Horizon Line Research Articles

ReScape: transforming coral-reefscape images for quantitative analysis

Ever since the first image of a coral reef was captured in 1885, people worldwide have been accumulating images of coral reefscapes that document the historic conditions of reefs. However, these innumerable reefscape images suffer from perspective distortion, which reduces the apparent size of distant taxa, rendering the images unusable for quantitative analysis of reef conditions. Here we solve this century-long distortion problem by developing a novel computer-vision algorithm, ReScape, which removes the perspective distortion from reefscape images by transforming them into top-down views, making them usable for quantitative analysis of reef conditions. In doing so, we demonstrate the first-ever ecological application and extension of inverse-perspective mapping—a foundational technique used in the autonomous-driving industry. The ReScape algorithm is composed of seven functions that (1) calibrate the camera lens, (2) remove the inherent lens-induced image distortions, (3) detect the scene’s horizon line, (4) remove the camera-roll angle, (5) detect the transformable reef area, (6) detect the scene’s perspective geometry, and (7) apply brute-force inverse-perspective mapping. The performance of the ReScape algorithm was evaluated by transforming the perspective of 125 reefscape images. Eighty-five percent of the images had no processing errors and of those, 95% were successfully transformed into top-down views. ReScape was validated by demonstrating that same-length transects, placed increasingly further from the camera, became the same length after transformation. The mission of the ReScape algorithm is to (i) unlock historical information about coral-reef conditions from previously unquantified periods and localities, (ii) enable citizen scientists and recreational photographers to contribute reefscape images to the scientific process, and (iii) provide a new survey technique that can rigorously assess relatively large areas of coral reefs, and other marine and even terrestrial ecosystems, worldwide. To facilitate this mission, we compiled the ReScape algorithm into a free, user-friendly App that does not require any coding experience. Equipped with the ReScape App, scientists can improve the management and prediction of the future of coral reefs by uncovering historical information from reefscape-image archives and by using reefscape images as a new, rapid survey method, opening a new era of coral-reef monitoring.

Intelligent Methods for Forest Fire Detection Using Unmanned Aerial Vehicles

This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods.

INTERPRETASI DATA SEISMIK REFLEKSI : PICKING HORIZON DAN PICKING FAULT

Seismic method practicum has been carried out with the title "Interpretation of reflection seismic data: picking horizon and picking fault". The seismic method is a geophysical method that is often used in imaging the subsurface conditions of the earth. The purpose of this practicum is to find out how to do picking horizon and picking fault. Picking horizon and picking faults are done with petrel software. Picking Horizon is a method that is carried out by making a horizon line on a continuous layer on a seismic cross section. For picking horizon, petrel software is used. From these data it is known that there are 3 horizons (layers). Fault picking is carried out simultaneously with seismic horizon picking. Fault picking is carried out starting from a clear shift in the horizon and continuing to the vertical shift zone. For picking faults, petrel software is used. From these data it is known that there are 4 faults (faults).

THEORETICAL SOLUTIONS FOR INTEGRATIVE TEACHING OF FINE ARTS AND ENGINEERING GRAPHICS WITH VARIOUS DISCIPLINES OF STILL LIFE, CONSISTING OF GEOMETRIC SHAPES IN PENCIL PAINTING

Through this article, it is necessary for the authors to draw attention in students to the description of what constitutes integrity in terms of location and composition of existence, methods of constructing a still life, logical connection between objects, and when describing these objects, it is necessary to draw attention to the horizon line, the ratio of geometric shapes, the correct finding of, the ability to correctly identify shadows and lights in geometric shapes, and to find the invoice of geometric shapes, the subjects of Fine Arts and engineering graphics were also briefly covered by various methods of integrative reading with different disciplines.

Дискурсивное пространство изучения феномена утопии в современной России: парадигмальный анализ

