Layout Of Objects Research Articles

IMapper

Next generation smart and augmented reality systems demand a computational understanding of monocular footage that captures humans in physical spaces to reveal plausible object arrangements and human-object interactions. Despite recent advances, both in scene layout and human motion analysis, the above setting remains challenging to analyze due to regular occlusions that occur between objects and human motions. We observe that the interaction between object arrangements and human actions is often strongly correlated, and hence can be used to help recover from these occlusions. We present iMapper, a data-driven method to identify such human-object interactions and utilize them to infer layouts of occluded objects. Starting from a monocular video with detected 2D human joint positions that are potentially noisy and occluded, we first introduce the notion of interaction-saliency as space-time snapshots where informative human-object interactions happen. Then, we propose a global optimization to retrieve and fit interactions from a database to the detected salient interactions in order to best explain the input video. We extensively evaluate the approach, both quantitatively against manually annotated ground truth and through a user study, and demonstrate that iMapper produces plausible scene layouts for scenes with medium to heavy occlusion. Code and data are available on the project page.

Dentate granule and mossy cells exhibit distinct spatiotemporal responses to local change in a one-dimensional landscape of visual-tactile cues

The dentate gyrus (DG) is critical for detecting changes in environments; however, how granule cells (GCs) and mossy cells (MCs), the two excitatory cell types of the DG, respond to small changes in the object layout is unclear. Here, we recorded GCs and MCs, identified by spike feature and optogenetic tagging, as mice ran on a treadmill belt enriched with visual-tactile cues. We observed that fixing a new cue on the belt induced a reconfiguration of GC and MC spatial representations via the emergence, extinction and rate alteration of firing fields. For both GCs and MCs, the response was maximal near the cue and spread over the entire belt. However, compared to the GC response, the MC response was stronger and more immediate, peaked at a slightly earlier belt position, and exhibited a transient component reminiscent of neuromodulatory activity. A competitive neural network model reproduced the GC response contingent on both the introduction of new object-vector inputs and the reconfiguration of MC activity, the former being critical for spreading the GC response in locations distant from the cue. These findings suggest that GCs operate as a competitive network and that MCs precede GCs in detecting changes and help expand the range of GC pattern separation.

Shadow-based Illusion of Depth and Transparency in Printed Images

A cast shadow is one of the visual features that serve as a perceptual cue to the three-dimensional (3D) layout of objects. Although it is well known that adding cast shadows to an object produces the illusion that the object has a 3D layout, investigations into this illusion have been limited to virtual objects in a display. Using a light-projection technique, we show that it is possible to create a similar 3D layout illusion for real two-dimensional objects. Specifically, we displayed spatial patterns that look like cast shadows in the vicinity of an object depicted as a printed image. The combination of the cast shadow patterns with the printed object made it appear as if the printed object hovered over its original location even though the object was physically two-dimensional. By using this technique, we demonstrated that the shadow-induced layout illusion resulted in printed images having novel perceptual transparency. Vision researchers may find our technique useful if they want to extend their studies on the perception of cast shadows and transparency with real objects.

Perceiving blurry scenes with translational optic flow, rotational optic flow or combined optic flow

Perceiving the spatial layout of objects is crucial in visual scene perception. Optic flow provides information about spatial layout. This information is not affected by image blur because motion detection uses low spatial frequencies in image structure. Therefore, perceiving scenes with blurry vision should be effective when optic flow is available. Furthermore, when blurry images and optic flow interact, optic flow specifies spatial relations and calibrates blurry images. Calibrated image structure then preserves spatial relations specified by optic flow after motion stops. Thus, perceiving blurry scenes should be stable when optic flow and blurry images are available. We investigated the types of optic flow that facilitate recognition of blurry scenes and evaluated the stability of performance. Participants identified scenes in blurry videos when viewing single frames and the entire videos that contained translational flow (Experiment 1), rotational flow (Experiment 2) or both (Experiment 3). When first viewing the blurry images, participants identified a few scenes. When viewing blurry video clips, their performance improved with translational flow, whether it was available alone or in combination with rotational flow. Participants were still able to perceive scenes from static blurry images one week later. Therefore, translational flow interacts with blurry image structures to yield effective and stable scene perception. These results imply that observers with blurry vision may be able to identify their surrounds when they locomote.

