Interval Research Corporation

About: Interval Research Corporation is a based out in . It is known for research contribution in the topics: Haptic technology & Signal. The organization has 180 authors who have published 245 publications receiving 19184 citations.

Non-parametric local transforms for computing visual correspondence

Abstract: We propose a new approach to the correspondence problem that makes use of non-parametric local transforms as the basis for correlation. Non-parametric local transforms rely on the relative ordering of local intensity values, and not on the intensity values themselves. Correlation using such transforms can tolerate a significant number of outliers. This can result in improved performance near object boundaries when compared with conventional methods such as normalized correlation. We introduce two non-parametric local transforms: the rank transform, which measures local intensity, and the census transform, which summarizes local image structure. We describe some properties of these transforms, and demonstrate their utility on both synthetic and real data.

Methods and systems for providing human/computer interfaces

Abstract: The present invention teaches a variety of methods and systems for providing computer/human interfaces. According to one method, the user interfaces with an electronic device such as a computer system by engaging a sensor with desired regions of an encoded physical medium. The encoded physical medium is preferably chosen to provide intuitive meaning to the user, and is thus an improved metaphor for interfacing with the computer system. Suitable examples of the encoded physical medium include a data-linked book, magazine, globe, or article of clothing. Some or all of the selected regions have had certain information encoded therein, information suitable for interfacing and controlling the computer system. When the user engages the sensor with a region having certain encoded information, the certain encoded information is interpreted and an appropriate action taken. For example, the sensor or the computer system may provide suitable feedback to the user. The encoded physical medium may have text and/or graphic illustrations that draw the user in or provide meaningful clues or instructions perhaps related to the encoded information. The sensor may have at least one identification number (ID) providing information such as user identity, sensor type, access type, or language type. The sensor can transmit the certain decoded information together with the at least one ID to the computer system.

Construction and evaluation of a robust multifeature speech/music discriminator

Abstract: We report on the construction of a real-time computer system capable of distinguishing speech signals from music signals over a wide range of digital audio input. We have examined 13 features intended to measure conceptually distinct properties of speech and/or music signals, and combined them in several multidimensional classification frameworks. We provide extensive data on system performance and the cross-validated training/test setup used to evaluate the system. For the datasets currently in use, the best classifier classifies with 5.8% error on a frame-by-frame basis, and 1.4% error when integrating long (2.4 second) segments of sound.

Video Rewrite: driving visual speech with audio

Abstract: Video Rewrite uses existing footage to create automatically new video of a person mouthing words that she did not speak in the original footage. This technique is useful in movie dubbing, for example, where the movie sequence can be modified to sync the actors’ lip motions to the new soundtrack. Video Rewrite automatically labels the phonemes in the training data and in the new audio track. Video Rewrite reorders the mouth images in the training footage to match the phoneme sequence of the new audio track. When particular phonemes are unavailable in the training footage, Video Rewrite selects the closest approximations. The resulting sequence of mouth images is stitched into the background footage. This stitching process automatically corrects for differences in head position and orientation between the mouth images and the background footage. Video Rewrite uses computer-vision techniques to track points on the speaker’s mouth in the training footage, and morphing techniques to combine these mouth gestures into the final video sequence. The new video combines the dynamics of the original actor’s articulations with the mannerisms and setting dictated by the background footage. Video Rewrite is the first facial-animation system to automate all the labeling and assembly tasks required to resync existing footage to a new soundtrack.

The haptic display of complex graphical environments

Abstract: Force feedback coupled with visual display allows people to interact intuitiv ely with complex virtual environments. For this synergy of haptics and graphics to flourish, however, haptic systems must be capable of modeling environments with the same richness, complexity and interactivity that can be found in existing graphic systems. To help meet this challenge, we have developed a haptic rendering system that allows for the efficient tactile display of graphical information. The system uses a common high-level framework to model contact constraints, surface shading, friction and tex ture. The multilevel control system also helps ensure that the haptic device will remain stable even as the limits of the renderer’s capabilities are reached.