Horizon Line Research Articles

Automatic far‐field camera calibration for construction scene analysis

AbstractThe use of cameras for safety monitoring, progress tracking, and site security has grown significantly on construction and civil infrastructure sites over the past decade. Localization of construction resources is a crucial prerequisite for many applications in automated construction management. However, most existing vision‐based methods perform the analysis in the image plane, overlooking the effect of perspective and depth. The manual and labor‐intensive process of traditional calibration techniques, as well as the busy and restrictive construction environment, makes this a challenging task. This study proposes a framework for automatic camera calibration with no manual intervention. The framework utilizes convolutional neural networks for geometrical scene analysis and object detection, which are used to estimate the location of horizon line, vertical vanishing point, as well as objects with known height distributions. This enables automatic estimation of camera parameters and retrieval of scale. The proposed framework is evaluated on images from two major construction projects in Melbourne, Australia. Results show that the proposed method achieves a minimum accuracy of 90% in estimating proximity of points on the ground and can facilitate further development of vision‐based solutions for safety and productivity analysis.

Bilder, Klänge und Gedanken als Orientierungsfaktoren: Anhaltspunkte bei Nietzsche und Wittgenstein

AbstractImages, sounds and thoughts as orientation factors: Clues with Nietzsche and Wittgenstein. – The paper demonstrates how images and sounds become clues both for Nietzsche and Wittgenstein in order to understand sentences and thoughts (I). Nietzsche pursues the question of how we orient ourselves not only through thoughts but also through images and sounds from his philosophical beginnings and, by doing so, he draws horizon lines for answering this question (II). In approximately these leeways, Wittgenstein asks how thinking, instead of simply thinking itself, shows itself: he explores the possibilities of methodically describing this showing itself and finds them in analogizing the understanding of a sentence on the one hand and the understanding of an image and of a piece of music on the other (III).

Graph-Based Horizon Line Detection for UAV Navigation

Perceiving the horizon line is a critical alternative for unmanned aerial vehicle (UAV) autonomous navigation, especially in the presence of noise-induced drift, unavailability of satellite navigation, and multipath errors. However, its quite tough to detect the horizon line, due to the remotely sensed big data, the dynamic changes in flight, and the serious consequences of failure. To address these problems, we propose a graph-based horizon line detection technique that is composed of graph-based image segmentation, connected domain cascade filtering, horizon line extraction, and UAV attitude estimation. We improve the graph-based image segmentation algorithm so that the segmentation results are more conducive to horizon line detection. We then determine the sky-component by cascade filtering and extract the horizon line based on the boundaries of the sky-component. Furthermore, we directly compute the roll and pitch according to the extracted horizon line and eliminate the ambiguity of the angles. To validate our approach qualitatively and quantitatively, we designed a fixed-wing UAV system. We then validated our algorithm through extensive flights under various conditions and compared the estimated rolls and pitches to the IMU ones. Statistical results show that the proposed technique provides unbiased attitude angles with error variance of about 2, which verify the validity and robustness of our method. For engineering, our program runs at approximately 60 frames per second on the fly after optimizing.

