments. At last, simulated and measured data experiments are given to verify the effectiveness of the proposed scheme, and the results show that this scheme can accurately simulate the SAR shadow of undulating terrain.

МЕТОДИ АНАЛІЗУ ЗОБРАЖЕНЬ МІСЦЕВОСТІ В НАВІГАЦІЙНИХ СИСТЕМАХ БПЛА

The paper analyzes modern methods of terrain image analysis in UAV navigation systems and presents experimental results of UAV navigation method research based on the use of spatial-spectral portraits of objects in terrain areas. In the conditions of radio-electronic suppression of the UAV navigation system by EW means, there is an urgent need for the development and application of new jam-proof UAV navigation methods. The purpose of the work is to substantiate the method of terrain image analysis in UAV technical vision systems. To achieve this goal, the following tasks were announced in the work: an analysis of the possible use of existing methods and systems of technical vision on UAVs was carried out; the substantiation of the method of image analysis using spatial-spectral terrain portraits in UAV technical vision systems was carried out. The method of calculating the traveled path based on the analysis of the flow of video data coming from the optoelectronic surveillance devices, the method of accurate mapping on the terrain based on the stereo effect that occurs during camera movement, and the method of accurate mapping based on reference photographs are analyzed. In order to improve the efficiency of the UAV technical vision system, it is proposed to use spatial-spectral portraits of objects in areas of the terrain. At the same time, the video frames are compared with embedded spectral portraits of the route sections, in the case of "recognition", the exact coordinates and orientation of the UAV are determined. The application of this method is connected with the need to take into account the impact of lighting changes on the spectral indicators of objects and areas of the terrain. The research examines existing techniques for correcting lighting changes for various cameras in laboratory and field conditions. It is proposed to use experimentally obtained dependencies for specific brands of sensor equipment to carry out corrections for changes in natural lighting. When organizing navigation systems based on spectral portraits of the terrain, it is recommended to use objects and areas with the most stable optical characteristics in relation to changes in lighting.

Ring-Masked Attention Network for Rotation-Invariant Template-Matching

To solve the rotational changes in matching localization of an underwater terrain image, this letter proposes the ring-masked attention network (RMANet), a model-driven deep network for rotational template-matching tasks. Since traditional convolutional neural networks cannot effectively encode rotational changes, we introduce a rotation-equivariant network to extract the rotation-equivariant features. This network determines the rotation of an image at the pixel level. Based on the rotation-equivariant features, we propose the ring-masked attention module (RMAM), which combines the idea of the ring projection transform with an attention mechanism to extract the rotation-invariant features that are independent of the orientation. The overall model combines the rotation-equivariant network with RMAM into an end-to-end network that can exploit both the feature-representation capability of the learning-based model and domain knowledge. Our experimental results show that, compared with popular approaches targeting rotational matching tasks, RMANet achieves performance gains in terms of both matching accuracy and running speed.

The Effects of Motivation, Destination Image and Satisfaction on Rural Tourism Tourists’ Willingness to Revisit

With the diversification of tourist demand for a destinations’ supply, rural tourism destinations are facing an increasingly fierce competition environment. Creating brand value and improving tourists’ willingness to revisit has become an inevitable strategic choice for rural tourism destinations. In this study, we proposed a framework of “tourism motivation-destination image-satisfaction-willingness to revisit” to investigate rural tourism. We investigated from the aspects of learning and entertainment motivation, novelty-seeking motivation, natural environment, cultural environment, social environment, infrastructure, and tourist satisfaction. To analyze data, a questionnaire survey was administered to 545 tourists using structural equation modeling (SEM) technology. The findings indicated that learning and entertainment motivation, natural environment, social environment, and tourist satisfaction had a direct and positive effect on tourists’ willingness to revisit. In addition, tourist satisfaction played an intermediary role between tourists’ tourism motivation and destination terrain image and their propensity to return. On this basis, some suggestions and illuminations are put forward to increase tourists’ willingness to revisit.

