Multimodal Scene Understanding

Multimodal Scene Understanding
Author: Michael Ying Yang
Publisher: Academic Press
Total Pages: 424
Release: 2019-07-16
Genre: Technology & Engineering
ISBN: 0128173599

Multimodal Scene Understanding: Algorithms, Applications and Deep Learning presents recent advances in multi-modal computing, with a focus on computer vision and photogrammetry. It provides the latest algorithms and applications that involve combining multiple sources of information and describes the role and approaches of multi-sensory data and multi-modal deep learning. The book is ideal for researchers from the fields of computer vision, remote sensing, robotics, and photogrammetry, thus helping foster interdisciplinary interaction and collaboration between these realms. Researchers collecting and analyzing multi-sensory data collections – for example, KITTI benchmark (stereo+laser) - from different platforms, such as autonomous vehicles, surveillance cameras, UAVs, planes and satellites will find this book to be very useful. - Contains state-of-the-art developments on multi-modal computing - Shines a focus on algorithms and applications - Presents novel deep learning topics on multi-sensor fusion and multi-modal deep learning

Virtual Reality

Virtual Reality
Author: National Research Council
Publisher: National Academies Press
Total Pages: 557
Release: 1995-01-13
Genre: Computers
ISBN: 0309051355

Despite widespread interest in virtual reality, research and development efforts in synthetic environments (SE)â€"the field encompassing virtual environments, teleoperation, and hybridsâ€"have remained fragmented. Virtual Reality is the first integrated treatment of the topic, presenting current knowledge along with thought-provoking vignettes about a future where SE is commonplace. This volume discusses all aspects of creating a system that will allow human operators to see, hear, smell, taste, move about, give commands, respond to conditions, and manipulate objects effectively in a real or virtual environment. The committee of computer scientists, engineers, and psychologists on the leading edge of SE development explores the potential applications of SE in the areas of manufacturing, medicine, education, training, scientific visualization, and teleoperation in hazardous environments. The committee also offers recommendations for development of improved SE technology, needed studies of human behavior and evaluation of SE systems, and government policy and infrastructure.

More Than Screen Deep

More Than Screen Deep
Author: National Research Council
Publisher: National Academies Press
Total Pages: 452
Release: 1997-10-12
Genre: Computers
ISBN: 9780309063579

The national information infrastructure (NII) holds the promise of connecting people of all ages and descriptionsâ€"bringing them opportunities to interact with businesses, government agencies, entertainment sources, and social networks. Whether the NII fulfills this promise for everyone depends largely on interfacesâ€"technologies by which people communicate with the computing systems of the NII. More Than Screen Deep addresses how to ensure NII access for every citizen, regardless of age, physical ability, race/ethnicity, education, ability, cognitive style, or economic level. This thoughtful document explores current issues and prioritizes research directions in creating interface technologies that accommodate every citizen's needs. The committee provides an overview of NII users, tasks, and environments and identifies the desired characteristics in every-citizen interfaces, from power and efficiency to an element of fun. The book explores: Technological advances that allow a person to communicate with a computer system. Methods for designing, evaluating, and improving interfaces to increase their ultimate utility to all people. Theories of communication and collaboration as they affect person-computer interactions and person-person interactions through the NII. Development of agents: intelligent computer systems that "understand" the user's needs and find the solutions. Offering data, examples, and expert commentary, More Than Screen Deep charts a path toward enabling the broadest-possible spectrum of citizens to interact easily and effectively with the NII. This volume will be important to policymakers, information system designers and engineers, human factors professionals, and advocates for special populations.

Vision for Robotics

Vision for Robotics
Author: Danica Kragic
Publisher: Now Publishers Inc
Total Pages: 94
Release: 2009
Genre: Artificial vision
ISBN: 1601982607

Robot vision refers to the capability of a robot to visually perceive the environment and use this information for execution of various tasks. Visual feedback has been used extensively for robot navigation and obstacle avoidance. In the recent years, there are also examples that include interaction with people and manipulation of objects. In this paper, we review some of the work that goes beyond of using artificial landmarks and fiducial markers for the purpose of implementing visionbased control in robots. We discuss different application areas, both from the systems perspective and individual problems such as object tracking and recognition.