Bøger af Ramesh Jain

Motion-based recognition deals with the recognition of an object and/or its motion, based on motion in a series of images. In this approach, a sequence containing a large number of frames is used to extract motion information. The advantage is that a longer sequence leads to recognition of higher level motions, like walking or running, which consist of a complex and coordinated series of events. Unlike much previous research in motion, this approach does not require explicit reconstruction of shape from the images prior to recognition. This book provides the state-of-the-art in this rapidly developing discipline. It consists of a collection of invited chapters by leading researchers in the world covering various aspects of motion-based recognition including lipreading, gesture recognition, facial expression recognition, gait analysis, cyclic motion detection, and activity recognition. Audience: This volume will be of interest to researchers and post- graduate students whose work involves computer vision, robotics and image processing.

With the proliferation of citizen reporting, smart mobile devices, and social media, an increasing number of people are beginning to generate information about events they observe and participate in. A significant fraction of this information contains multimedia data to share the experience with their audience. A systematic information modeling and management framework is necessary to capture this widely heterogeneous, schemaless, potentially humongous information produced by many different people. This book is an attempt to examine the modeling, storage, querying, and applications of such an event management system in a holistic manner. It uses a semantic-web style graph-based view of events, and shows how this event model, together with its query facility, can be used toward emerging applications like semi-automated storytelling. Table of Contents: Introduction / Event Data Models / Implementing an Event Data Model / Querying Events / Storytelling with Events / An Emerging Application / Conclusion

This book presents a framework for converting multitudes of data streams available today including weather patterns, stock prices, social media, traffic information, and disease incidents into actionable insights based on situation recognition.

Humans are the best functioning example of multimedia communication and computing - that is, we understand information and experiences through the unified perspective offered by our five senses. This innovative textbook presents emerging techniques in multimedia computing from an experiential perspective in which each medium - audio, images, text, and so on - is a strong component of the complete, integrated exchange of information or experience. The authors' goal is to present current techniques in computing and communication that will lead to the development of a unified and holistic approach to computing using heterogeneous data sources. Gerald Friedland and Ramesh Jain introduce the fundamentals of multimedia computing, describing the properties of perceptually encoded information, presenting common algorithms and concepts for handling it, and outlining the typical requirements for emerging applications that use multifarious information sources. Designed for advanced undergraduate and beginning graduate courses, the book will also serve as an introduction for engineers and researchers interested in understanding the elements of multimedia and their role in building specific applications.