Search

Reconstruction of 3D space from visual data has always been a significant challenge in the field of computer vision. A popular approach to address this problem can be found in the form of bottom-up reconstruction techniques which try to model complex 3D scenes through a constellation of volumetric primitives. Such techniques are inspired by the current understanding of the human visual system and are, therefore, strongly related to the way humans process visual information, as suggested by recent visual neuroscience literature. While advances have been made in recent years in the area of 3D reconstruction, the problem remains challenging due to the many possible ways of representing 3D data, the ambiguity of determining the shape and general position in 3D space and the difficulty to train efficient models for the prediction of volumetric primitives. In this article, we address these challenges and present a novel solution for recovering volumetric primitives from depth images. Specifically, we focus on the recovery of superquadrics, a special type of parametric models able to describe a wide array of 3D shapes using only a few parameters. We present a new learning objective that relies on the superquadric (inside-outside) function and develop two learning strategies for training convolutional neural networks (CNN) capable of predicting superquadric parameters. The first uses explicit supervision and penalizes the difference between the predicted and reference superquadric parameters. The second strategy uses implicit supervision and penalizes differences between the input depth images and depth images rendered from the predicted parameters. CNN predictors for superquadric parameters are trained with both strategies and evaluated on a large dataset of synthetic and real-world depth images. Experimental results show that both strategies compare favourably to the existing state-of-the-art and result in high quality 3D reconstructions of the modelled scenes at a much shorter processing time.

Quantitative approaches for the integration of production and distribution planning are attracting the interest of scholars and companies in recent years. They can significantly improve supply chain performance and sustainability. In this paper, we propose an optimization model for the integrated scheduling of production and distribution activities, with reference to a real-life company in the food sector. The model takes into consideration changeover times and perishability, and aims to jointly minimize energy, storage and distribution costs. Its applicability is shown through a set of computational experiments, carried out on instances generated from historical data. Two different rescheduling strategies, where the first one reproduces the current behaviour of the firm, are compared. The results show that the current practices of the company can be improved and the model is a valid tool for supporting operational business decisions.

Coordination of the production and distribution activities represents a significant opportunity to cut costs and limit waste in the food supply chains. In this paper, we propose two mathematical models. The first one aims to integrate the harvesting, storage, and distribution activities of an agricultural company dealing with perishable products. The second one promotes horizontal collaboration between heterogeneous agri-companies for the distribution phase, in order to achieve cost savings. Computational experiments, conducted on a set of real-life instances, confirm the effectiveness and efficiency of the proposed models, which provide multi-level support. At the tactical level, managerial insights suggest the most profitable parameter setting, in terms of harvesting frequency and quality of service. At the operational level, the use of a heuristic framework can support the decision-making of the companies, suggesting when collaboration is profitable.

Global corporations are characterized by a large number of employees and geographically dispersed offices. Moreover, the competitiveness in the global market requires them to invest in their human resources to be able to remain a step ahead of competition. Implementing large scale classical education in such environments is challenging and costly. Mobile e-learning (m-learning) allows users to tailor their professional training and education to their needs and time constraints. However, in self-paced education, it is very hard to keep user retention and engagement. To achieve the latter, we have designed and developed an m-learning platform for corporate environments based on the triggering persuasive technology principle that try to incite users in regularly using the platform. We have evaluated the application in-the-wild in corporate environments of differently sized companies with 300 users. Users were subjected to three different conditions: no triggering, simple regular triggering, and adaptive triggering. The results show that the use of adaptive triggering in m-learning increases user engagement as well as course completion rates more than simple regular triggering and no triggering.

When people talk to each other, eye contact is very important for a trustful and efficient communication. Video-conferencing systems were invented to enable such communication over large distances, recently using mostly Internet and personal computers. Despite low cost of such solutions, a broader acceptance and use of these communication means has not happened yet. One of the most important reasons for this situation is that it is almost impossible to establish eye contact between distant parties on the most common hardware configurations of such videoconferencing systems, where the camera for face capture is usually mounted above the computer monitor, where the face of the correspondent is observed. Different hardware and software solutions to this problem of missing eye contact have been proposed over the years. In this article we propose a simple solution that can improve the subjective feeling of eye contact, which is based on how people perceive 3D scenes displayed on slanted surfaces, and offer some experiments in support of the hypothesis.

