Ramesh Jain - US grants

The project is an initial exploratory research effort in segmentation of range images and the development of a robust method to recover symbolic descriptors of surfaces from those images. The surfaces will be represented as polynomials, whose coefficients will be obtained from a number of explicitly determined surface points, obtained using existing techniques. Appropriate descriptors will be derived from the terms of the representing polynomials. A search will be made for more powerful and general surface descriptors. The project will also study the efficacy of the segmentation program in recovering symbolic descriptors from images containing several objects, some of which may be only partially visible.

There has been a growing research interest in range image understanding in the computer vision community. Range images offer several advantages over conventional intensity images in the recognition of 3-dimensional objects. This project provides partical support for a workshop brings together active researchers in range image understanding to discuss emerging themes in this field. The workshop will identify major research area that should be addressed for making range image understanding systems useful in industrial and other application. Guidelines for establishing a common range image data base will also be discussed. Findings of the workshop will be widely disseminated in the computer vision community.

This recommendation is to provide funding to enhance the computational facilities for research in computer vision and related areas in the Electrical Engineering and Computer Science Department at the University of Michigan. The research efforts in the Computer Vision Research Laboratory address almost all aspects of computer vision. There is, however, a clear emphasis on symbolic computation. The activity will involve integrating symbolic computation with the low-level processes. The increasing requirement for symbolic processing has resulted in an emphasis on LISP machines. This award will provide funding for a set of high-quality workstations which will provide the necessary capabilities.

The objective of this research is to develop a robust algorithm for motion detection and segmentation of dynamic scenes. Preliminary results in motion detection using local structures of hypersurfaces in the spatio-temporal domain are promising. They will be extended to dynamic scenes acquired using stationary as well as moving cameras. The proposed approach will be based on a combination of surface approximation and region growing for the segmentation of a dynamic scene. The applicability of the proposed algorithn to sequences in the egomotion complex log space will also be studied. Both laboratory and outdoor scenes will be used for the experimental verification of the algorithms.

This award is for the purchase of equipment for the high speed acquisition of images and for manipulator end-effector hardware. The image equipment is needed for real-time performance and the end-effector hardware is needed for experimentation with manipulation tasks. The equipment is also used in integrating vision and manipulation tasks incorporating perception, cognition, and action. Applied robotics involves the integration of many areas including vision research, control research, sensor integration, and planning algorithms. This proposal requests funds for the purchase of equipment to support vision research and manipulator research. The vision equipment will allow real time processing of visual data while the manipulators (grippers, etc.) will allow the testing of manipulator algorithms with the robot arm connected to actual manipulators.

From satellite images to elementary school textbooks, our everyday life is full of information presented in the form of images. Since so much information is in non-alphanumeric form, as a natural extension of the ideas in databases, researchers started exploring the design and implementation of image databases. The progress in this area requires close interaction among researchers from disparate areas of computer science and other fields. To bring together active researchers in databases, object-oriented systems, image and signal processing, multi- media, and other related areas a workshop will be organized. In addition to the researchers in the above and related areas, a few researchers and practitioners interested in applying these systems in industry, health-care, global change and other areas will be invited. The practitioners will provide input into the discussion to guarantee that useful systems will be designed by researchers and practitioners working in this emerging area. The participants will be drawn from academic institutions, research centers, Government, and industry. The report of the workshop will be submitted to NSF and will be widely publicized. The report will identify major research areas that should be addressed by researchers for designing user-friendly visual information management systems suitable for a wide range of application domains.

Effective power system operation requires well-planned commitments of generating units in a planning phase combined with responsive real-time dispatching of power in an operational control phase. Typically, the unit commitment plan is determined by an optimization model that considers a forecast for demand, fixed security constraints, and known unit availabilities. The operational controller considers actual random demand, varying security reserves, and unforeseen unit losses. This project will combine these tasks by integrating the planning and operating phases in a unified control framework. The emphasis in the planning phase will be on considering random effects, contingencies and the values attributed to potential ending states. The emphasis on the operating phase will be on considering longer term effects, recognizing conditions requiring corrective actions, searching for similar situations and potential actions for learning from both practical experience and simulated events.

9320436 Jain Improved computational methods and information management tools are critical in order to enhance the national competitive edge across broad sectors of the economy and to make rapid progress in education, medicine, global change analysis and several other aspects of scientific endeavor. Until recently, information in computers was almost always in alpha-numeric form, but today, alpha-numeric information seems very restricting in our interactions with computers. We need multimedia systems that will seamlessly manage audio, video, graphics, alpha-numeric and several other forms of information. To meet these new demands, many aspects of multimedia computing are being addressed by researchers at the University of California, San Diego. This award provides equipment to support active research projects in the emerging areas of multimedia computing in the Departments of Computer Science and Engineering, and Electrical and Computer Engineering at the University of California, San Diego. The massive storage equipment will be used for several research projects covering many important areas of multimedia computing: multimedia servers, networking, operating systems, and databases. This equipment will also facilitate joint research projects in distributed multimedia information systems. The massive storage will help to take some of the algorithms and studies to the level of realistic prototypes. In addition, the equipment will also be available to other researchers developing multimedia tools in robotics, artificial intelligence, health care, manufacturing and other related areas. ***

This project is working to make rapid prototyping and reverse engineering facilities available over wide-area computer networks. It includes several research thrusts along with an integration effort to ensure that the facilities will be usable remotely with little on-site intervention. The project has four major thrusts: (1) development of algorithms for checking consistency of geometric descriptions; (2) development of new languages based on constructive solid geometry for communicating geometric descriptions; (3) connection of rapid prototyping equipment to a wide rear network, with device drivers and server software to allow remote access; (4) connection of a 3D scanner to the network for remote access.