The Lost List

The Lost List Ryan Bradley (bio) My grandfather once taught me how to use a sextant. We were at sea, motoring toward Baja California’s Isla San Martín, many miles off Punta Colonet, out of sight of land. The time was important, as I recall. We took turns squinting into the sextant’s sight, lining up the angle of the noonday sun so that the mirrors reflected its image onto the horizon line, which kept bouncing up and down with us and the boat and the ocean’s swell. It was hot, and awkward, and I remember wanting to give up on the task several times. Someone on board — my uncle, most likely — snapped a photo of us. I must have been aware of his taking it, because I’m hamming it up, brow furrowed and squinting hard into the sight, like I know what the hell I am doing. It’s not a good photo of me, but my grandfather looks perfectly at ease. He’d navigated this way during World War II, up to and even after his ship, a combat cutter, was torpedoed by a German sub and partially sank in the North Atlantic. He would have died were it not for some Icelandic fisherman who happened to be trawling nearby, and to whom I owe my existence. After making note of the angle, I [End Page 480] remember retreating into the shade and staring at a nautical chart, then drawing a line from where we had been to where we now, with the help of the sextant, supposed we were. It seemed both very precise — the instrument, the charts, the various calculations — and something approximating a tremendous guess. The great blue sky and deep blue sea and us, on a little white boat, out in the vastness, trying to find our way. ________ About a year ago I began keeping a list of lost things: objects and areas that acted as engines of disappearance or disorientation; individuals who had vanished suddenly and mysteriously, then returned, or not; animals that had taken strange and extraordinary rambles trying to find — something, whatever it was wasn’t always clear. I suppose my intent was something like the sun lines I’d learned from my grandfather, the plotted points on a nautical chart. If I could take all these entries and order them just so, perhaps they would lead somewhere. When I began the list, the world was shutting down, the future felt terribly uncertain, and I felt lost. My lost list was a way to calm my mind, order chaos, plot a course through the unknown. I began with places. The first entry is the Box-Death Hollow Wilderness, in southern Utah — a mess of slot canyons, dry washes, and a few trails. People often get lost there. In 2012, a fifty-nine-year-old woman hiking the Box-Death Hollow jumped down a small ledge and broke her leg. Lying there, she realized she hadn’t told anyone where she was. She was also a diabetic and had failed to pack food. Forty years earlier, however, she’d taken a survival course; she had on her person a scarf and a walking stick, which she used to fashion a brace for her leg. During the day, she slept, so that she could stay up all [End Page 481] night, huddled beneath her poncho in order to stave off hypothermia. She did not wander, for she knew that she wouldn’t get far with her leg. More importantly, she recalled from her course that once someone began looking for her, she had a much better chance of being found if she stayed put. On the fourth day, a local search and rescue team spotted her. Beneath places there are entries for the Black Sea, the North Sea, the Orkney Islands, the Bermuda Triangle, and Mocha Island, off the coast of Chile, where shipwrecks are so common that many of its houses are cobbled together from the scavenged parts of boats run aground. The Lost Sea in Tennessee is an underground lake, the largest in the United States, and where some 20,000 years ago, a giant jaguar...

ВИЗНАЧЕННЯ ВАЖЛИВОСТІ ВПЛИВУ ТЕХНОЛОГІЧНИХ ЧИННИКІВ НА ВІДНОВЛЕННЯ ЗАЛІЗОБЕТОННИХ КОНСТРУКЦІЙ

The article made an analytical study, by expert estimates, the determination of the importance of technological factors that have the greatest impact on the physical and mechanical properties of recovered parts of concrete structures. Technological factors were identified during the analysis of scientific literature. For the consideration of the experts was presented eight technological factors, namely: the stiffness, the repair mixture; seal; thickness of the recovery layer; the ambient temperature when performing rehabilitation works; condition of the surfaces of the concrete samples (the surface can be cleaned, stripped, with notches artificially destroyed...); the method of preparing the repair surface (use of contact layer); moisture content of the repair surface (dry, damp, wet); provision and maintenance Department relative to the horizon line (the position of the top "floor"; the side – "wall"; bottom – "ceiling"). The information obtained from experts, were edited on the basis of mathematical (statistical) method. The calculated estimate of the average degree of agreement of opinions of all experts and assessment of the significance of coefficient of concordance. Determined weight factors are considered: preparation of the repair surface; position of the repair site relative to the horizon; the state of the surfaces of the concrete samples (the repair surface is not cleaned, cleaned, with notches artificially destroyed); the stiffness of the mixture; sealing; moisture repair surface (dry, damp, wet); the ambient temperature when performing recovery operations and the thickness of the recovery layer.