Pharmaceutical supply chains are very complex and characterized by many actors, who want to maximize their respective revenue. Except for special cases, wholesale distributors are usually in the middle between pharmaceutical manufacturers and retailers. Their role is then crucial for the efficiency of the entire chain. This work mainly aims to support a pharmaceutical wholesaler in the vehicle fleet organization. A quantitative approach is proposed, whose validity is confirmed by the application to a case study in Calabria, a region in South Italy. Studying and optimizing the distribution of medicines means cutting costs and guaranteeing an adequate service level to pharmacies. Ensuring the availability of medicines at any time of the day guarantees the satisfaction of final consumer, who moves this market.

It has been a longstanding goal in computer vision to describe the 3D physical space in terms of parameterized volumetric models that would allow autonomous machines to understand and interact with their surroundings. Such models are typically motivated by human visual perception and aim to represents all elements of the physical word ranging from individual objects to complex scenes using a small set of parameters. One of the de facto stadards to approach this problem are superquadrics - volumetric models that define various 3D shape primitives and can be fitted to actual 3D data (either in the form of point clouds or range images). However, existing solutions to superquadric recovery involve costly iterative fitting procedures, which limit the applicability of such techniques in practice. To alleviate this problem, we explore in this paper the possibility to recover superquadrics from range images without time consuming iterative parameter estimation techniques by using contemporary deep-learning models, more specifically, convolutional neural networks (CNNs). We pose the superquadric recovery problem as a regression task and develop a CNN regressor that is able to estimate the parameters of a superquadric model from a given range image. We train the regressor on a large set of synthetic range images, each containing a single (unrotated) superquadric shape and evaluate the learned model in comparaitve experiments with the current state-of-the-art. Additionally, we also present a qualitative analysis involving a dataset of real-world objects. The results of our experiments show that the proposed regressor not only outperforms the existing state-of-the-art, but also ensures a $270\times$ faster execution time.

Problematika pembelajaran daring pada masa pandemi COVID-19 adalah ketidaksusaian lingkungan dengan mengubah kebiasaan lama sehingga orang tua melakukan berbagai cara agar orang tua bisa memberikan perilaku yang positif terhadap anak. Tulisan ini fokus pada model perilaku positif pada orang tua dimana peran orang tua sangat penting bagian dari pembelajaran daring oleh anak ditengah ketidakpastian pandemi COVID-19 berakhir. Adapun metode dalam tulisan ini adalah studi kepustakaan atau kajian literatur tentang perilaku positif dengan analisis model logika. Hasil menunjukan bahwa faktor yang mempengaruhi perilaku positif orang tua kepada anak dalam pembelajaran daring ditengah pandemi COVID-19 harus memenuhi unsur percaya diri, harapan, optimisme, ketahanan dan kecerdasan orang tua dalam menyikapi pembelajaran daring dilakukan oleh anaknya. Selain itu modal sosial sebagai alternatif memperkuat perilaku positif orang tua terhadap anak agar rasa nyaman atas kehadiran orang tua untuk mendampingi pembelajaran daring.

The need to model visual information with compact representations has existed since the early days of computer vision. We implemented in the past a segmentation and model recovery method for range images which is unfortunately too slow for current size of 3D point clouds and type of applications. Recently, neural networks have become the popular choice for quick and effective processing of visual data. In this article we demonstrate that with a convolutional neural network we could achieve comparable results, that is to determine and model all objects in a given 3D point cloud scene. We started off with a simple architecture that could predict the parameters of a single object in a scene. Then we expanded it with an architecture similar to Faster R-CNN, that could predict the parameters for any number of objects in a scene. The results of the initial neural network were satisfactory. The second network, that performed also segmentation, still gave decent results comparable to the original method, but compared to the initial one, performed somewhat worse. Results, however, are encouraging but further experiments are needed to build CNNs that will be able to replace the state-of-the-art method.

Patient admission and surgery scheduling is a complex combinatorial optimization problem. It consists on defining patient admission dates, assigning them to suitable rooms, and schedule surgeries accordingly to an existing master surgical schedule. This problem belongs to the class of NP-hard problems. In this paper, we firstly formulate an integer programming model for offline patient admissions, room assignments, and surgery scheduling; then apply a matheuristic that combines exact methods with rescheduling approaches. The matheuristic is evaluated using benchmark datasets. The experimental results improve those reported in the literature and show that the proposed method outperforms existing techniques of the state-of-the-arts.