3D Reconstruction of Remote Sensing Mountain Areas with TSDF-Based Neural Networks

The remote sensing 3D reconstruction of mountain areas has a wide range of applications in surveying, visualization, and game modeling. Different from indoor objects, outdoor mountain reconstruction faces additional challenges, including illumination changes, diversity of textures, and highly irregular surface geometry. Traditional neural network-based methods that lack discriminative features struggle to handle the above challenges, and thus tend to generate incomplete and inaccurate reconstructions. Truncated signed distance function (TSDF) is a commonly used parameterized representation of 3D structures, which is naturally convenient for neural network computation and computer storage. In this paper, we propose a novel deep learning method with TSDF-based representations for robust 3D reconstruction from images containing mountain terrains. The proposed method takes in a set of images captured around an outdoor mountain and produces high-quality TSDF representations of the mountain areas. To address the aforementioned challenges, such as lighting variations and texture diversity, we propose a view fusion strategy based on reweighted mechanisms (VRM) to better integrate multi-view 2D features of the same voxel. A feature enhancement (FE) module is designed for providing better discriminative geometry prior in the feature decoding process. We also propose a spatial–temporal aggregation (STA) module to reduce the ambiguity between temporal features and improve the accuracy of the reconstruction surfaces. A synthetic dataset for reconstructing images containing mountain terrains is built. Our method outperforms the previous state-of-the-art TSDF-based and depth-based reconstruction methods in terms of both 2D and 3D metrics. Furthermore, we collect real-world multi-view terrain images from Google Map. Qualitative results demonstrate the good generalization ability of the proposed method.

ML models and neural networks for analyzing 3D data spatial planning tasks: Example of Khasansky urban district of the Russian Federation

The article addresses the issue of the Earth's surface surveillance. It was determined that artificial intelligence tools and machine learning methods are required to enhance the effectiveness of image recognition. Cores, Era 5, and ArcGIS cloud computing services (APIs) were installed to evaluate spatial data quality. The article presents the results of analyzing climate data received through applications developed by the authors. Raster terrain images of Slavyanka city located in Khasansky District of the Russian Federation were obtained, and corresponding graphs of temperature regimes were built. The root-mean-square deviation (RMSD) value calculated using machine learning techniques served as the basis for developing a neural network. It was later used to define the land features of the Khasansky city district to evaluate the possibility of construction works in this area. The map received allowed setting the designation purpose of the land plots and their rating in terms of suitability for construction works and defining areas not serviceable for any civil engineering activities. Complex climatic factors and obtained raster images of the terrain were considered. Testing the neural network for terrain recognition showed the model's training error of up to 1.3%. In terms of statistics, RSSD (2.5 ± 0.95), the Pearson's criterion, the Student's criterion, and the statistical significance of the results were estimated. The obtained results can be used for terrain recognition and expert evaluation of land plots.

Fusion Information Multi-View Classification Method for Remote Sensing Cloud Detection

In recent years, many studies have been carried out to detect clouds on remote sensing images. Due to the complex terrain, the variety of clouds, the density, and content of clouds are various, and the current model has difficulty accurately detecting the cloud in the image. In our strategy, a multi-view data training set based on super pixel is constructed. View A uses multi-level network to extract the boundary, texture, and deep abstract feature of super pixels. View B is the statistical feature of the three channels of the image. Privilege information View P contains the cloud content of super pixels and the tag status of adjacent super pixels. Finally, we propose a cloud detection method for remote sensing image classification based on multi-view support vector machine (SVM). The proposed method is tested on images of different terrain and cloud distribution in GF-1_WHU and Cloud-38 remote sensing datasets. Visual performance and quantitative analysis show that the method has excellent cloud detection performance.