Integrating visuospatial information across distinct experiences.

In two experiments, we examined whether the presence of stable visual information and the confluence of the viewpoints would cause participants to integrate in a single memory representation spatial locations they encoded at different points in time. Participants studied from the same or from different viewpoints two layouts of objects within a common visually cluttered room. Then, they carried out a series of pointing trials that involved objects from either the same or different layouts. Results showed that participants were faster for within- than between-layout judgments when they had studied the two layouts from different viewpoints but were equally fast across the two types of judgment after studying the layouts from the same viewpoint (Experiment 1). This finding suggests that they integrated locations into a single representation only when encoding the layouts from the same viewpoint. However, when participants' memory for the layout studied first was refreshed prior to testing (Experiment 2), no difference in response time was found, suggesting that they had integrated all locations in a single representation before the beginning of testing.

Research on facility layout optimization algorithm of deep-water semi-submersible drilling platform

We aimed to create a facility layout design of semi-submersible drilling platform (DSDP) with performance constraints. The Boltzmann survival mechanism of simulated annealing algorithm was introduced into the replacement strategy of genetic algorithm to form an improved genetic algorithm called genetic and simulated annealing algorithm (GASA). The new algorithm alleviates the “combination explosion” and premature convergence of the traditional genetic algorithm. The layout problem of DSDP is efficiently solved by using this new algorithm. When the number of layout objects increases, GASA’s performance is better than that of the genetic algorithm.

Characterizing projective geometry of binocular visual space by Möbius transformation

Binocular vision involves the projection of objects in the 3-D visual space onto the two retinae and the comparison of spatial layout of objects in these retinal half-images. Here we characterize the unitary representation of the binocular space as a complex half-plane from the perspective of the cyclopean eye. We then investigate its automorphism group, namely the Möbius transformation group, and the associated invariants when the two eye positions are treated as fixed points of the automorphism. A three-point simple ratio from an object point to both eyes is constructed; as a complex number, its angle measures the difference in azimuth of the projected rays from the object point to each eye (i.e., horizontal disparity) while its modulus measures the ratio of the distances of the object point to the two eyes (i.e., relative vertical magnification or vertical size ratio). The four-point cross-ratio of two such simple ratios, as the only four-point invariant under Möbius transforms, reflects the fact that the relative disparity between any two object points remains unchanged when the eyes change fixation. Since the complex half-plane is biholomorphically equivalent to an open unit disk, both Poincaré model and Klein–Beltrami model give rise to a hyperbolic geometry, consistent with the empirically supported Luneburg’s (1947; 1950) model of binocular geometry (for the depth plane). Finally, the hyperbolic tangent function f(z)=tanh(z), with inverse f−1(z)=12log1+z1−z, is shown to act as the psychophysical function relating the physical representation of the binocular space to its cyclopean representation.

Геометрические аспекты автоматизированной компоновки летательных аппаратов

In this paper have been considered questions related to automation of the layout for products with high layout density (primarily means of transport). It has been demonstrated how an aircraft’s geometric shape is formed on the basis of infrastructural and layout constraints. Influences of aerodynamic and internal layouts on the aircraft’s geometric shape have been described, taking into account mass-inertia characteristics of units placed in it. The layout’s reverse problem (when a required layout space is initial data for the aircraft’s geometric shape under hard infrastructure restrictions) has been presented. A project task of finding the rational parameters for the aircraft’s geometric shape as the task of multi-criterion discrete optimization has been described in a generalized form. It has been demonstrated that this task can be formulated as a search for the vector of design parameters as a multitude of admissible variants for design-and-engineering solutions. In the paper has been described a physical task formulation for automated layout as a system of restrictions on objects allocation indoor (required orientation, mutual compatibility, serviceability etc.). Mathematical task formulation for automated layout as the optimization problem has been described too. Since the allocation task is a classical geometric problem, it is necessary to develop appropriate geometric models for its solving. It has been shown that this process’s complexity is due to the complexity related to computer representation of information about geometric shape for layout objects of modern transport, especially the aerospace one. In this paper it has been shown that the abundance of models used in modern applied geometry and allowing describe geometric shapes for objects of any complexity, does not provide any solution for automated layout tasks. Possibilities of modern software have been also shown, and the reasons not allowing its direct use in the tasks of automated layout have been proved. The layout task’s mathematical formulation has been described as an optimization problem, specifying its objective function, limitations and efficiency criteria. Has been justified an approach (receptor methods and apparatus of normal equations) allowing, while creating geometric models for the automated layout, go from exhaustive options for allocation of layout objects to intellectual algorithms for automated allocation As has been shown in the paper, fractal theory is a good mathematical tool for study of rigid bodies’ surface geometry and mechanisms influencing on the obtaining surface structure.