Patient admission scheduling problems consist in deciding which patient to admit and at what time. More complex problems address also bed assignment problems at the same time. The complexity of the problem motivates researchers to design suitable approaches to support bed managers in making decisions. The aim of this paper is to define an efficient model formulation for the offline elective patient admission scheduling problem, which defines admission dates and assigns patients to rooms. Due to the multiobjective nature of the problem, we suggest how to set weight values, used to penalise constraint violations. These values are tested on a set of benchmark instances. Improvements in schedule quality are presented.

This paper presents a literature review about the application of blockchain-based systems in transportation. The main aim was to identify, through the implementation of a multi-step methodology: current research-trends, main gaps in the literature, and possible future challenges. First, a bibliometric analysis was carried out to obtain a broad overview of the topic of interest. Subsequently, the most influential contributions were analysed in depth, with reference to the following two areas: supply chain and logistics; road traffic management and smart cities. The most important result is that the blockchain technology is still in an early stage, but appears extremely promising, given its possible applications within multiple fields, such as food track and trace, regulatory compliance, smart vehicles’ security, and supply-demand matching. Much effort is still necessary for reaching the maturation stage because several models have been theorized in recent years, but very few have been implemented within real contexts. Moreover, the link blockchain-sustainability was explored, showing that this technology could be the trigger for limiting food waste, reducing exhaust gas emissions, favouring correct urban development, and, in general, improving quality of life.

The Internet offers a powerful network of information on breastfeeding that is used by doctors, patients, and scientists. The objective of this study is to describe the process of development of a data extraction tool to evaluate the content and quality of breastfeeding information on the Internet. Using a descriptive study method, we examined Internet pages to determine which variables needed to be measured in order to develop the data extraction tool. A purposive sampling of websites was selected to pilot test this tool. The developed data extraction tool has a descriptive structure to characterize websites and text pages. Using the developed tool, we can assess whether the information on text pages is supportive of breastfeeding and whether other strategies that protect breastfeeding are followed. The developed data extraction tool is a useful instrument that can assist researchers in evaluating the quality of information posted on the Internet related to breastfeeding.

We present a quantitative study of digital signage audience measurement using computer vision. We developed a camera-enhanced digital signage display that acquires audience measurement metrics with computer vision algorithms. Temporal metrics of a person’s dwell time, display in-view time and attention time are extracted. The system also determines demographic metrics of the gender and age group. The digital signage display was deployed in a real-world environment of a clothing boutique, where demographic and viewership data of 1294 store customers were recorded, manually verified and analysed. The analysis shows that 35% of customers specifically looked-at the display, having the average attention time of 0.7 s. Interestingly, the attention time was substantially higher for men (1.2 s) than for women (0.4 s). Age group comparison reveals that children (1–14 years) are the most responsive to the digital signage. Finally, the analysis shows that the average attention time is significantly higher when displaying the dynamic content (0.9 s) when compared with the static content (0.6 s).

The realization of a new access network for Telecom Italia has the objective to increase bandwidth capacity for the final user, enabling new services through the adoption of evolved and managed technologies. This article describes the present status of the network and the evolutionary trends.

Purpose– The purpose of this paper is to set an example of how people with severe learning difficulties could be more integrated into our society.Design/methodology/approach– The installation consists of puzzles in the form of a specially designed table with an integrated touch screen. As the visual templates for the puzzles serve pictures painted by a person with severe learning difficulties. The pieces of the puzzles are manipulated directly by the player on the touch screen presenting an intuitive and easily learned user interface.Findings– The framework for the work was a creation of an interactive art installation in the form of a game where users assemble puzzles on a touch monitor, housed in a specially designed table. Paintings by a person with severe learning difficulty served as visual templates for the puzzles. The pieces of the puzzles can be manipulated directly by the user on a touch screen presenting an intuitive and easily learned user interface, which stimulates the learning of fine motor skills and encourages practice, thus making it suitable for persons with severe learning difficulties in an art therapy setting.Practical implications– As the work has the format of an interactive art installation, this enables it to gain publicity through exhibitions in art galleries.Social implications– The installation demonstrates how people with severe learning difficulties can be integrated into the broader society. At the same time, these people are encouraged to use modern computer information technology, which is becoming a necessity also for this group of users. Ethical issues regarding how this group of people can get involved in such work are also discussed.Originality/value– Combining the habituation of people with severe learning difficulties with computer technology in the form of a game, and framing the whole process as a fine art undertaking, to win the public recognition, is a novelty in addressing the needs of these people.