Unknown terrain imaging with adaptive spatial resolution using UAV

Recently, Unmanned Aerial Vehicles (UAVs), or drones equipped with advanced cameras, have introduced a major revolution in surveying wide landscapes to collect ground data very fast. Capturing images of an unknown area with the desired resolution is of utmost importance for many real-life applications. For a UAV fitted with a given camera, its altitude from the ground surface primarily determines the spatial resolution of mapping. Hence, for an uneven terrain, it is a great challenge to maneuver the UAV dynamically to capture snapshots maintaining the desired spatial resolution throughout the area. This paper proposes a novel fully-automated technique for simple nadir drones to capture images of an unknown 3D terrain satisfying a predefined spatial resolution criterion. Also, an adaptive real-time flight path planning scheme is presented to minimize the distance traversed by the drone. A detailed performance evaluation study on real terrain data shows that the proposed technique can cover almost 97−99% of the area, maintaining the specified resolution with an almost 46−59% reduction in the path length compared to the conventional techniques.

Robotic Mapping Approach under Illumination-Variant Environments at Planetary Construction Sites

In planetary construction, the semiautonomous teleoperation of robots is expected to perform complex tasks for site preparation and infrastructure emplacement. A highly detailed 3D map is essential for construction planning and management. However, the planetary surface imposes mapping restrictions due to rugged and homogeneous terrains. Additionally, changes in illumination conditions cause the mapping result (or 3D point-cloud map) to have inconsistent color properties that hamper the understanding of the topographic properties of a worksite. Therefore, this paper proposes a robotic construction mapping approach robust to illumination-variant environments. The proposed approach leverages a deep learning-based low-light image enhancement (LLIE) method to improve the mapping capabilities of the visual simultaneous localization and mapping (SLAM)-based robotic mapping method. In the experiment, the robotic mapping system in the emulated planetary worksite collected terrain images during the daytime from noon to late afternoon. Two sets of point-cloud maps, which were created from original and enhanced terrain images, were examined for comparison purposes. The experiment results showed that the LLIE method in the robotic mapping method significantly enhanced the brightness, preserving the inherent colors of the original terrain images. The visibility and the overall accuracy of the point-cloud map were consequently increased.

Epidemic and sanitary charts and tables of the second half of the XIX century as the “health passports” for Russian territories

The title of this article reproduces the intentions of the creators of the health cards and the hopes of their modern viewers. Judging by the statements, they wanted to see and show the state of the sanitary and epidemiological situation in the Russian Empire and wanted to do it as reliably and clearly as possible. The article’s authors asked themselves a question: have these desires and hopes come true, that is - are now the tables of sanitary statistics and disease maps “health passports” of various administrative and territorial units of the Russian Empire? Can historians use them as reliable evidence? In order to answer this question, it was necessary to reconstruct then existing system for recording and collecting data on infectious patients, diseases and pathogenicity, ways of their aggregation and representation. Only then would it be possible to find out how these data were applied to conditional terrain images, why either manufactured terrain plans or an administrative map of the empire were used, what was visible and what was in the dark zone. The article’s authors found that the resources available in post-reform Russia did not make it possible to make the collection of sanitary statistics total for the entire territory timely, and even more so to organise a retest of practical information. The supply of information depended on the density of the network of medical institutions in the empire and doctors’ ideas about the value of such information. This circumstance ensured fragmented, multi-temporal and spatial asymmetry in showing the sanitary condition of the Russian Empire and the morbidity of its inhabitants. On this basis, medical historians are advised to read these mediums in the reverse perspective: high morbidity rates should be read as evidence of well-organised medical care (i.e. relative epidemic well-being) and vice versa.

Neural Path Planning With Multi-Scale Feature Fusion Networks

Path planning is critical for planetary rovers that perform observation and exploration missions in unknown and dangerous environment. And due to the communication delay, it is difficult for the planet rover to receive instructions from Earth in time to guide its own movement. In this work, we present a novel neural network-based algorithm to solve the global path planning problem for planetary rovers. Inspired by feature pyramid networks used for object detection, we construct a deep neural network model, termed the Pyramid Path Planning Network (P3N), which has a well-designed backbone that efficiently learns a global feature representation of the environment, and a feature pyramid branch that adaptively fuses multi-scale features from different levels to generate the local feature representation with rich semantic information. The P3N learns environmental dynamics from terrain images of planetary surface taken by satellites, without using additional elevation information to construct an explicit environmental model in advance, and can perform path planning policy after end-to-end training. We evaluate the effectiveness of the proposed method on synthetic grid maps and a realistic data set constructed from the lunar terrain images. Experimental results demonstrate that our P3N has higher prediction accuracy and faster computation speed compared to the baseline methods, and generalize better in large-scale environments.