Fast and Scalable Position-Based Layout Synthesis.

The arrangement of objects into a layout can be challenging for non-experts, as is affirmed by the existence of interior design professionals. Recent research into the automation of this task has yielded methods that can synthesize layouts of objects respecting aesthetic and functional constraints that are non-linear and competing. These methods usually adopt a stochastic optimization scheme, which samples from different layout configurations, a process that is slow and inefficient. We introduce an physics-motivated, continuous layout synthesis technique, which results in a significant gain in speed and is readily scalable. We demonstrate our method on a variety of examples and show that it achieves results similar to conventional layout synthesis based on Markov chain Monte Carlo (McMC) state-search, but is faster by at least an order of magnitude and can handle layouts of unprecedented size as well as tightly-packed layouts that can overwhelm McMC.

Selection of macroreference frames in spatial memory.

Spatial memories are often hierarchically organized with different regions of space represented in unique clusters within the hierarchy. Each cluster is thought to be organized around its own microreference frame selected during learning, whereas relationships between clusters are organized by a macroreference frame. Two experiments were conducted in order to better understand important characteristics of macroreference frames. Participants learned overlapping spatial layouts of objects within a room-sized environment before performing a perspective-taking task from memory. Of critical importance were between-layout judgments thought to reflect the macroreference frame. The results indicate that (1) macroreference frames characterize overlapping spatial layouts, (2) macroreference frames are used even when microreference frames are aligned with one another, and (3) macroreference frame selection depends on an interaction between the global macroaxis (defined by characteristics of the layout of all learned objects), the relational macroaxis (defined by characteristics of the two layouts being related on a perspective-taking trial), and the learning view. These results refine the current understanding of macroreference frames and document their broad role in spatial memory.

Video Generation From Text

Generating videos from text has proven to be a significant challenge for existing generative models. We tackle this problem by training a conditional generative model to extract both static and dynamic information from text. This is manifested in a hybrid framework, employing a Variational Autoencoder (VAE) and a Generative Adversarial Network (GAN). The static features, called "gist," are used to sketch text-conditioned background color and object layout structure. Dynamic features are considered by transforming input text into an image filter. To obtain a large amount of data for training the deep-learning model, we develop a method to automatically create a matched text-video corpus from publicly available online videos. Experimental results show that the proposed framework generates plausible and diverse short-duration smooth videos, while accurately reflecting the input text information. It significantly outperforms baseline models that directly adapt text-to-image generation procedures to produce videos. Performance is evaluated both visually and by adapting the inception score used to evaluate image generation in GANs.

Human performance and strategies while solving an aircraft routing and sequencing problem: an experimental approach

As airport resources are stretched to meet increasing demand for services, effective use of ground infrastructure is increasingly critical for ensuring operational efficiency. Work in operations research has produced algorithms providing airport tower controllers with guidance on optimal timings and sequences for flight arrivals, departures, and ground movement. While such decision support systems have the potential to improve operational efficiency, they may also affect users’ mental workload, situation awareness, and task performance. This work sought to identify performance outcomes and strategies employed by human decision makers during an experimental airport ground movement control task with the goal of identifying opportunities for enhancing user-centered tower control decision support systems. To address this challenge, thirty novice participants solved a set of vehicle routing problems presented in the format of a game representing the airport ground movement task practiced by runway controllers. The games varied across two independent variables, network map layout (representing task complexity) and gameplay objective (representing task flexibility), and verbal protocol, visual protocol, task performance, workload, and task duration were collected as dependent variables. A logistic regression analysis revealed that gameplay objective and task duration significantly affected the likelihood of a participant identifying the optimal solution to a game, with the likelihood of an optimal solution increasing with longer task duration and in the less flexible objective condition. In addition, workload appeared unaffected by either independent variable, but verbal protocols and visual observations indicated that high-performing participants demonstrated a greater degree of planning and situation awareness. Through identifying human behavior during optimization problem solving, the work of tower control can be better understood, which, in turn, provides insights for developing decision support systems for ground movement management.