A simple and fast method of determining the position of the optical center without any specialized equipment is presented. The position of the optical center is a depth determining parameter in a panoramic depth imaging system [Peer, P., Solina, F., 2002. Panoramic depth imaging: single standard camera approach. Internat. J. Comput. Vision 47 (1/2/3), 149-160; Peer, P., Solina, F., 2005. Multiperspective panoramic depth imaging. In: Computer Vision and Robotics. Nova Science Publishers]. The reconstructed distances correspond well to the actual measured distances on the scene. ne.

In this paper we present a panoramic depth imaging system. The system is mosaic-based which means that we use a single rotating camera and assemble the captured images in a mosaic. Due to a setoff of the camera's optical center from the rotational center of the system we are able to capture the motion parallax effect which enables stereo reconstruction. The camera is rotating on a circular path with a step defined by the angle, equivalent to one pixel column of the captured image. The equation for depth estimation can be easily extracted from the system geometry. To find the corresponding points on a stereo pair of panoramic images the epipolar geometry needs to be determined. It can be shown that the epipolar geometry is very simple if we are doing the reconstruction based on a symmetric pair of stereo panoramic images. We get a symmetric pair of stereo panoramic images when we take symmetric pixel columns on the left and on the right side from the captured image center column. Epipolar lines of the symmetrical pair of panoramic images are image rows. The search space on the epipolar line can be additionaly constrained. The focus of the paper is mainly on the system analysis. Results of the stereo reconstruction procedure and quality evaluation of generated depth images are quite promissing. The system performs well for reconstruction of small indoor spaces. Our finall goal is to develop a system for automatic navigation of a mobile robot in a room.

In contemporary digital art computer technology plays an integral part not only in the creation of art pieces but also in their functioning as artworks. Such digital artworks have usually a performative or interactive character and therefore rely on an underlying working computer system. Since computer technology advances with such unrelenting pace, hardware and software modules eventually become obsolete. How to preserve digital art works in these circumstances from an art preservation standpoint is much debated. In this article we discuss issues in the preservation of digital art works using as a case study a 15 years old interactive art installation '15 seconds of fame'. The art installation could be maintained in a good working order first just by small changes, reacting mainly to new versions of operating systems. After more then ten years a complete rewrite of the code was necessary to move it to a new computing platform.

A classical or static anamorphic image requires a specific, usually a highly oblique view direction, from which the observer can see the anamorphosis in its correct form. This paper explains dynamic anamorphosis which adapts itself to the changing position of the observer so that wherever the observer moves, he sees the same undeformed image. This dynamic changing of the anamorphic deformation in concert with the movement of the observer requires from the system to track the 3D position of the observer’s eyes and the re-computation of the anamorphic deformation in real time. This is achieved using computer vision methods which consist of face detection and tracking the 3D position of the selected observer. An application of this system of dynamic anamorphosis in the context of an interactive art installation is described. We show that anamorphic deformation is also useful for improving eye contact in videoconferencing. Other possible applications involve novel user interfaces where the user can freely move and observe perspectively undeformed images.

We present an approach to reliable and efficient recovery of part-descriptions in terms of superquadric models from range data. We show that superquadrics can directly be recovered from unsegmented data, thus avoiding any presegmentation steps (e.g. in terms of surfaces). The approach is based on the recover-and-select paradigm. We present several experiments on real and synthetic range images, where we demonstrate the stability of the results with respect to viewpoint and noise.

The article describes technical and user-interface issues of transferring the contents and functionality of the CD-ROM version of the Slovenian sing language dictionary to the web. The dictionary of Slovenian sign language consist of video clips showing the demonstra- tion of signs that deaf people use for communication, text description of the words corresponding to the signs and pictures illustrating the same word/sign. A new technical solution—a video sprite—for concatenating subsections of video clips necessary for their smooth display on most available platforms was developed. The contents of the dictionary which were re-edited are combined also with other resources available on the web. Added were also new exercises for learning the sign language.

In this paper we present the development of an interactive, content-aware and cost-effective digital signage system. Using a monocular camera installed within the frame of a digital signage display, we employ real-time computer vision algorithms to extract temporal, spatial and demographic features of the observers, which are further used for observer-specific broadcasting of digital signage content. The number of observers is obtained by the Viola and Jones face detection algorithm, whilst facial images are registered using multi-view Active Appearance Models. The distance of the observers from the system is estimated from the interpupillary distance of registered faces. Demographic features, including gender and age group, are determined using SVM classifiers to achieve individual observer-specific selection and adaption of the digital signage broadcasting content. The developed system was evaluated at the laboratory study level and in a field study performed for audience measurement research. Comparison of our monocular localization module with the Kinect stereo-system reveals a comparable level of accuracy. The facial characterization module is evaluated on the FERET database with 95% accuracy for gender classification and 92% for age group. Finally, the field study demonstrates the applicability of the developed system in real-life environments.