Real time reorientation and cognitive load adjustment allow for broad application of virtual reality in a pediatric hospital

With a new generation of affordable portable virtual reality (VR), clinicians are discovering more utility for VR, while also identifying opportunities for improvement, such as the inability to reorient the horizon line during repositioning or transport, or modulate cognitive load in real time. At our institution, this lack of functionality prohibited or decreased VR usage in some clinical scenarios such as dressing changes with dynamic positioning. The purpose of this brief report is to describe the development and use of a VR application that is optimized for the healthcare setting and report historical effects of patients who utilized VR as supplement to Child Life procedures. Eligible affects per chart review included Happy, Relaxed, Anxious, Distressed, Unable to Assess. Given the need for real-time reorientation and cognitive load modulation, we created the Space Pups™ VR application. The experience was launched as part of the Stanford Chariot Program in the summer of 2017, and its usage was tracked through the electronic medical record and a VR application dashboard. Chart review was queried from 3 January 2018 to 9 August 2021 for pediatric patients who used VR with real-time reorientation and cognitive load modulation as a supplement to their Child Life interventions. The Space Pups™ experience has been successfully used in a variety of settings, including perioperative care, vascular access, wound care, and ENT clinic, a total of 1696 times. Patients ranged from 6 years to 18-year old, with no reports of side effects. Significant results (P<0.001) were observed pre- and post-VR use for affect improvements in Happy, Relaxed, and Anxious, but not for Distressed. The ability to reorient VR experiences in real time has increased functionality where other applications have failed. While more studies are needed to quantify the anxiolytic and pain-reducing effect of Space Pups™, our report demonstrates the feasibility of this VR experience as a non-pharmacological modality to safely increase patient cooperation in a wide variety of clinical settings.

Visually Induced Motion Sickness on the Horizon

Visually induced motion sickness is an unpleasant but common side-effect of many simulations and VR-applications. We investigated whether an earth-fixed reference frame provided in the simulation is able to reduce motion sickness. To do so, we created a moving starfield that did not contain any indicators of the spatial orientation of the observer. As the observer was simulated to move through the randomly oscillating starfield, a time-to-contact task had to be carried out. Two colored stars on collision course with each other had to be spotted, then they disappeared and the time of their collision had to be judged. Eye-movements, task performance, and motion sickness were recorded. This condition without visual reference to the observer's upright was supplemented with three conditions containing either an earth-fixed fixation cross, an earth-fixed horizon line, or a line that was yoked to the head. Results show that only the earth-fixed horizon was able to significantly reduce visually induced motion sickness. Thus, a mere earth-stationary anchor does not suffice, a clear indication of earth horizontal seems necessary to reap a modest benefit.

FEATURES OF HOLOGRAPHIC PERCEPTION OF VISUAL PERSPECTIVE IN ARCHITECTURE

The article is devoted to the phenomenon of holographic human perception in the analysis of the architectural environment. Includes aspects of perspective-tonal perception of visual factors of holographic scanning of the human visual system. Aimed at understanding and reproducing the features and nuances of vision, in the context of summary analysis and reproduction of the system of energy flows in the elements of visual perception. The holographic factor of perception of reality is based on the difference between the work of the right and left eye, with the peculiarity of the angular adjustment of vision to the object of observation. The horizon line or the height of the perception of volumes, as well as the position of the spaces of the architectural environment remain dominant.

Fast infrared horizon detection algorithm based on gradient directional filtration.

Infrared imaging has been widely used in the field of sea surface monitoring. Horizon detection is a key step before a target's detection, locating, and tracking in the sea-sky infrared scene. Reducing processing time while ensuring accuracy is the research focus of infrared horizon detection. This paper proposes a novel method of a line segment detector (LSD) algorithm with gradient direction filtering. First, the rough extraction of the sea-sky region is used to limit the size of the detected image, and then the potential horizon line segment is extracted, applying the improved LSD algorithm in the sea-sky region, which probably contains many false extraction results. Then, gradient direction filtering is designed to pick the horizon line segments in this step. Finally, the horizon line segments are stitched to obtain the whole horizon line based on random sample consensus. The results of the comparative experiments show that this novel method has high detection accuracy, and the processing time is significantly shortened; what is more, we can also conclude that this method has a good performance on the detection stability.