A Novel Shadow and Layover Segmentation Network for Multi-Angle SAR Images Fusion

Shadow and layover are geometric distortion phenomenons in side-view imaging synthetic aperture radar (SAR) systems, especially in mountainous areas and densely populated urban areas. The shadow can block the target of the observation area, making it impossible to obtain the scattering characteristics of the target. The layover causes phase distortion and alters target characteristics. Shadow and layover severely hinder the interpretation of SAR images. To confront the above problems, a multi-angle fusion algorithm based on unsupervised progressive segmentation network is proposed. Firstly, inspired by mega-constellations of low earth orbit, a spaceborne SAR collaborative observation model is proposed to generate multi-angle images of fluctuant terrain. Secondly, according to the difference of echos in the shadow and layover regions, an unsupervised progressive segmentation network is designed to sequentially segment the shadow and layover regions. Finally, to improve the contrast and brightness of the fused SAR image, a single-scale weighted fusion algorithm is designed. Experiments were conducted using the simulated multi-angle SAR images. Compared with single-angle images, the accuracy of target detection and figure-of-merit of the fused SAR image are significantly higher than those of other methods.

Contrastive Learning Ideas in Underwater Terrain Image Matching

The distinctive nature of the intrinsic features of underwater terrain images, along with their variability of intensity and texture due to the complex environment in which they are acquired, poses great challenges to manual feature-based template-matching methods. In this paper, we propose a novel data-driven framework for template matching of underwater terrain images. This combines the idea of contrastive learning with the template-matching process, allowing self-supervised end-to-end training without the need for additional data annotation. The resulting positive and negative sample comparisons improve the discriminatory ability of the model. Specifically, we achieve data enhancement by simulating grayscale and texture differences between images to improve the anti-interference capability of the model, and we propose a patch-based sample-extraction strategy to extract positive and negative samples. To further improve the discriminative ability for features among patches, we propose a feature-fusion module based on an attention mechanism. This improves the level of discrimination of the features to be matched by fusing the contextual features of patches. In addition, we solve the problem of matching multi-scale templates by introducing a masking mechanism. We performed detailed ablation experiments on the components in the framework to verify their effectiveness. We also compared the performance of our model with other state-of-the-art template-matching methods. The experimental results demonstrate that our proposed method has superior matching performance when compared to its competitors.

Underwater Terrain Image Stitching Based on Spatial Gradient Feature Block

At present, underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system. However, the processed underwater terrain images have inconspicuous and few feature points. In order to better realize the stitching of underwater terrain images and solve the problems of slow traditional image stitching speed, we proposed an improved algorithm for underwater terrain image stitching based on spatial gradient feature block. First, the spatial gradient fuzzy C-Means algorithm is used to divide the underwater terrain image into feature blocks with the fusion of spatial gradient information. The accelerated-KAZE (A-KAZE) algorithm is used to combine the feature block information to match the reference image and the target image. Then, the random sample consensus (RANSAC) is applied to optimize the matching results. Finally, image fusion is performed with the global homography and the optimal seam-line method to improve the accuracy of image overlay fusion. The experimental results show that the proposed method in this paper effectively divides images into feature blocks by combining spatial information and gradient information, which not only solves the problem of stitching failure of underwater terrain images due to unobvious features, and further reduces the sensitivity to noise, but also effectively reduces the iterative calculation in the feature point matching process of the traditional method, and improves the stitching speed. Ghosting and shape warping are significantly eliminated by re-optimizing the overlap of the image.

Value Iteration Networks with Double Estimator for Planetary Rover Path Planning.