Educational Possibilities of the Project Colour Visualization of Music We propose a system of colour visualization of music based on a system of colour signs, which are connected to musical tones. Tones, which are in harmonic relationships, are represented by related colours. First, we outline the foundations on which the system of colour signs is based - the mathematical model of harmony. We discuss several possibilities of visual representation of expressive elements of music - melody, composition, rhythm and harmony. These relationships enabled us to develop a computer program that employs these elements for visualization. The program mimics human perception in which the parts are determined by the perception of the whole. Furthermore, the program enables the development of tools that can enhance music understanding during listening or performing. Music performance can acquire a new quality with the use of interactive coloured musical instruments, which by using colours show the performer different possibilities for forming musical harmonies and thereby change the composing of music into a game and attractive colour-aural journey. Here we stumble upon a challenge for educational science and methodology: how to use such upcoming multimedia tools. These tools would bring the processes of learning and playing a game closer together since playing games is a child's most natural form of functioning. Furthermore, in the area of artistic creation we can once again establish a balance between our logical and intuitive nature.

We describe an interactive system for content based image retrieval. The system presents the user with 15 randomly selected images from the database. The user grades the images with one of five possible grades (YES, yes, neutral, no, NO) according to what he is looking for. The system returns the first 15 images with the highest probability of YES grade. The attributes used are a combination of color features. Three different machine learning techniques are compared.

In the mixed reality of the computer installation Presence, which functions as a prototype for a smart space, the visitor is placed in the position of a person in audience with the king. The interaction with a digital avatar is structured according to the rules of social behaviours and following the script of the Shakespeare’s play. The paper explains different aspects of the conceptualisation of an interdisciplinary collaboration between artists and computer engineers.

In this paper we are trying to establish a framework for natural and man-made scene differentiation based on perspective geometrical properties of the scenes. Although, we have not jet achieved expected results with built classifier, evidence of distinguishing attributes exists and some of them are introduced in this paper.

Over the years building models of objects from sensory data has been tackled in various ways. Following [1], model based recognition methods are divided into graph theoretic and non graph theoretic. Graph theoretic methods use graphs as a representation for objects and scenes. An object is divided into parts. Nodes of a graph that describes an object characterize the parts of the object and arcs of the graph represent spatial relations among parts of the object. Recognition of an object in the scene is performed as search for a subgraph isomorphism between the scene graph and each of the model graphs. In non graph theoretic methods, local features are used to describe the object. Grimson and Lozano-Peres [3], used a constrained tree search to efficiently coordinate values of point features and surface normals in models to those found in the scenes.

Segmentation with Volumetric Part Models. Volumetric models are top-level shape representation in computer vision applications. Volumetric models are especially suited for part-level representation on which manipulation, recognition and other reasoning can be based. The two most popular types of volumetric models in computer vision are generalized cylinders and superquadrics. This paper gives an overview of recovery and segmentation methods applying these two types of volumetric models. Methods of segmentation into parts are analyzed and advantageous properties of part-models discussed.

This paper proposes a technique for object recognition using superquadric built models. Superquadrics, which are three-dimensional models suitable for part-level representation of objects, are reconstructed from range images using the recover-and-select paradigm. Using interpretation trees, the presence of an object from the model database can be hypothesized. These hypotheses are verified by projecting and re-fitting the object model to the range image of the scene which at the same time enables a better localization of the object in the scene.

Computer vision is one out of many areas that wants to understand the process of human functionality and copy that process with intention to complement human life with intelligent machines. For better human–computer interaction it is necessary for the machine to see people. This can be achieved by employing face detection algorithms, like the one used in the installation “15 Seconds of Fame”. Mentioned installation unites the areas of modern art and technology. Its algorithm is based on skin colour detection. One of the problems this and similar algorithms have to deal with is sensitivity to the illumination conditions under which the input image is captured. Hence illumination sensitivity influences face detection results. One of the aspects from which we can observe illumination influence is the choice of the proper colour space. Since some colour spaces are designed to eliminate the influence of illumination (brightness) when describing colour of an object, an idea of using such a colour space for skin-colour detection has been taken under consideration and some of the methods have been researched and tested.