9417435 Jain ABSTRACT UCSD MS Program in World Class Manufacturing Engineering The University of California, San Diego proposes to create a 2-year MS Program World Class Manufacturing Engineering with a strong international and information systems focus. In partnerships with ALCOA Electronic Packaging, Hewlett-Packard, Hughes Aircraft, and TITAN Linkabit, it is targeted toward displaced defense engineers, particularly women and minorities. Aiming to take advantage of manufacturing and management strengths overseas, the program has a unique emphasis on foreign language and culture learning (approximately 50% of the students) and includes a 9-month internship in a manufacturing firm in the U.S. or abroad. With good support from institutions with strong international studies program, it expects a steady state of 30 students per year with expansion in later years to feed in undergraduates. ***

9422069 Jain For the past decade, the importance of visual computing has increased exponentially. Visual computing, which embraces processing, interpreting, modeling, assimilating, storing and synthesizing visual information, now plays a pivotal role in many fields. These include such subjects as: virtual reality, multimedia, robotics, computer-human interaction, scientific visualization and communication. This award is to purchase equipment for supporting a number of ongoing research projects that are committed to this important field. The goal of these projects is to improve visual information computing through innovative experimental research. The equipment which include two visualization systems, one real-time image processing subsystem, and a number of visual sensors will be dedicated to support four individual research projects each addressing a different aspect of visual computing, namely Visual Information Assimilation, Visual Interaction through Gesture Recognition, Modeling and Design of Optoelectronic Visual Information Processors, and Physics-based Visualization of Multipedal Walking Systems. ***

This workshop will be held on June 19, 1995, in conjunction with the ICCV conference at MIT in Cambridge, Mass. The objective of the workshop is to bring together researchers who in the last few years have started addressing problems in Visual Information Management (VIM). Most of these efforts, however, were focussed either on only a small aspect of the problem or a very narrow application. Clearly, visual information management systems encompass central aspects of databases, image processing and image understanding, very sophisticated interfaces, networks and storage systems, knowledge based systems, compression and decompression, and object oriented systems. Without addressing most of these issues, one may either address only theoretical issues, or may work in a microcosm that will, at best, be extremely narrow in its utility and extensibility. Considering the growing need and interest in the organization and retrieval of visual and other non-alphanumeric information, and the insufficient number of academic projects in this area, the workshop on visual information management systems will provide a much needed platform. While VIM is a very broad area, the focus of the workshop is on what researchers in computer vision could contribute. The challange for vision researchers is to develop tools for analyzing the semantic content of video and image, and then representing that content in a way that can be efficiently searched and compared, and finally delivering that content to users in the form a of useful, focused presentation. Computer vision can contribute techniques for semiautomatically and automatically extracting features that will be essential for indexing and query formulation in image and video databases. Computer vision researchers have addressed problems in human and robotic vision for several applications, but very little attention has been given to this new emerging field. This workshop will be exploring computer vision techniques which are going to prov ide the basic foundation for visual information management systems.

This award supports a workshop to develop an intellectual and research agenda on the topics of citizen diplomacy and citizen networks. Citizen diplomacy and citizen networks are conceptualized as a technologically mediated form of soft-diplomacy. Citizen diplomacy raises intellectual scientific challenges for researchers that are by nature interdisciplinary: technical, economic and political, and social. Technical scientific research questions concern developing new capabilities for the mobile phone for use as a primary client, novel multimodal interaction environments, the reliability of a country?s infrastructure, and using technology to create incentives to participate. Political and economic research questions include studying government policy, Internet censorship, the cost of network use, and the instability of political climates. Social and cultural research questions include dealing with illiteracy, language differences, cultural awareness, finding others to participate, developing trust in others and in technology, managing system abuse and malicious behavior, and dealing with time zone differences. There is a critical need to develop a focused research agenda that outlines the scientific and technical challenges that effectively integrates these and other research topics to benefit from the socio-technical transformations of the world wide network.

The development of technologies to support citizen diplomacy will benefit citizens of the United States as well as those in developing countries. Creating citizen networks between the developing and developed worlds will help to break down cultural, social, and political barriers. Taking such a ?bottom-up? approach with citizens may influence policy at national levels. People in both developed and developing countries will gain by learning new ideas and cultural practices. Above all, we expect that citizen diplomacy can expose young people to alternative life paths, thus limiting the impacts of local extremist views.

