In social scenes, humans interact with each other by sending visible social signals, such as facial expressions, body gestures, and gaze movements. Social cognition, the ability to perceive, model, and predict such social signals, enables people to understand social interactions and to plan their behavior in accordance with the understanding. Computational social cognition is a necessary function allowing artificial agents to enter the social spaces because it enables a socially acceptable behavior. However, two key challenges preclude developing computational social cognition: (1) the core attributes of social cognition such as attention, emotion, and intent are latent quantities that cannot be directly measured by existing sensors; (2) social behaviors are interdependent to each other, i.e., a unified representation is required to understand social behavior as wholes. In this thesis, we address these challenges by establishing a computational foundation towards social scene understanding from social cameras. A social camera is a camera held or worn by a member of a social group that inherits his/her gaze behavior. This social camera is an ideal sensor to capture social signals for three reasons: (1) social cameras naturally secure the best view because the wearers or holders intelligently localize the best view point to attend to what they find interesting; (2) social cameras produce more views of events of greater interest; (3) social cameras efficiently capture socially important events by following social behaviors when the scenes are dynamic. We leverage these advantages of social cameras to understand social scenes. We present a framework to develop social cognition by perceiving social signals, modeling the relationship between them, and predicting social behaviors. Social Signal Reconstruction: Reconstructing social signals in a unified 3D coordinate system provides a computational basis to analyze social scenes, e.g., to build a model, reason about relationships, and predict social behaviors. We leverage social cameras to reconstruct three types of social signals: gaze movement, body motion, and general scene motion. (1) Gaze is a strong indicator of attentive behaviors. We model the gaze using the primary gaze direction that is emitted from the center of the eyes and aligned with the head orientation. This gaze model is reconstructed in 3D by leveraging ego- and exo-motion of social cameras. (2) Human body motion such as gestures often conveys intent of social interactions. We model skeletal motion using a set of articulated joint trajectories where the distance between the trajectories of adjacent joints remains constant. This articulation constraint in conjunction with a temporal constraint is applied to reconstruct human body motion without an activity specific prior. (3)We further relax the articulation constraint to model general scene motion occurring in social interactions. We represent a 3D trajectory using a linear combination of predefined trajectory basis vectors. We solve for the parameters of each trajectory by formulating it as a linear least squares system that allows us to reconstruct topology-independent motion and handle missing data. Social Behavior Understanding: Social behaviors are interactive by definition and therefore, an individual behavioral analysis in isolation cannot fully account for the fundamental relationship between behaviors. For instance, a social signal transmitted by one person can trigger responses in other and the responses can, in turn, affect the behavior of the person. A relational analysis between the signals is needed to characterize the social interactions. We exploit the reconstructed social signals in a unified coordinate system to understand the relationship between them. In particular, our analysis focuses on joint attention, the primary social attribute that is strongly corv related with attentive behaviors. We present a method to reconstruct 3D joint attention modeled by social charges—latent quantities that form at locations where primary gaze directions of members in a social group intersect. Inspired by the study of electric fields, we model the relationship between gaze behaviors using a gradient field induced by the social charges. This gradient field allows us to predict gaze behaviors given social charges at any location in the scene. Our overarching goal is to develop computational social cognition that will enable artificial agents to accomplish their tasks in a socially acceptable way. This thesis takes a first step towards the goal by leveraging social cameras. We present a 3D representation of social signals and based on the reconstructed signals, we build a relational model of social behaviors, which allows us to predict the behaviors. We apply our frameworks in real-world social scenes including sporting events, meetings, and parties.

No description available.

Computer graphics perspective is based on photography, the pin-hole camera model. This thesis examines the perspective as practiced by artists, who develop the picture geometry within the planar surface of the canvas. Their approach is flexible, depth is simulated with planar composition as the primary geometry. Renaissance artists discovered construction methods to draw the foreshortening of realistic pictures: the construction of a tiled floor in perspective was fundamental. This thesis presents the framework, a computer program, I developed to create the perspective of pictures based on the geometry practices of artists. Construction lines on the image plane simulate the 3D geometry of the pictorial space; cartoons of foreground elements are manipulated in 2D within the picture perspective; projected shadows, examples of double projection, are also included. A formalism, reformulating algebraically the straight-edge and compass evaluations, generalizes the planar geometry that solves the challenge of depicting 3D. A revised Painter’s algorithm produces the occlusions between the picture elements from sequencing them from their definitions on the canvas.

The structure from motion (SfM) problem is that of determining 3-dimensional (3D) information of a scene from sequences of 2-dimensional (2D) images [59]. This information consists of object shape and motion and relative camera motion. In general, objects may undergo complex non-rigid motion and may be occluded by other objects or themselves. These aspects make the general SfM problem under-constrained and the solution subject to missing or incomplete data.

This dissertation presents interaction techniques for 3D modelling of large structures in outdoor augmented reality environments. Augmented reality is the process of registering projected computer-generated images over a user's view of the physical world. With the use of a mobile computer, augmented reality can also be experienced in an outdoor environment. Working in a mobile outdoor environment introduces new challenges not previously encountered indoors, requiring the development of new user interfaces to interact with the computer. Current AR systems only support limited interactions and so the complexity of applications that can be developed is also limited. This dissertation describes a number of novel contributions that improve the state of the art in augmented reality technology. / Thesis (PhD)--University of South Australia, 2004.

Computer models are used extensively to investigate biological systems. Many of these systems can be described in terms of fields???spatially- and temporally- varying scalar, vector and tensor properties defined over domains. For example, the spatial variation of muscle fibers is a vector field, the spatial and temporal variation in temperature of an organ is a scalar field, and the distribution of stress across muscle tissue is a tensor field. In this thesis I present my research on how to represent fields in a format that allows researchers to store and distribute them independently of models and to investigate and manipulate them intuitively. I also demonstrate how the work can be applied to solving and analysing biomedical models. To represent fields I created a two-layer system. One layer, called the Field Representation Language (FRL), represents fields by storing numeric, analytic and meta data for storage and distribution. The focus of this layer is efficiency rather than usability. The second layer, called the Abstract Field Layer (AFL), provides an abstraction of fields so that they are easier for researchers to work with. This layer also provides common operations for manipulating fields as well as transparent conversion to and from FRL representations. The applications that I used to demonstrate the use of AFL and FRL are (a) a fields visualisation toolkit, (b) integration of models from different scales and solvers, and (c) a solver that uses AFL internally. The layered architecture facilitated the development of tools that use fields. A similar architecture may also prove useful for representations of other modelled entities.

175 leaves : ill. (part col.) tables, graphs ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / Thesis (Ph.D.)--University of Adelaide, Dept. of Electrical Engineering, 1978

Thesis (MFA)--Rochester Institute of Technology, 1989. / Includes bibliographical references (leaf 20).

Thesis (M.F.A.)--Rochester Institute of Technology, 2007. / Typescript. Accompanying CD-ROM contains the Online Cake Instructor module. Includes bibliographical references (leaves 44-45).

Thesis (M.S.)--Rochester Institute of Technology, 1988. / Includes bibliographical references (leaves 55-57).