Computer vision is one out of many areas that want to understand the process of human functionality and copy that process with intention to complement human life with intelligent machines. For better human-computer interaction it is necessary for the machine to see people. This can be achieved by employing face detection algorithms, like the one used in the installation "15 Seconds of Fame" (F. Solina et al., 2002). Mentioned installation unites the areas of modern art and technology. Its algorithm is based on skin-color detection. One of the problems this and similar algorithms have to deal with is sensitivity to the illumination conditions under which the input image is captured. Hence illumination sensitivity influences face detection results. This problem is being more or less successfully solved by the use of color compensation and color constancy methods. In this work some of these methods are described, realized and tested. Their basic intention is to eliminate the influence of non-standard illumination from images. Tests that were performed showed that methods apply positive influence on face detection results.

We have designed a system with an intuitive user interface for remote camera control and image-based queries over the Internet. While searching for present solutions we realized the importance of a well-designed user interface. We developed a system, which enables remote observation and remote control of the JVC network camera over the Internet. The user interface is based on the combination of live video and a static panoramic view of a remote location. It provides a complete overview of a remote location and significantly simplifies the control over the Internet. By interactively moving a rectangular frame in the panoramic picture, the user locally selects the new direction of the camera. Visual summaries of activities at the observed location can be generated as well as custom queries with a simple user interface over the Internet.

The conventional least squared distance method of fitting a model to a set of data points gives unreliable results when the amount of noise in the input is significant compared with the amount of data correlated to the model itself. The theory of robust statistics formally addresses these problems and is used in this work to develop a method of separation of the data of interest from noise. It is based on iteratively reweighted least squares algorithm where Hampel redescending function is applied for weighting data. The method has been efficiently tested in modeling synthetic and real 2D image data with second order curves. >

An algorithm is proposed for the detection and separation of specularity from Lambertian reflectance using multiple image frames from different viewpoints. The algorithm is based on the physical model of the multiple reflection mechanism in which the appearance of specularity varies depending on viewing direction while that of Lambertian reflection does not. The approach is to move camera sensors actively and to obtain as many image frames as possible. Experimental results are presented to show the efficiency of the algorithm. >

This paper proposes a technique for object recognition using superquadric built models. Superquadrics, which are three dimensional models suitable for part-level representation of objects, are reconstructed from range images using the recover-and-select paradigm. Using an interpretation tree, the presence of an object in the scene from the model database can be hypothesized. These hypotheses are verified by projecting and re-fitting the object model to the range image which at the same time enables a better localization of the object in the scene.

"15 seconds of fame" is an interactive art installation, which elevates the face of a randomly selected gallery visitor for 15 seconds into a "work of art". The installation was inspired by Andy Warhol's statement that "In the future everybody will be world famous for fifteen minutes" as well as by the pop-art style of his works. The installation consists of a computer with a flat-panel monitor, a digital camera and a proprietary software that can detect human faces in images and graphically transform them. In this paper we present the technical background of the installation, in particular, how computer vision techniques were applied in this art installation.

In the doctoral thesis we developed an interactive and user-adaptive information interface based on computer vision and machine learning methods. By using a camera-enhanced digital signage display we employed real-time computer vision algorithms to extract temporal, spatial, and demographic features of the observers, which are further used for observer specific broadcasting of digital signage contents. The algorithms were chosen and modified to optimize the balance between accuracy and time complexity, subjected to design-aim to perform in real-time and using conventional hardware. More particularly, we used the Mixture of Gaussians method for background segmentation, Viola & Jones method for face detection algorithm, Active Appearance Models for face alignment and POSIT algorithm for head pose estimation. The developed interface is used as the key research tool to explore three currently open problems in the field of human-computer interaction: dynamic anamorphosis, quantitative audience measurement study of digital signage in real-world environment, and modeling of the purchase decision process. In the first study, we developed a new interactive computer vision based method which adapts image projection to the changing position of the observer so that wherever the observer moves, he sees the same undeformed image. We call this capacity dynamic anamorphosis. We formalized the anamorphic transformation and proposed a real-time algorithm for tracking the 3D position of the observer's eyes and the re-computation of the anamorphic deformation. As an interesting application, we show that dynamic anamorphosis could be used to improve eye-contact in videoconferencing. In the second study, we used the developed interface to perform a quantitative audience measurement field study, which evaluates user attention. Temporal metrics of a person's dwell time, display in-view time and attention time are extracted using real-time image analysis. The system also determines demographic metrics of the gender and age group based on images of faces. The digital signage display was deployed in a real-world environment of a clothing boutique, where demographic and viewership data of 1294 store customers were recorded, manually verified and analysed. The analysis shows that 35% of customers specifically looked-at the display, having the average attention time of 0.7 s. Interestingly, the attention time was substantially higher for men (1.2 s) than for women (0.4 s). In the third study, the interface is applied to model the purchase decision process, which is an interdisciplinary study, where data collected with the developed interface and subjected to machine learning are combined to model and analyze the decision and roles in a purchasing process. Finally, more generally, the developed system presents a contribution to the field of human-computer interaction and shows further possibilities for scientific use and applications, such as open problem of display blindness, development of new interactive methods for broadcasting of relevant content, and quantitative analysis of user behavior.