Preliminary Support for the Line Bias Illusion as a Contributor to Black Hole Effects

ABSTRACT Objective We tested the plausibility of the hypothesized Line Bias Illusion to explain a spatial disorientation phenomenon known as the Black Hole Illusion (BHI): in the absence of a visible horizon, pilots misjudge an implicit horizon from the convergence point of parallel runway edge lines. Background BHI occurs when impoverished visual conditions at night cause pilots to fly too low on landing approaches. Multiple hypotheses have been proposed to explain BHI, without clear consensus in the literature. Method We conducted multiple experiments in which participants judged the intersection point of dotted lines on a computer screen. In Experiment 1, participants placed a horizon line where they believed two converging dotted line segments should intersect. In Experiments 2A and 2B, participants estimated the intersection point of single dotted line segments with a separate solid line. Results Participants in Experiment 1 tended to place the intersection point of two converging lines too low on the computer screen. Participants in Experiments 2A and 2B tended to respond as if the stimulus lines were more horizontal than actually presented. Conclusion Our findings are consistent with the hypothesis that pilots misjudge the location of an implicit horizon based on the runway edge lines. In the context of a visual spatial strategy that assumes a stable horizon, such a misperception may cause pilots to adopt a low flight path.

Muon radiography employing the DIRC principle for density change measurements under volcanoes and fluid reservoirs

Mapping the density distribution and monitoring density changes under volcanoes and geological reservoirs is a major challenge in geology and volcanology. Muon radiography has a high potential to advance this field, but often there are no inexpensive high-end detectors available that are suitable for field installations. A DIRC-type Cherenkov detector as a muon camera has a small dimension and is suited for such field applications (MagmaDIRC idea). In measuring directions and energies of the incoming muons one can turn the mass density integrals along the lines of flight into a radiography image, and by discarting low-energy muons with their blurred angular information one obtains sharper images. In particular one may detect the time variation of the mass density distributions situated above the horizon line in a volcanic edifice that occurs when magma is filling its plumbing system or when the level of a lava lake changes. Using numerical simulations, we discuss design aspects and the requirements of such a DIRC system. Two sites are identified for proof-of-principle field measurements. The required measurement times are estimated for the given site conditions and morphology based on the specifications of an operational DIRC system. The merits of DIRC sensors are contrasted to other muon radiography techniques.

Comparative Analysis Between Recurrent Convolutional and Convolutional Neural Networks for Horizon Detection

The preliminary step in the navigation of Unmanned Vehicles is to detect and identify the horizon line. One method to locate the horizon and obstacles in an image is through a supervised learning, semantic segmentation algorithm using Neural Networks. Unmanned Aerial Vehicles (UAVs) are rapidly gaining prominence in military, commercial and civilian applications. For the safe navigation of UAVs, there poses a requirement for an accurate and efficient obstacle detection and avoidance. The position of the horizon and obstacles can also be used for adjusting flight parameters and estimating altitude. It can also be used for the navigation of Unmanned Ground Vehicles (UGV), by neglecting the part of the image above the horizon to reduce the processing time. Locating the horizon and identifying the various obstacles in an image can help in minimizing collisions and high costs due to failure of UAVs and UGVs. To achieve a robust and accurate system to aid navigation of autonomous vehicles, the efficiency and accuracy of Convolutional Neural Networks (CNN) and Recurrent-CNNs (RCNN) are analysed. It is observed via experimentation that the RCNN model classifies test images with higher accuracy.

Onboard Visual Horizon Detection for Unmanned Aerial Systems with Programmable Logic

We introduce and analyze a fast horizon detection algorithm with native radial distortion handling and its implementation on a low power field programmable gate array (FPGA) development board in this paper. The algorithm is suited for visual applications in an airborne environment, that is on board a small unmanned aircraft. The algorithm was designed to have low complexity because of the power consumption requirements. To keep the computational cost low, an initial guess for the horizon is used, which is provided by the attitude heading reference system of the aircraft. The camera model takes radial distortions into account, which is necessary for a wide-angle lens used in most applications. This paper presents formulae for distorted horizon lines and a gradient sampling-based resolution-independent single shot algorithm for finding a horizon with radial distortion without undistortion of the complete image. The implemented algorithm is part of our visual sense-and-avoid system, where it is used for the sky-ground separation, and the performance of the algorithm is tested on real flight data. The FPGA implementation of the horizon detection method makes it possible to add this efficient module to any FPGA-based vision system.