Path planning technology is significant for planetary rovers that perform exploration missions in unfamiliar environments. In this work, we propose a novel global path planning algorithm, based on the value iteration network (VIN), which is embedded within a differentiable planning module, built on the value iteration (VI) algorithm, and has emerged as an effective method to learn to plan. Despite the capability of learning environment dynamics and performing long-range reasoning, the VIN suffers from several limitations, including sensitivity to initialization and poor performance in large-scale domains. We introduce the double value iteration network (dVIN), which decouples action selection and value estimation in the VI module, using the weighted double estimator method to approximate the maximum expected value, instead of maximizing over the estimated action value. We have devised a simple, yet effective, two-stage training strategy for VI-based models to address the problem of high computational cost and poor performance in large-size domains. We evaluate the dVIN on planning problems in grid-world domains and realistic datasets, generated from terrain images of a moon landscape. We show that our dVIN empirically outperforms the baseline methods and generalize better to large-scale environments.

NUMERICAL MODELLING OF THE MORPHODYNAMICS OF THE PLOČE GRAVEL BEACH IN RIJEKA

The morphodynamics of an artificial gravel beach in the Bay of Rijeka (Ploče Beach) was analyzed. The morphological changes of the beach face were monitored through an intense situation of gravitational surface wind waves from the incident SSW direction. A numerical modeling technique was applied, after initially establishing a numerical model for wave deformation. A model for sediment transport was established based on its results. Both models were based on the finite volume method. In addition, the partial contribution of the longshore component of sediment transport was analyzed based on empirical formulae. The modeling results were verified by comparing the positions and amounts of eroded/accumulated material along the beach with the processing of terrain images in the form of point clouds. The erosion and accumulation positions of the beach sediment material, obtained by numerical model simulations, corresponded to the surveyed positions. The total volume of eroded and accumulated material based on terrain image processing corresponded to the model values.

METHOD OF ALLOCATION OF MOUNTING POINTS ON AEROPHOTOGRAPHS OBTAINED BY UNLIMITED AIRCRAFT FOR USE DURING THE CAR

A retrospective analysis of the use of unmanned aerial vehicles in the combat zone indicates a steady increase in the use of electronic warfare by the enemy, which reduces the effectiveness of reconnaissance flights of unmanned aerial vehicles, and in some cases leads to their loss. The article considers the prospects of creating and improving high-precision navigation systems, which is currently one of the priority areas for the development of unmanned aerial vehicles and relevant for ensuring high efficiency of unmanned aerial vehicles for both civil and military purposes. To develop and study methods and algorithms for localizing the position of unmanned aerial vehicles based on terrain images obtained by non-identical surveying means, taking into account the influence of electronic warfare on it, the article primarily considers approaches to comparing earth surface images as the main information component. The next step is to assess the correctness of the choice of informative parameters of the anchor points, where the mathematical model for their description and selection is the basis for the development of methods and algorithms for the formation of an autonomous navigation system for unmanned aerial vehicles. Taking into account the research conducted in the work, it was proposed to implement on board the drone intelligent information and calculation system of autonomous navigation, the algorithm of which is based on the logical basis of the SIFT descriptor. Thanks to the software implementation of the approaches proposed in the work and obtained on the basis of their experimental results, it is possible to develop and further improve methods of positioning unmanned aerial vehicles in space.

Visual SLAM-Based Robotic Mapping Method for Planetary Construction.

With the recent discovery of water-ice and lava tubes on the Moon and Mars along with the development of in-situ resource utilization (ISRU) technology, the recent planetary exploration has focused on rover (or lander)-based surface missions toward the base construction for long-term human exploration and habitation. However, a 3D terrain map, mostly based on orbiters’ terrain images, has insufficient resolutions for construction purposes. In this regard, this paper introduces the visual simultaneous localization and mapping (SLAM)-based robotic mapping method employing a stereo camera system on a rover. In the method, S-PTAM is utilized as a base framework, with which the disparity map from the self-supervised deep learning is combined to enhance the mapping capabilities under homogeneous and unstructured environments of planetary terrains. The overall performance of the proposed method was evaluated in the emulated planetary terrain and validated with potential results.