Deaf people, as a marginal community, may have severe problems in communicating with hearing people. Usually, they have a lot of problems even with such—for hearing people—simple tasks as understanding the written language. However, deaf people are very skilled in using a sign language, which is their native language. A sign language is a set of signs or hand gestures. A gesture in a sign language equals a word in a written language. Similarly, a sentence in a written language equals a sequence of gestures in a sign language. In the distant past deaf people were discriminated and believed to be incapable of learning and thinking independently. Only after the year 1500 were the first attempts made to educate deaf children. An important breakthrough was the realization that hearing is not a prerequisite for understanding ideas. One of the most important early educators of the deaf and the first promoter of sign language was Charles Michel De L’Epée (1712-1789) in France. He founded the fist public school for deaf people. His teachings about sign language quickly spread all over the world. Like spoken languages, different sign languages and dialects evolved around the world. According to the National Association of the Deaf, the American Sign Language (ASL) is the third most frequently used language in the United States, after English and Spanish. ASL has more than 4,400 distinct signs. The Slovenian sign language (SSL), which is used in Slovenia and also serves as a case study sign language in this chapter, contains approximately 4,000 different gestures for common words. Signs require one or both hands for signing. Facial expressions which accompany signing are also important since they can modify the basic meaning of a hand gesture. To communicate proper nouns and obscure words, sign languages employ finger spelling. Since the majority of signing is with full words, signed conversation can proceed with the same pace as spoken conversation.

In this article, we present a panoramic depth imaging system. The system is mosaic-based which means that we use a single rotating camera and assemble the captured images in a mosaic. Due to an offset of the camera's optical center from the rotational center of the system, we are able to capture the motion parallax effect which enables stereo reconstruction. The camera rotates on a circular path with the step defined by an angle equivalent to one column of the captured image. The equation for depth estimation can be easily extracted from the system geometry. To find the corresponding points on a stereo pair of panoramic images the epipolar geometry needs to be determined. We focused mainly on the system analysis. The system performs well in the reconstruction of small indoor spaces.

This Phase I Strategic Technology Transfer Report (STTR) final report summarizes the development of a prototype interactive software environment, SpecLab, for analyzing non-stationary processes that admit local power-law representations. Standard spectral analysis procedures assume stationarity, whereas most naturally occuring processes admit random departures from strict stationarity. SpecLab estimates and synthesizes the non-stationary process by allowing both the power-law parameters and the power-law scale range to vary over a data segmentation chosen interactively by the user. The SpecLab procedures are accessible via a graphical user interface that guides the user through the steps involved in selecting data segmentations and executing the estimation procedures. In its final form SpecLab will provides efficient user access to leading-edge analysis procedures for non-stationary processes. SpecLab is also configured to provide reproducible research that would ordinarily be available only as text, equations, and graphs.

In this chapter we define superquadrics after we outline a brief history of their development. Besides giving basic superquadric equations, we derive also some other useful geometric properties of superquadrics.

The earlier chapters have already shed some light on the utility of superquadrics in computer vision. The primary role of superquadrics has been in filling a much felt need for a volumetric representation in conjunction with shape recovery and segmentation. Despite initial reluctance in using superquadrics due to their nonlinear form, they have proven to be the modeling primitives of choice for many applications that require volumetric models. It is important to understand the limitations of the basic superquadric models, namely their limited shape vocabulary, and the fact that they are really coarse-grain closed volumetric models suitable, in particular, for object-centered generic shape descriptions. Like any other shape primitive, superquadrics can not represent arbitrary shapes. In the power of representing shapes, they are a subset of generalized cylinders, with a non-linearly varying superelliptical cross-section. For example, complex shapes such as bifurcating elongated objects (blood vessels) are better described by a generalized cylinder defined by a spine function and a cross-section function.