Using the example of Russian discourse, the article demonstrates modern trends in the study of utopias. Research topics are analysed and key conceptual trends are highlighted. The subject of consideration is monographs, dissertations and articles published in scholarly peer-reviewed journals, the selection criteria being relevance, novelty, use of modern methodology, as well as practical significance. The analysis involved general research methods. The works span between 2020 and 2023, which includes the period of the COVID-19 pandemic as well as serious changes in the global political situation. The author hypothesizes that the pandemic and foreign policy events of 2022–2023 have updated the topics of utopia and dystopia studies. The paper concludes that the interest in the subject remains strong and that in-depth historical and philosophical research into this phenomenon is being conducted. In Russian discourse, utopia is often viewed as “a place that does not exist”. When utopia is interpreted as a “blessed land”, it represents an ideal or an ever-elusive horizon line. In cases where the feasibility of implementing a utopia is discussed, it is noted that it ceases to be a utopia and undergoes a number of fundamental changes, turning into its antipode. The possibility of serious social changes, dreamed of by the authors of utopias, is not categorically denied by researchers, the reservation being that people must be prepared for a new social order, different from the existing models of society. The most successful form of a utopian work is still considered to be a narrative. With the use of modern technologies, utopia is primarily visualized in disaster films or computer games, that is, once again takes on a shape of its opposite. However, despite a significant amount of research published on the problems of utopia, Russian discourse remains quite conservative in relation to the global trends in understanding and studying this phenomenon.

A Fast Horizon Detector and a New Annotated Dataset for Maritime Video Processing

Accurate and fast sea horizon detection is vital for tasks in autonomous navigation and maritime security, such as video stabilization, target region reduction, precise tracking, and obstacle avoidance. This paper introduces a novel sea horizon detector from RGB videos, focusing on rapid and effective sea noise suppression while preserving weak horizon edges. Line fitting methods are subsequently employed on filtered edges for horizon detection. We address the filtering problem by extracting line segments with a very low edge threshold, ensuring the detection of line segments even in low-contrast horizon conditions. We show that horizon line segments have simple and relevant properties in RGB images, which we exploit to suppress noisy segments. Then we use the surviving segments to construct a filtered edge map and infer the horizon from the filtered edges. We propose a careful incorporation of temporal in- formation for horizon inference and experimentally show its effectiveness. We address the computational constraint by providing a vectorized implementation for efficient CPU execution, and leveraging image downsizing with minimal loss of accuracy on the original size. Moreover, we contribute a public horizon line dataset to enrich existing data resources. After extensive tests, we report the following major findings: 1) thanks to its filter, our algorithm accurately detects horizon lines with low or weak edge response, 2) the vectorized filter takes no more than 1.71% of the overall computations, while most of the computations are taken by the Line Segment Detection (LSD) algorithm we integrated into our pipeline, 3) our strategy of incorporating the temporal information avoids outlier detections, mitigates the effect of strong noisy lines, and exhibits high robustness when using incorrect detections as a temporal reference. Our algorithm’s performance is rigorously evaluated against state-of-the-art methods, and its core components are validated through ablation experiments.

К вопросу о пространственной композиции пейзажа эпохи символизма и модерна (на примере работ 1890‑х гг. М.В. Якунчиковой-Вебер, К.А. Сомова, А.Н. Бенуа)

The paper presents an attempt to analyse and classify the spatial composition of landscape paintings created in the 1890s by painters who actively collaborated with the World of Art (Mir iskusstva) association and were close to Art Nouveau and Symbolism. Their novelty partially results from impressionist innovations, with the latter revised in terms of both plastic effect and meaning. One of such revised formulae is vividly embodied in the works by М.V. Yakunchikova-Weber, as well as Е.D. Polenov and V.D. Polenov: fragment of a landscape depicting (almost) no ground or sky, tending towards a carpet-like surface and filled with vegetation forms of varying degrees of conventionality. Landscapes focusing on the lower layer of vegetation, flowers, and grass growing from the ground, or in combination with a smooth lake surface motif (the sky as if overturned into water) become a special variant of composition. This comes in tune with the Art Nouveau’s interest in vegetation and water, and Symbolism’s fascination with the motif of reflections. The latter may also be implemented in landscape in a window compositions: combination of reflection (microcosm of the painter’s inner world) and landscape (nature’s macrocosm) on the illusively two-layer surface. М.V. Yakunchikova-Weber and К.А. Somov transform the Landscape without sky, view from a balcony perspectives anticipated by C. Monet’s experiments into a special type of chamber park landscape: a beautiful shelter isolated from the world and the sky endlessness disturbing the soul. At the same time, panoramic landscapes (by K.А. Somov and А.N. Benois) tend towards an extremely high or low horizon line that is far from the everyday perception, oftentimes being presented from behind the back of a park statue and as if seen by its eyes.