Efficient Horizon Line Detection using Clustering and Fast Marching Method

Video analysis of maritime scenarios typically includes detection of horizon line for reference. The horizon line is the imaginary line, which separates water and sky as well as water and land. The horizon line plays a major role in terms of demarcating the water region in the video frame for further analysis. Considerable research has been aimed at horizon line detection. Various approaches have been reported including (i) Canny based edge detection followed by Hough transform, (ii) machine learning combined with statistical methods. However, the Hough transform has several limitations, in terms excessive analysis time, deviation of estimated line from the actual horizon line, sensitivity to presence of floating objects on the horizon, error due to presence of large number of edges. Present paper describes an efficient method for detecting the horizon line for analysis videos obtained by cameras mounted on floating vessels such as unmanned surface vehicle in maritime and inland scenarios. The proposed method is based on K-means clustering followed by seed based region growing using Fast Marching Method. For detecting the horizon line, two clusters are used in water-sky region like in marine environment images whereas three or more clusters are used in water-land-sky region like in in-land rivers/lakes images. In most cases, the upper part of the frame belongs to sky region whereas lower part belongs to water region. After K means clustering, based on the selection of seed point in lower part of the frame, the water region is segmented using fast marching method from non water regions and hence the horizon line is detected. This proposed method performance is compared with edge detection followed by Hough transform for different datasets. Experimental results show that the proposed method detects efficient line without compromising the processing time.

A New Method of Improving the Azimuth in Mountainous Terrain by Skyline Matching

Augmented reality (AR) applications have a serious problem with the accuracy of the azimuth angle provided by mobile devices. The fusion of the digital magnetic compass (DMC), accelerometer and gyroscope gives the translation and rotation of the observer in 3D space. However, the precision is not always appropriate since DMC is prone to interference when using it near metal objects or electric currents. The silhouette of ridges separates the sky from the terrain and forms the skyline or horizon line in a mountainous scenery. This salient feature can be used for orientation. With the camera of the device and a digital elevation model (DEM) the correct azimuth angle could be determined. This study proposes an effective method to adjust the azimuth by identifying the skyline from an image and matches it with the skyline of the DEM. This approach does not require manual interaction. The algorithm has also been validated in a real-world environment.

Symbolic Economies between a Black Mirror and Black Aesthetic

This essay seeks to review the edges of Eric Lott's Black Mirror. But to approach the inner and outer edges of “a black mirror” is to sense the threat that they could become two sides of the same coin. In chapter 1, “Black Mirror: State Fantasy and Symbolic Surplus Value,” Lott writes, “we should explore the dimensions and especially the consequences of the fantasy race is – consequences that suffuse the consciousness of class, sexuality, gender, and other lines of force. Live there a while, in thought as in life. That is what this book tries to do.” To take up this invitation is therefore to first locate that space which readers are asked to live in for a while. However, to near that territory is not to enter the fantasy of race, if only to critique it, for we are already there. Nor is it accessed by abandoning the value of race, Lott contends, especially while the economy of whiteness continues profiting from “black symbolic capital.” Here we encounter the daunting scope of a “black mirror,” where horizon lines become Fata Morganas: an area that covers “the mechanics, dispositions, and effects of the dominant culture's looking at itself always through a fantasized black Other” (xvii). The dimensions of that mirror prove wider still, as any race, gender or class is shown capable of reflecting itself in it. More specifically, Black Mirror questions how signs of racial difference might possibly divest from the dominant symbolic economies in which they are exchanged, except Black Mirror largely does so by demonstrating their reinvestment. When analyzing the fantasies, angles and contradictions of a “black mirror,” readers are compelled to seek its outer edges, a market with real use-value, spaces where gifts are exchanged, or a beyond alluded to as “occupying the tain of the mirror – the mirror's tin backing that allows it to reflect at all” (20).

