Browsing Faculty of Arts and Sciences by Keyword "computer vision"

Now showing items 1-8 of 8

    • A Framework for Rapid Active Learning in Resource-Constrained Environmental Sensing Domains 

      Behari, Nikhil Swaminathan (2022-05-23)
      Recent advancements in deep convolutional neural networks have enabled accurate, efficient, and intelligent feature learning for a wide variety of classification tasks. However, there remains a research to practice gap ...

    • Bayesian Painting by Numbers: Flexible Priors for Colour-Invariant Object Recognition 

      Chua, Jeroen C.; Givoni, Inmar E.; Adams, Ryan Prescott; Frey, Brendan J. (Springer-Verlag, 2013)
      Generative models of images should take into account transformations of geometry and reflectance. Then, they can provide explanations of images that are factorized into intrinsic properties that are useful for subsequent ...

    • Image-Based Visual Hulls 

      Matusik, Wojciech; Buehler, Chris; Raskar, Ramesh; Gortler, Steven; McMillan, Leonard (Association for Computing Machinery, 2000)
      In this paper, we describe an efficient image-based approach to computing and shading visual hulls from silhouette image data. Our algorithm takes advantage of epipolar geometry and incremental computation to achieve a ...

    • Learning Silhouette Features for Control of Human Motion 

      Ren, Liu; Shakhnarovich, Gregory; Hodgins, Jessica; Pfister, Hanspeter; Viola, Paul (Association for Computing Machinery, 2005)
      We present a vision-based performance interface for controlling animated human characters. The system interactively combines information about the user's motion contained in silhouettes from three viewpoints with domain ...

    • Modeling Mitral Valve Leaflets from Three-Dimensional Ultrasound 

      Howe, Robert D.; Schneider, Robert J.; Burke, William Conroy; Marx, Gerald Ross; Del Nido, Pedro J. (Springer Science + Business Media, 2011)
      The geometry of the mitral leaflets, most commonly viewed using three-dimensional ultrasound, is an important input for mechanical models predicting valve closure. Current methods for leaflet modeling from ultrasound either ...

    • Optogenetics and Computer Vision for C. elegans Neuroscience and Other Biophysical Applications 

      Leifer, Andrew (2012-07-19)
      This work presents optogenetics and real-time computer vision techniques to non-invasively manipulate and monitor neural activity with high spatiotemporal resolution in awake behaving Caenorhabditis elegans. These methods ...

    • Perceptually-consistent boundaries and shape from stereo occlusions 

      Wang, Jialiang (2021-05-13)
      Stereo is the estimation of depth from two views of the same scene. There are two types of depth cues in a stereo image pair: matching and occlusion. Matching refers to regions of the scene that are visible to both views, ...