Современная детская книжная иллюстрация: композиция, пространство, движение, время

The composition in a modern children’s book is associated with solving the problems of space and movement. Dynamics is part of the structure of the book, the book design system is determined by the movement of the plot, the principles of reception, the rhythm of the font and the alternation of images are dynamic. The principles of space construction in a modern children’s book are associated with the leading means of artistic expression of the art of graphics. The space of the book turns into a narrative, a space of history; narrative space acts as the theme of the image, and the void is also narrative as a kind of figure of silence. Space as an artistic technique uses the principles of panorama, division into plans, and the location of the horizon line. The transformation of time in the structure of a modern children’s book is focused on the concept of dialogue between the plot and the image. Time uses a reception complex, focusing on perception, viewing, interactive practices, book design can use the principle of repetition and return. The epoch style and font can mark the epoch. Space and time act in book design as a system of plot development, a spacetime continuum. The time of the narration, the time of the artist and the time of the viewer can exist in a synchronous and diachronic format. Time as a character change involves the interpretation of a theme, a change in spatial coordinates, search, study, movement. The use of a certain point of view and foreshortening in the composition of a modern children’s book illustration can be achieved by the technique of duplication of viewing, an image «from the back» or from above, a panoramic view and fragmentation. Classical «pictorial» composition and spatial construction are often used. The theme of movement in the composition of the book is associated with the popularity of the type of travelogue book (tales of wandering-the formation of a hero, educational literature, travel literature, guidebooks). Methods of constructing space in the book composition system – top view, angular composition, combination of spatial plans, close-up. The dynamics of the font correlates with the dynamics of the text, the letters «come to life». Several effects associated with new media: animation, cinematic effect of space, theatricalization, imitation of a recognizable screensaver. The serial nature of the images can apply a sequential arrangement of the stages of movement, «storyboard», step-bystep approach or removal of the object, dialogic composition, close-up.

A hybrid system for identifying the presence of clouds on the horizon line

Common passive surveys for the presence of clouds in the sky are carried out using the digital processing of photographs taken using fish-eye type lenses. Another type of survey is carried out using active measuring systems, e.g. thermal imaging, active laser distance sensors, etc. A common feature of these sensors is the high cost of the measuring apparatus, which is hardly acceptable for small local short-term weather forecasting stations. The main task of these weather stations is to forecast local dynamic weather phenomena that have (or may have) an impact on the use or operation of technical facilities (e.g. photovoltaic farms, cranes, etc.) or agricultural plant protection measures. This paper proposes a hybrid method for detecting clouds and predicting changes in cloud cover on the horizon line. The proposed method is based on an analysis of colour photographs of the cross-section of the sky using chrominance distribution by the RGB method. In the next step, the CCT colour temperature and the ALS-based ambient light intensity resulting from spectral analysis are determined for the cross-section of the sky being identified. The survey results indicate the dependence of the variability of CCT and ALS parameters for classifying objects on the horizon line. The above analysis makes it possible to distinguish the sky on the horizon, a cloud, or agglomeration elements. The data obtained from the surveys show that the proposed structure of the hybrid system for analysing the presence and movement of clouds on the horizon line can provide the basis for further development of data processing algorithms for a passive sensor of the apparatus for detecting clouds and other objects on the horizon line.

HORIZON DETECTION using Machine Learning

This project focuses on utilizing machine learning techniques for horizon detection, with applications ranging from planetary rover localization to flight control and port security. Traditional methods like GPS are unavailable in certain scenarios, making horizon detection a critical visual cue for precise position and orientation estimation. The proposed approach involves Canny edge detection, followed by the classification of edges as either "horizon" or "non-horizon" using a Support Vector Machine (SVM) trained on ground truth data and SIFT (Scale-Invariant Feature Transform) features. When applied to new images, this process identifies a consistent horizon line, offering a robust and adaptable solution for addressing \complex real-world challenges.

The method of inertial-visual orientation of the aircraft

The article proposes a method for determining the orientation angles of an aerial vehicle based on information from an optical camera and a triad of angular velocity sensors. The basic formulae necessary for determining the orientation angles and calculating the size of the image area for processing are given. Simulation of the operation of the algorithm for determining the pitch angle of the airial vehicle on real images was carried out. At the same time, the errors of sensors were taken into account. The use of angular velocity sensors of low and medium accuracy class was considered. The advantages of the method are the absence of the need to detect the horizon line and low requirements for the navigation computer.