Сравнительный анализ когнитивных характеристик и креативности младших подростков с интеллектуальной и художественной одаренностью

The work is aimed at identifying specific manifestations of creativity and basic cognitive characteristics in young adolescents with artistic and intellectual giftedness. The relevance of the study is due to lack of study of the issue of cognitive manifestations of different types of giftedness in early adolescence, in which the issue of specialization of education is often resolved. The study involved 54 intellectually gifted adolescents (M = 11.4 years old) and 32 artistically gifted peers (M = 11.2 years old). The study used the following methods: a computerize d battery of test tasks for studying bas ic cognitive characteristics (“number sense”, visua l working memory and information processing speed), "Raven’s Progressive Matrixes”, “Verbally-figura l creativity test”, drawing tests of Urban and "Horizon Line ". The results confirm the hypothesis about the specificity of creativity in younger adolescents with different types of giftedness (intellectual and artistic). Intellectually gifted younger adolescents show higher rates of divergent verbal creativity compared to their artistically gifted peers; and artistically gifted younger adolescents surpass their intellectually gifted peers in terms of picturesque (figurative) creativity and are distinguished by their highquality originality, revealing a high emotional expressiveness and creative approach to the implementation of the plan. No statistically significant intergroup differences in the basic indicators of cognitive development and general intelligence were found, although artistically gifted adolescents better than their intellectually gifted peers compare asymmetrically expressed amounts (“number sense”), but they are inferior in terms of information processing speed.

Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy

The existing infrared (IR) ship target segmentation methods may suffer serious performance degradation in the situation of diverse background clutters and ship targets. To cope with this problem, a novel ship target segmentation method is proposed in this paper. Initially, the IR image is transformed into the map of large eigenvalues of structure tensor (STLE), where the horizon line and ship target boundary can be explicitly characterized. According to the scene context clue, the automatic horizon line detection (AHLD) is proposed to efficiently judge the existence of horizon line and remove sky/land region clutters. Then, based on the intensity distribution of ship target and sea background, the adaptive maximum histogram entropy (AMHE) is presented to accurately perceive the brightness (dark or bright) of ship target, and coarsely segment the bright or dark ship target from sea background. After that, considering the ship target boundary information, the regions-of-interest (ROI) of ship target is located and the ship foreground map (SFM) is developed to address the under-segmentation. Finally, a new Watershed algorithm namely structure tensor and maximum histogram entropy modified Watershed transform (TEWT) is constructed to completely extract the whole ship target. Extensive experiments show that the proposed method outperforms the state-of-the-art methods, especially for IR images with intricate background clutter and heavy noise. Moreover, the proposed method can work stably for ship target with unknown brightness, uneven intensities, low contrast, variable quantities, sizes, and shapes.

Hierarchical two-pathway autoencoders neural networks for skyline context conceptualisation

In this paper, we proposed a novel hierarchical two-pathway autoencoders architecture to transform a local information based on skyline scene representation, into nonlinear space. The first pathway is intended for the transformation of the geometric features extracted from the horizon line. The second pathway is applied after the first one to joint the colour information under the skyline to the transformed geometric features, and to get the landscape context conceptualisation. To evaluate our suggested system, we constructed the SKYLINEScene database containing 2,000 images of rural and urban landscapes, with a high degree of diversity. In order to investigate the performance of our HTANN-Skyline, many experiments were carried out using this new database. Our approach shows its robustness in skyline context conceptualisation and enhances the classification rates by 1% compared to the AlexNet architecture; and by more than 10% compared to the hand-crafted approaches based on global and local features.

GPS‐level accurate camera localization with HorizonNet

AbstractThis paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation method where the horizon line is extracted in a 360° panoramic image around the USV. We design a convolutional neural network (CNN) architecture to determine an approximate horizon line in the image and implicitly determine the camera orientation (the pitch and roll angles). The panoramic image is warped to compensate for the camera orientation and to generate an image from an approximately level camera. A second CNN architecture is designed to extract the pixelwise horizon line in the warped image. The extracted horizon line is correlated with digital elevation model data in the Fourier domain using a minimum output sum of squared error correlation filter. Finally, we determine the location of the maximum correlation score over the search area to estimate the position of the USV. Comprehensive experiments are performed in field trials conducted over 3 days in the archipelago. Our approach provides excellent results by achieving robust position estimates with global positioning system (GPS)‐level accuracy in previously unvisited test areas.