Site Network: Home |



Getting computer vision systems to recognise reality



Enabling cognitive computer vision systems to emulate human capabilities is the driving force behind the VAMPIRE project, as will be demonstrated at the IST2004 event with its object localisation via hybrid tracking methods, context-aware scene augmentation and interactive object learning.



To date, computer vision systems have been unable to emulate the full capabilities of the human visual system. The human eye-brain combination has proved able to categorise previously unseen objects with ease, using background knowledge and context. We recognise a pig as a pig because of the shape of its body and because we see it in a farmyard or field.



Context and background knowledge essential

However the VAMPIRE project seeks to enable cognitive computer vision systems to develop similar capabilities. Project participants are working on the thesis that learning and cognitive capabilities in vision systems cannot be realised without using Visual Active Memory (VAM) processes, which provide the context and background knowledge for learning and categorising objects and behaviours despite a dynamically changing environment.



The aim of VAMPIRE (due to complete in July 2005) is to develop and test this hypothesis that Visual Active Memory is instrumental to cognition. One of the scenarios used to test the hypothesis is to use two static cameras to provide visual input for an action recognition system within an office environment. The resulting algorithms for object and action-recognition enable the system to develop a consistent interpretation of the scene.



Other scenarios include locating the position of augmented-reality (AR) users, interactive object learning (a user interactively teaches the system to recognise new objects), and scene augmentation based on visually-detected events (the user touches a book in front of him, whereupon the system displays information about the book within his visual field).



Providing assistance while it learns

What is innovative about the project is that it tightly couples object acquisition and recognition processes while including the human brain in the processing loop. The system aims to gather knowledge that enables it to learn, at the same time as it provides information to the human user. It makes use of a general memory infrastructure that stores the visual event, learns new concepts and retrieves past events in order to provide the necessary object categorisation.



VAMPIRE has also developed several innovations in aspects of computer vision such as tracking of objects in real-time, hybrid tracking integrating inertial and visual cues, use of attention cues, acquisition of object models from a very limited range of example images, and categorisation from contextual reasoning.



First mobile demonstrators on show

The project has already shown the first mobile AR demonstrators to show object localisation via hybrid tracking methods, as well as context-aware scene augmentation and interactive object learning. All these abilities are to be demonstrated on the VAMPIRE project stand at IST 2004. A project-related workshop has also generated positive feedback from industry on several potential application areas, including quality assurance in manufacturing and teaching systems.

0 comments:

Post a Comment


This website does not recommend the purchase or sale of any stocks, options, bonds or any investment of any kind. This website does not provide investment advice. Disclaimer and Notices: Disclaimer: This website may contain "forward-looking" information including statements concerning the company's outlook for the future, as well as other statements of beliefs, future plans and strategies or anticipated events, and similar expressions concerning matters that are not historical facts. The forward-looking information and statements are subject to risks and uncertainties that could cause actual results to differ materially from those expressed in, or implied by, the statements. The information on this website includes forward looking statements, including statements regarding projections of future operations, product applications, development and production, future benefits of contractual arrangements, growth in demand, as well as statements containing words like believe, estimate, expect, anticipate, target, plan, will, could, would, and other similar expressions. These statements are not guarantees of future performance. Actual results could differ materially from the results implied or expressed in the forward looking statement. Additional information concerning factors that could cause actual results to differ materially from those in the forward looking statements are included in MVIS most recent Annual Report on Form 10-K filed with the Securities and Exchange Commission under the heading 'Risk factors related to the company's business,' and our other reports filed with the Comission from time to time. Except as expressly required by Federal securities laws, MVIS Blog undertakes no obligation to publicly update or revise any forward looking statements, whether as a result of new information, future events, changes in circumstances, or other reasons. Legal Notice: Although considerable care has been taken in preparing and maintaining the information and material contained on this website, MVIS Blog makes no representation nor gives any warranty as to the currency, completeness, accuracy or correctness of any of the elements contained herein. Facts and information contained in the website are believed to be accurate at the time of posting. However, information may be superseded by subsequent disclosure, and changes may be made at any time without prior notice. MVIS Blog shall not be responsible for, or liable in respect of, any damage, direct or indirect, or of any nature whatsoever, resulting from the use of the information contained herein. While the information contained herein has been obtained from sources believed to be reliable, its accuracy and completeness cannot be guaranteed. MVIS Blog has not independently verified the facts, assumptions, and estimates contained on this website. Accordingly, no representation or warranty, express or implied, is made as to, and no reliance should be placed on the fairness, accuracy, or completeness of the information and opinions contained on this website. Consequently, MVIS Blog assumes no liability for the accompanying information, which is being provided to you solely for evaluation and general information. This website does not contain inside information, proprietary or confidential information learned or disclosed as part of employment relationships or under nondisclosure agreements or otherwise.