Search For:

Displaying 1-17 out of 17 total
Webcam2Satellite: Estimating cloud maps from webcam imagery
Found in: 2013 IEEE Workshop on Applications of Computer Vision (WACV)
By Calvin Murdock,Nathan Jacobs,Robert Pless
Issue Date:January 2013
pp. 214-221
We consider the problem of estimating the current satellite cloud map from a collection of broadly distributed, ground-based webcams. The approach uses historical, geo-referenced satellite imagery to learn a mapping between the satellite image and the grou...
 
LOST: Longterm Observation of Scenes (with Tracks)
Found in: Applications of Computer Vision, IEEE Workshop on
By Austin Abrams,Jim Tucek,Joshua Little,Nathan Jacobs,Robert Pless
Issue Date:January 2012
pp. 297-304
We introduce the Longterm Observation of Scenes (with Tracks) dataset. This dataset comprises videos taken from streaming outdoor webcams, capturing the same half hour, each day, for over a year. LOST contains rich metadata, including geolocation, day-by-d...
 
Using cloud shadows to infer scene structure and camera calibration
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nathan Jacobs, Brian Bies, Robert Pless
Issue Date:June 2010
pp. 1102-1109
We explore the use of clouds as a form of structured lighting to capture the 3D structure of outdoor scenes observed over time from a static camera. We derive two cues that relate 3D distances to changes in pixel intensity due to clouds shadows. The first ...
 
Toward Fully Automatic Geo-Location and Geo-Orientation of Static Outdoor Cameras
Found in: Applications of Computer Vision, IEEE Workshop on
By Nathan Jacobs, Nathaniel Roman, Robert Pless
Issue Date:January 2008
pp. 1-6
Automating tools for geo-locating and geo-orienting static cameras is a key step in creating a useful global imaging network from cameras attached to the Internet. We present algorithms for partial camera calibration that rely on access to accurately time-...
 
Location-specific Transition Distributions for Tracking
Found in: Motion and Video Computing, IEEE Workshop on
By Nathan Jacobs, Michael Dixon, Robert Pless
Issue Date:January 2008
pp. 1-6
Surveillance and tracking systems often observe the same scene over extended time periods. When object motion is constrained by the scene (for instance, cars on roads, or pedestrians on sidewalks), it is advantageous to characterize and use scene-specific ...
 
Geolocating Static Cameras
Found in: Computer Vision, IEEE International Conference on
By Nathan Jacobs, Scott Satkin, Nathaniel Roman, Richard Speyer, Robert Pless
Issue Date:October 2007
pp. 1-6
A key problem in widely distributed camera networks is geolocating the cameras. This paper considers three scenarios for camera localization: localizing a camera in an unknown environment, adding a new camera in a region with many other cameras, and locali...
 
Consistent Temporal Variations in Many Outdoor Scenes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nathan Jacobs, Nathaniel Roman, Robert Pless
Issue Date:June 2007
pp. 1-6
This paper details an empirical study of large image sets taken by static cameras. These images have consistent correlations over the entire image and over time scales of days to months. Simple second-order statistics of such image sets show vastly more st...
 
Shape Background Modeling : The Shape of Things That Came
Found in: Motion and Video Computing, IEEE Workshop on
By Nathan Jacobs, Robert Pless
Issue Date:February 2007
pp. 27
Detecting, isolating, and tracking moving objects in an outdoor scene is a fundamental problem of visual surveillance. A key component of most approaches to this problem is the construction of a background model of intensity values. We propose extending ba...
 
Finding Minimal Parameterizations of Cylindrical Image Manifolds
Found in: Computer Vision and Pattern Recognition Workshop
By Michael Dixon, Nathan Jacobs, Robert Pless
Issue Date:June 2006
pp. 192
Manifold learning has become an important tool to characterize high-dimensional data that vary nonlinearly due to a few parameters. Applications to the analysis of medical imagery and human motion patterns have been successful despite the lack of effective...
 
A CRF approach to fitting a generalized hand skeleton model
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Radu Paul Mihail,Gustav Blomquist,Nathan Jacobs
Issue Date:March 2014
pp. 409-416
We present a new point distribution model capable of modeling joint subluxation (shifting) in rheumatoid arthritis (RA) patients and an approach to fitting this model to posteroanterior view hand radiographs. We formulate this shape fitting problem as infe...
   
Exploring the geo-dependence of human face appearance
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Mohammad T. Islam,Scott Workman, Hui Wu,Nathan Jacobs,Richard Souvenir
Issue Date:March 2014
pp. 1042-1049
The expected appearance of a human face depends strongly on age, ethnicity and gender. While these relationships are well-studied, our work explores the little-studied dependence of facial appearance on geographic location. To support this effort, we const...
   
Estimating cloudmaps from outdoor image sequences
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Nathan Jacobs,Joshua King,Daniel Bowers,Richard Souvenir
Issue Date:March 2014
pp. 961-968
Cloud shadows dramatically affect the appearance of outdoor scenes. We describe two approaches that use video of cloud shadows to estimate a cloudmap, a spatio-temporal function that represents the clouds passing over the scene. Our first method makes stro...
   
Teaching graphics for games using Microsoft XNA
Found in: 2013 18th International Conference on Computer Games: AI, Animation, Mobile, Interactive Multimedia, Educational & Serious Games (CGAMES)
By Radu Paul Mihail,Judy Goldsmith,Nathan Jacobs,Jerzy W. Jaromczyk
Issue Date:July 2013
pp. 36-40
We present an approach to teaching introductory computer graphics for game development using Microsoft XNA as a development platform. One of the main challenges for such courses is an uneven level of student knowledge and skills, particularly in the underl...
   
Cloud Motion as a Calibration Cue
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Nathan Jacobs,Mohammad T. Islam,Scott Workman
Issue Date:June 2013
pp. 1344-1351
We propose cloud motion as a natural scene cue that enables geometric calibration of static outdoor cameras. This work introduces several new methods that use observations of an outdoor scene over days and weeks to estimate radial distortion, focal length ...
 
Participatory integration of live webcams into GIS
Found in: Proceedings of the 1st International Conference and Exhibition on Computing for Geospatial Research & Application (COM.Geo '10)
By Austin Abrams, Nathan Jacobs, Nick Fridrich, Robert Pless
Issue Date:June 2010
pp. 1-8
Global satellite imagery provides nearly ubiquitous views of the Earth's surface, and the tens of thousands of webcams provide live views from near Earth viewpoints. Combining these into a single application creates live views in the global context, where ...
     
The global network of outdoor webcams: properties and applications
Found in: Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (GIS '09)
By Andrew D. Richardson, Austin Abrams, Bobby H. Braswell, Kylia Miskell, Nathan Jacobs, Nick Fridrich, Robert Pless, Walker Burgin
Issue Date:November 2009
pp. 111-120
There are thousands of outdoor webcams which offer live images freely over the Internet. We report on methods for discovering and organizing this already existing and massively distributed global sensor, and argue that it provides an interesting alternativ...
     
Real-time constant memory visual summaries for surveillance
Found in: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks (VSSN '06)
By Nathan Jacobs, Robert Pless
Issue Date:October 2006
pp. 155-160
In surveillance applications there may be multiple time scales at which it is important to monitor a scene. This work develops on-line, real-time algorithms that maintain background models simultaneously at many time scales. This creates a novel temporal d...
     
 1