High-Acuity Information Is Retained through the Cortical Visual Hierarchy of Primates

Vision requires perception of both coarse layout and fine details of objects. In this issue of Neuron, Lu etal. (2018) describe a possible basis for the latter: neuronal clusters in area V4 coding high-acuity information, despite the tendency along the visual hierarchy to generate global representations of objects.

StereoEditor: controllable stereoscopic display by content retargeting

We report a stereoscopic editing method, named as StereoEditor, to achieve controllable stereoscopic display. By taking content-aware, depth-adaptive and object-selective retargeting into account, the resolution, depth and object of stereoscopic input are simultaneously edited to create flexible stereoscopic output. The retargeting semantics from retinal disparity limits, viewing distance, and object’s scaling factors can be adjusted flexibly to achieve particular stereoscopic display, which can be controlled by user’s preference and practical viewing conditions. Compared with previous methods, our method can achieve a better tradeoff among shape preservation, depth control and object layout, leading to promising viewing experience.

Automated Decision Making in the Problem Solving of Objects Layout for Chemical and Refining Industries Using Expert Software Systems

In this paper, mathematical modeling of objects layout is considered for the phase of construction engineering of industrial facilities. The authors propose a new approach that allows to define the problem and to automatically create a mathematical layout model of the industrial facilities. The approach is based on a method of generating and controlling the limitations of the mathematical layout model. The distinctive feature of this method is the possibility to add new restrictions and to consider them in the process of layout calculations without changing the code. The proposed approach has been tested in solving practical problems of designing layouts of industrial facilities.

Review of Methods for Synthesis of the Model of Class of Spiroid Gearboxes for Intelligent CAD Systems. Part 1. Graph Method

Создание интеллектуальных систем автоматизации конструирования требует решения задачи накопления и обобщения конструкторского опыта. Разработка модели конструкторской деятельности сталкивается с отсутствием сквозного алгоритма, позволяющего синтезировать конструкцию, имея в качестве исходных данных потребительские качества изделия. Именно этим объясняется функциональный набор современных САПР, которые способны автоматизировать процессы выполнения графических работ, строить трехмерные модели, выполнять отдельные инженерные расчеты, готовить конструкторскую и технологическую документацию, однако не позволяют выполнить структурный синтез будущего изделия. Решающим фактором в реализации процесса структурного синтеза становятся опыт конструктора и его интуиция. Автор статьи, разрабатывая методологию автоматизации процесса структурного синтеза, ставит вопрос о накоплении «конструкторского опыта» для его дальнейшего использования в качестве информационного обеспечения системы автоматизированного конструирования, способной максимально автоматизировать процесс структурного синтеза будущей конструкции. Обобщение опыта рассматривается автором как формирование модели класса объектов, позволяющей зафиксировать максимальное количество особенностей конструктивных исполнений изделия и его компонентов. Еще одна задача, которая должна быть решена при создании модели класса объектов, - это обеспечение возможности ее автоматизированной реализации. В качестве модели класса объектов автор предлагает использовать классификатор, представляющий собой набор классификационных признаков (вопросов) и множество значений признаков (альтернативных ответов на каждый из поставленных вопросов). В качестве объекта конструирования рассмотрен спироидный редуктор, представляющий собой объект средней степени сложности. Графовое представление конструкции объекта, позволяющее продемонстрировать все конструктивные единицы, обладающие определенными, интересующими конструктора свойствами, является наглядным и удобным для математического, а следовательно, алгоритмического описания. В статье обоснована необходимость и возможность создания классификатора в качестве обобщенной модели класса спироидных редукторов, построенной графовым методом, состоящим в обобщении графовых моделей отдельных конструктивных решений. Автором рассмотрен графовый метод Половинкина, обоснована необходимость его модификации, предложен графовый метод, обеспечивающий высокую степень автоматизации процесса обобщения конструкторского опыта и создания классификатора.