A common underlying task of most recognition applications is building the scene description in terms of symbolic entities. A challenging problem in scene understanding is segmentation, where each piece of information must be mapped either to a shape primitive or discarded as noise. At the same time, there should be a minimum number of such primitives applied, so as to get as compact a description as possible. The absence of the domain knowledge further makes it more difficult, as ambiguities arise due to multiple representations and incomplete data.

The modeling capabilities of superquadrics can be enhanced with global and local deformations. Global deformations such as tapering, bending or twisting require just a few additional parameters in the superquadric equations. Local deformation, in general, overlay the original superquadric with a new parameterization grid which enables local change of shape. Therefore, local deformations are by its nature not tightly integrated with superquadrics and are in this book just discussed at the end of this chapter. Hyperquadrics, which include superquadrics as a special case, and are generated by taking hyperslices of high-dimensional algebraic hypersurfaces, are also described at the end of the chapter, as well as ratioquadrics which are very similar to superquadrics but have continuous first derivatives everywhere on the surface.

One of the criteria for selection of geometric primitives in computer vision is their accessibility (Brady, 1983) . Accessibility, which can also be defined as computability of the primitive, is essential since the goal of computer vision is to recover structure from images. This requirement not only constrains the choice of the primitives but imposes certain conditions on the model-recovery procedure as well. For example, the primitives should have local support, so that they can cope with occlusions and self-occlusions. Besides, primitives should balance, according to the requirements of the task, the trade-off between data reduction and faithfulness to measured data. All model based approaches are restricted in the sense that they cannot model everything present in the input data. They should, however, model reliably those structures in the image that are essential for a given task. It is also important that the recovery method signals when the models are inadequate to describe the data, so that a different type of model can be invoked.

List of Figures. List of Tables. Preface. Contributing Authors. Introduction A. Leonardis, et al. 1. From images to virtual and augmented reality A. Zisserman, et al. 2. Surface reconstruction from multiple views using apparent contours and surface testure G. Cross, A. Zisserman. 3. Consistent projective reconstruction from multiple views M. Urban, et al. 4. Accurate natural surface reconstruction from polynocular stereo R. Sara. 5. Building models from sensor data: An application shared by the computer vision and the computer graphics community G. Roth. 6. Acquiring range images of objects with non-uniform reflectance using high dynamic scale radiance maps D. Skocaj, A. Leonardis. 7. Dynamic view interpolation without affine reconstruction R.A. Manning, C.R. Dyer. 8. Facial motion capturing using an explanation-based approach H. Tao, Th.S. Huang. 9. Image-based 3D modeling: Modeling from reality L. Van Gool, et al. 10. Computer vision and graphics techniques for modeling dressed humans N. Jojica, T.S. Huang. 11. Urban site models: Accurate, detailed, rapid and inexpensive F.W. Leberl, et al. 12. Medical visualisation, biomechanics, figure animation and robot teleoperation: Themes and links G.J. Clapworthy, et al. 13. Can virtual look real? A review of virtual studio techniques A. Wojdala. 14. Real-time 3D-teleimmersion K. Daniilidis, et al. 15. Augmented reality: A problem in need of many computer vision-based solutions G. Klinker. 16. Registration methods for harmoniousintegration of real world and computer generated objects G. Simon, et al. 17. 3D object tracking using analysis/synthesis techniques A. Gagalowicz, P. Gerard. 18. Augmented reality by integrating multiple sensory modalities for underwater scene understanding V. Murino, A. Fusiello. Index.

This paper describes the TDMA uplink of the ACTS PLANET project, realizing a high split long range access network using optical amplification. An overview of the network topology and the different building blocks is given. In particular, the differentiating burst mode receiver, the optical repeater units and the amplified splitter controller will be discussed. Bit error measurements were performed to define the system limits of the access network. It is shown that a feeder length of 90 km, in combination with a split factor of 2000 and a drop section length of 10 km are feasible.

Reverse engineering of shape strives to construct CAD models of existing objects. Automatic construction of CAD models from range images requires the segmentation of the 3D data points into subsets that correspond to individual models. We present the results of our approach to segmentation and modeling of range images which enables the reconstruction of a compact geometric representation in the MDL sense which may consist of different types of models.