GPro3D: Deriving 3D BBox from ground plane in monocular 3D object detection

Considering the inherent ill-posed nature, monocular 3D object detection (M3OD) is extremely challenging. The ground plane prior is a highly informative geometry clue in M3OD. However, it has been neglected by most mainstream methods. This paper introduces an original M3OD framework that leverages the ground plane to directly derive the object’s 3D Bounding Box (BBox) and 3D attributes geometrically. We identify and tackle three key factors that limit the applicability of the ground plane: the projection point localization issue, the ground plane tilt issue, and the lack of ground plane annotation issue. For the projection point localization issue, we propose leveraging the car’s explicit and salient wheel pixels, which are easier for the neural network to detect compared to the bottom vertices or the bottom center of the 3D BBox. To tackle the ground plane tilt problem, we propose a vertical-edge-enhanced horizon line detection algorithm to precisely deduce the ground plane equation. Moreover, using only M3OD labels, wheel pixel and horizon line pseudo-labels can be easily generated to train the network without extra data or annotation cost. Extensive experiments demonstrate the effectiveness and superiority of our framework over previous methods.

Quality assessment of the Topo-Iberia CGPS stations and data quality's effects on postfit ionosphere-free phase residuals

This paper analyzed GPS data from the Topo-Iberia network spanning almost 12 years (2008–2020). The data quality information for all 26 Topo-Iberia stations is provided for the first time, complementing the Spanish Geological Survey's storage work. Data analyses based on quality indicators obtained using TEQC have been carried out. The guidelines and data quality information from the IGS stations have been considered as the quality references, with the stations ALJI, EPCU, and TIOU standing out as the worst stations, while on the contrary, FUEN, PALM, PILA, and TRIA meet the quality requirements to become an IGS station. The relationship between the GPS data quality and their GAMIT- and GipsyX-derived postfit ionosphere-free phase residuals has also been investigated, and the results reveal an inversely proportional relationship. It has been found that the stations showing an increase in elevation of the horizon line, also show an increase in cycle slips and multipath, are among the poorest quality stations, and among those with the highest postfit RMS of phase residuals. Moreover, the evolution of the vegetation around the antenna should be considered as it could cause a progressive loss of quality, which is not complying with the IGS standards. The quality assessment shows that the Topo-Iberia stations are appropriate for geodetic purposes, but permanent monitoring would be necessary to avoid the least possible loss of data and quality. In addition, a method to characterize the GNSS data quality is proposed.

Analysis of errors of the artificial horizon sensor based on vision system

The article discusses the features of the practical implementation of the artificial horizon sensor based on the onboard vision system. Proposed, developed on the basis of well-known applications, a variant of the algorithm for the operation of an unmanned aerial vehicle orientation video system. The problems of automatic detection and determination of the position of the horizon line on changing digital images that make up the video stream from the onboard digital camera are shown. The analysis of the factors influencing the accuracy of estimation of carrier orientation angles using the proposed system is carried out. The results of a practical study are presented, characterizing the degree of influence of the considered factors on the total error. A discrete stochastic mathematical model of an unmanned aerial vehicle orientation system based on an onboard vision system has been developed. The possibility of providing an acceptable level of accuracy of the orientation video system due to certain technical and algorithmic solutions is shown. The conclusion is made about the expediency of using this system in autonomous multisensor navigation systems for unmanned aerial vehicles.

Research on a Horizon Line Detection Method for Unmanned Surface Vehicles in Complex Environments

A critical step in the visual navigation of unmanned surface vehicles (USVs) is horizon line detection, which can be used to adjust the altitude as well as for obstacle avoidance in complex environments. In this paper, a real-time and accurate detection method for the horizon line is proposed. Our approach first differentiates the complexity of navigational scenes using the angular second moment (ASM) parameters in the grey level co-occurrence matrix (GLCM). Then, the region of interest (ROI) is initially extracted using minimal human interaction for the complex navigation scenes, while subsequent frames are dynamically acquired using automatic feature point matching. The matched ROI can be maximally removed from the complex background, and the Zernike-moment-based edges are extracted from the obtained ROI. Finally, complete sea horizon information is obtained through a linear fitting of the lower edge points to the edge information. Through various experiments carried out on a classical dataset, our own datasets, and that of another previously published paper, we illustrate the significance and accuracy of this technique for various complex environments. The results show that the performance has potential applications for the autonomous navigation and control of USVs.