Dr. Sharad Mehrotra and an interdisciplinary team of collaborators at the University of California at Irvine (UCI) will develop I-sensorium, to serve as a "living laboratory" to support research in several related areas of cyber-physical systems: including theoretical foundations and underlying principles of building sentient systems; engineering, software, and systems level challenges; and novel application contexts where such sentient systems can be used. I-Sensorium will serve as a testbed for exploring and testing novel sentient technologies. I-Sensorium augments Responsphere, an existing UCI crisis response test-bed with state-of-the-art storage and computational infrastructure to acquire and process continuous streams of sensory data from Responsphere sensors. The I-Sensorium software will leverage multiple ongoing research projects at UCI on large-scale, heterogeneous sensor databases, sensor middleware platforms for querying and analysis of heterogeneous sensor data, and an event representation system for multi-media data, to provide a high level programming environment for the I-Sensorium allowing a broad group of researchers to participate and benefit from its creation.

The development of I-Sensorium offers opportunities for research-based education and training in many aspects of cyber-physical systems. The infrastructure as well as the sensor data acquisition enabled by it presents research challenges and opportunities in sensor data management, machine learning, computer vision, event modeling, among others. Interactions with industrial partners and government agencies are expected to lead to advances in the applications of cyber-physical systems in real-world settings. Education and outreach efforts are aimed at broadening the participation of women and members of underrepresented groups in computer science and engineering. Further information about this project can be found at: http://www.i-sensorium.org

The Planning Grants for Engineering Research Centers competition was run as a pilot solicitation within the ERC program. Planning grants are not required as part of the full ERC competition, but intended to build capacity among teams to plan for convergent, center-scale engineering research.

This planning grant to establish an Engineering Research Center brings together researchers from Iowa State University, Arizona State University, Georgia Tech, and University of California Irvine to study how engineering technologies can be used to improve the everyday functioning of older U.S. adults as they age. Older adults represent the fastest-growing demographic group, which is creating urgent and largely unmet needs for affordable services, technologies, and environmental support infrastructure for these citizens to age optimally. Our engineering approach will have a high societal impact by meeting the needs of older adults and better preparing individuals, families, and communities for optimal and affordable aging. Our proposed approach will integrate concepts and ideas from engineering, life sciences, computational sciences, and social sciences to provide affordable solutions to the scientific and societal challenges associated with aging. The planning grant activities will enable us to expand research capacity in this area by connecting with a broad range of stakeholders and industry. Our educational and outreach activities will produce diverse, creative, responsible, entrepreneurial, and globally engaged leaders. All these activities will lead to an improved fundamental understanding of the most important needs of aging in place and help create a new research paradigm with engaged stakeholders to provide transformative and affordable solutions to optimal aging and reduce growing healthcare costs.

Our proposed approach will integrate convergent research, education, and technology transfer programs focused on novel sensor and network technology integrated with Internet of Things data fusion, designer materials for delivery, and cognitive competence and enhanced everyday functioning. Together with our industrial and innovation partners, we will transform the design and manufacture of aging-centric technologies and lead to rapid commercialization by a systems-approach encompassing scientific, social, and behavioral considerations from the earliest stages of conceptualization. The planning grant activities will help us to: (i) expand research capacity in this research area; (ii) integrate new education, outreach, and technology transfer activities across the partner institutions; (iii) engage a broad group of stakeholders and industrial partners; (iv) strategize on team formation and effective leadership/management; and (v) design and implement a national survey of older adults to further guide our research vision. All of these planning grant activities will lead to the development of the full complement of skills needed to successfully address this complex societal challenge and build effective relationships with a diverse stakeholder community.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Scientific and technological advances in the last century have helped humankind move past infectious disease as the primary cause of mortality. Average lifespan has doubled from 40 years to above 80 years in developed countries. Today, chronic disease presents our greatest health challenge. Current healthcare practice based on the episodic infectious disease health model is not a good approach to treating chronic disease. Instead, healthcare needs to focus on diet, exercise, and other lifestyle activities. Future health systems will use rich, multi-modal data to sense health state continuously and provide guidance in making daily lifestyle decisions. The lifestyle navigational approach is a close-loop sense-estimate-act cycle based on sensors, computing elements, and actuators and closely guided by the personal model of the individual. To provide guidance, predict the future, or understand preferences of an individual, we must build a model that is specific to an individual. The personal model contains not only ordinary medical record data, but also information about disease propensity and lifestyle behaviors.

This project will develop methods to easily and accurately track behaviors that have an impact on health and chronic disease, and methods for incorporating such information into a personalized lifestyle health model. These models will be critical in developing a navigational approach to health in order to facilitate precision medicine based on predictive and preventive approaches. Nutrition is one of the major components of lifestyle, and yet there are no fully satisfactory approaches for food logging. This proposal will specifically create a novel approach to food logging based on using a wearable sensor to detect heart rate changes associated with eating, which triggers an ecological momentary assessment (EMA) for food logging. A food log compared with already available activity logs provides enough quantitative information to understand and analyze lifestyle quantitatively for a person. This project will develop novel event mining techniques by extending machine learning approaches for building lifestyle related causal models for a person that will be used in predictive approaches as well as in guiding the person's lifestyle decisions.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.