Geografis Information System Sebagai Media Informasi Persebara Benda – Bendayang Bernilai Budaya Dan Sejarah Di Sumatera Selatan

From the existence of objects - objects of value culture and history, especially the statues in South Sumatra Province is quite a lot in various areas in the South Sumatra. But until now there is no geographic description of the layout of objects - objects that are valuable cultural and historical especially the statues in South Sumatra. The purpose of this study is to establish a web-based geographic information system regarding the distribution of the statues so that users can access information via the Internet and direct berintraksi with the system. The system provides several tools that can be used to berintraksi with map information, zoom in, zoom out. In general, this WebGIS can help the community, and students in search of locations - locations spread of statues in South Sumatra.

ANALISIS VISUAL SAMPUL MAJALAH “BOBO” EDISI BULAN APRIL 2016

Bobo Magazine is one of children’s magazine which is still exsisted from 1974 until now. Their cover has its own uniqueness. This research was aimed at identifying visual layout of Bobo Magazine, finding the quality of element’s design and visuals elements. The research method is qualitative approach which are collected from observation results, documentation and library research. The object of research was Bobo’s magazine cover of April edition, 2016. The data analysis used to analyze visualization quality was the theory of Tom Lincy about five principal design on printed works, such as proportion, balance, contrast, rhyme, and unity. From the visual data analysis it was found that layout composition from illustration, texts/letter, and colour on cover has applied the principles of unity, balance, rhyme, contrast and proportion. The visual’s fascination is unique, different from others, because it was supported by the use of Bobo’s family characters as icons, the use of bright pastel colours, the use of exact San Serif letters and dynamic layout of objects

Rapid three-dimensional scene modeling by sketch retrieval and auto-arrangement

The existing three-dimensional (3D) object layout methods are focused mainly on indoor scenes and they are limited for outdoor applications. In this study, we propose a data-driven method for outdoor scene modeling by using fast retrieval and automatic optimization layout techniques. Unlike the current methods, we first employ an improved manifold ranking algorithm in the sketch-based 3D model retrieval stage, which achieves higher accuracy. Next, according to the particular properties of outdoor architectures, specialized constraints are then proposed to define an energy function, which meets both the functional and aesthetic requirements. Finally, we cast the auto-arrangement as a combinatorial optimization problem, which we solve using an optimization algorithm. In contrast to the earlier version of this method, which was presented at Cyberworlds 2016, this extended version combines simulated annealing and particle swarm optimization algorithms, which have the advantages of rapid convergence and avoiding becoming trapped by local minima. Our experimental results demonstrate that the proposed method is more intuitive and effective for modeling 3D scenes, and can be employed in the actual development of game scenes.

Creativity of third graders’ leadership cartoons: Comparison of mood-enhanced to neutral conditions

Research on mood related to subsequent creativity is sparse for samples of children. The current study was conducted to determine the effects of positive mood induction through upbeat music and simulated laughter on creativity. Fourteen gifted third grade students (9 female, 5 male; 10 White, 3 African American, 1 Native American; aged 8–9 years) from a low-socio-economic urban public school in the Midwest participated in the repeated-measures study with two trials in the control and two trials in the experimental conditions. Each lesson began with wordplay work in making a layout of word cards, definition cards, and objects to show homophone or words with multiple meanings concepts. Students analyzed humorous cartoons related to leadership that the researchers had made. Finally, students used paper images and wrote in speech bubbles to create their own leadership cartoons. During the experimental condition, two mood-lifting activities were added: students listened to a couple of minutes of upbeat instrumental music as they gathered for the class and later, before cartoon production occurred, they participated in simulated laughter for thirty seconds. Results showed that cartoons produced during the experimental condition contained more humor, were more original, and had greater fluency of speech or thought bubbles with very large, large, and medium effect sizes respectively. Greater creativity is attributed to positive mood allowing more working memory for complex synthesis of ideas, recognition of more diverse ideas, and a safe environment for taking creative risks.