Magnitude and determinants of road traffic accidents in North Gondar Zone; Amhara Region, Ethiopia

Background: Despite efforts that the government has made to minimize the number of casualties or injury levels in Ethiopia, road traffic accidents remain a severe health concern throughout the country and in the study area as well. This study aims to examine the primary contributing variables of road traffic accidents in the North Gondar zone, under 24 administrative. Methods: The functional class of roads were directly examined on the site to evaluate the existing conditions of the roads which includes the geometric design constraints, functional class, daily traffic, and surfacing materials. Secondary source of data types, previously recorded road traffic accident information was collected from North Gondar zone traffic police departments. Road inventory information was collected from Gondar branch Ethiopian road authority under the specified horizon lines. Results: The magnitude and frequency of traffic accidents caused by driver-related factors( age, sex, level of education, driving experience, ownership responsibility of a vehicle and driver responsibility, time and day-wise distribution of traffic accidents), vehicle-related factors (failures of mechanical parts and its service age), road related factors( geometric design and construction, inventory information, road surfacing materials), pedestrians, and environmental factors were critically analysed. The result shows that a higher proportion (67%) of traffic accidents are mainly due to driver behaviour related factors than other causative factors. Conclusions: According to the results of the study, bad driving behaviour’s (exceeding the design speed, using a phone while driving, dangerous overtaking, excessive braking, loading above capacities, illegally parking out of public stations should be controlled to reduce the road traffic accident in the study area. In addition, successive up-to-date advanced computerized traffic accident safety training and recording systems should be given at least once a year through regional-based or at a central zone administrative zones for the traffic officers.

The Polish Catholic Church under German Occupation: The Reichsgau Wartheland, 1939–1945

The Polish Catholic Church under German Occupation: The Reichsgau Wartheland, 1939–1945

Nothingness in the digital Space

Valerie Messini (Peter Weibel Research Institute for Digital Culture) chooses the phenomenon of emptiness in art as a point of departure for her contribution "Nothingness in the digital Space" and presents her artistic projects operating with different technologies to approach the phenomenon of emptiness in connection with corporeality in digital space. "1-NO1-100.000" uses dance movement to explore emptiness in virtual space, and "Deep Empty - Wide Open" uses deep learning to question the extent to which horizon lines function as mental voids.

Сцены осирического ритуала в стеле Абкау (Louvre C 15): проблемы интерпретации

The article deals with the relief scenes of the ancient Egyptian stele Abkau (XI Dyn.), which are usually interpreted in the context of the Osirian cult. On the basis of comparative analysis of drawings and inscriptions of the stele with the Egyptian funerary texts (the Pyramid Texts, the Coffin Texts, the Book of the Dead, the Book of Day and Night) the author reveals the symbolic meaning of stela reliefs in the context of the mythological stories about the birth of the sun god from a lotus flower, the mourning of Osiris, the birth and growth of his son Horus in Buto, the battle of Horus with the enemies of Osiris and his subsequent ascension to the throne, the stay of the solar god and the deceased in the Fields of Offerings and/or the Fields of Reeds, which were considered the dwelling of “blessed” souls. In the context of the solar, Osiris and funerary cults, the Neshmet bark is understood not only as an Osirian boat and a boat of the deceased in the afterlife, but also as an image of a celestial boat, as well as a symbol of the lunar crescent and the horizon line. The study of the composition of stela reliefs reveals that they do not represent the sailing of the Neshmet bark depicted in the middle of the register, but rather its stationary stay in the sanctuary of the temple of Abydos, among the rooms where offerings were made to the various gods mentioned in the line above the middle register.

Virtual Grid Mapping for Visual Size Measurements

This paper proposes a novel, more robust method for single-image visual size measurements, named Virtual Grid Mapping (VGM). VGM requires just a single image as input; however, it does not require any prior information concerning the scene like the horizon line or reference objects. Unlike current methods, the VGM approach uses a grid of virtual 3D points projected to the 2D image plane, along with the fusion of probable depth values indicated by 2D-3D point correspondences, it manages to reduce the uncertainty originating from the calibration and the positioning of the camera; thus, providing more accurate measurements. Given the geometric properties of the camera, a novel approach of VGM is that it automatically generates and projects a grid of virtual 3D points to the 2D image plane, enabling the establishment of approximative correspondences between 3D points of the real world and 2D points of the image plane. Then, by considering these initial 3D-2D point correspondences as known, a range of possible depth values is estimated, and through an adaptive fusion process, the size of an object of interest can be accurately approximated. Another advantage of VGM over the state-of-the-art deep learning -based methods, is that it requires a simple training process. Experiments performed on simulated and real image datasets, captured in controlled conditions and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in-the-wild</i> , show that the mean absolute percentage error (MAPE) of the proposed method ranges between 3.13% and 11.66%.