Zoom techniques for achieving scale invariant object tracking in real-time active vision systems

Show simple item record

dc.contributor.advisor Cockburn, Juan en_US
dc.contributor.advisor Savakis, Andreas en_US
dc.contributor.advisor Czernikowski, Roy en_US
dc.contributor.author Nelson, Eric en_US
dc.date.accessioned 2006-09-27T20:21:47Z en_US
dc.date.available 2006-09-27T20:21:47Z en_US
dc.date.issued 2006-09-27T20:21:47Z en_US
dc.identifier.uri http://hdl.handle.net/1850/2620 en_US
dc.description.abstract In a surveillance system, a camera operator follows an object of interest by moving the camera, then gains additional information about the object by zooming. As the active vision field advances, the ability to automate such a system is nearing fruition. One hurdle limiting the use of object recognition algorithms in real-time systems is the quality of captured imagery; recognition algorithms often have strict scale and position requirements where if those parameters are not met, the performance rapidly degrades to failure. The ability of an automatic fixation system to capture quality video of an accelerating target is directly related to the response time of the mechanical pan, tilt, and zoom platform—however the price of such a platform rises with its performance. The goal of this work is to create a system that provides scale-invariant tracking using inexpensive off-the-shelf components. Since optical zoom acts as a measurement gain, amplifying both resolution and tracking error, a new second camera with fixed focal length assists the zooming camera if it loses fixation—effectively clipping error. Furthermore, digital zoom adjusts the captured image to ensure position and scale invariance for the higher-level application. The implemented system uses two Sony EVI-D100 cameras on a 2.8GHz Dual Pentium Xeon PC. This work presents experiments to exhibit the effectiveness of the system. en_US
dc.format.extent 2711470 bytes en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US en_US
dc.subject Camera en_US
dc.subject Invariant object en_US
dc.subject Optical en_US
dc.subject Real-time en_US
dc.subject Scale en_US
dc.subject Technique en_US
dc.subject Tracking en_US
dc.subject Vision systems en_US
dc.subject Zoom en_US
dc.subject.lcc TA1634 .N45 2006 en_US
dc.subject.lcsh Computer vision en_US
dc.subject.lcsh Automatic tracking en_US
dc.subject.lcsh Zoom lenses en_US
dc.subject.lcsh Electronic surveillance en_US
dc.subject.lcsh Optical pattern recognition en_US
dc.title Zoom techniques for achieving scale invariant object tracking in real-time active vision systems en_US
dc.type Thesis en_US
dc.description.college Kate Gleason College of Enginering en_US
dc.description.department Computer Engineering en_US
dc.description.approval 2006-07 en_US

Files in this item

Files Size Format View
ENelsonThesis07-2006.pdf 2.711Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse