Zoran Zivkovic | Intel Corporation (original) (raw)

Papers by Zoran Zivkovic

Research paper thumbnail of ppeared in Proc. IEEE ICCV Workshop on Recognition, Amalysis, and Tracking of

Research paper thumbnail of Mid-Air Interactive Display Real Time Demo Video

Research paper thumbnail of Mid-air interactive display using modulated display light

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011

Display light is modulated using frequencies invisible to human eye. A camera captures images and... more Display light is modulated using frequencies invisible to human eye. A camera captures images and the known light modulation is used to isolate the display generated light. The resulting demodulated images do not depend on the ambient light conditions and the objects close to the display are clearly visible and easy to detect/track. Touch-screen like mid-air interaction with the display can be realized by robustly detecting human hands when they are close to the display.

Research paper thumbnail of Real-Time Implementations of Hough Transform on Simd Architecture

Research paper thumbnail of Approximate Bayesian methods for kernel-based object tracking

Computer Vision and Image Understanding, Jun 1, 2009

Research paper thumbnail of Image based navigation using a topological map

Research paper thumbnail of Inexpensive user tracking using Boltzmann Machines

Research paper thumbnail of Keeping Track of Humans: Have I Seen This Person Before?

Proceedings of the 2005 Ieee International Conference on Robotics and Automation, Apr 18, 2005

Research paper thumbnail of Efficient probabilistic planar robot motion estimation given pairs of images

Research paper thumbnail of The planar two point algorithm

Research paper thumbnail of Hierarchical map building and planning based on graph partitioning

Proceedings 2006 Ieee International Conference on Robotics and Automation 2006 Icra 2006, Feb 1, 2006

Research paper thumbnail of Mapping large environments with an omnivideo camera

Mon Notic Roy Astron Soc, 2008

We study the problem of mapping a large indoor environment using an omnivideo camera. Local featu... more We study the problem of mapping a large indoor environment using an omnivideo camera. Local features from omnivideo images and epipolar geometry are used to compute the relative pose between pairs of images. These poses are then used in an Extended Information Filter using a trajectory based representation where only the robot poses corresponding to captured images are reconstructed. The

Research paper thumbnail of Efficient probabilistic planar robot motion estimation given pairs of images

Robotics: Science and Systems VI, 2010

Research paper thumbnail of Improving the Selection of Feature Points for Tracking

Pattern Analysis and Applications, Jul 1, 2004

Research paper thumbnail of How did we built our hyperbolic mirror omni- directional camera - practical issues and basic geometry

Research paper thumbnail of Recognizing Strokes in Tennis Videos Using Hidden Markov Models

Research paper thumbnail of Visual Object Tracking and Recognition in a Visual Vocabulary Framework

Research paper thumbnail of Combining A Priori Knowledge and Sensor Information for Updating the Global Position of an Autonomous Vehicle

Research paper thumbnail of Toward robust foveated wide field of view people detection

Research paper thumbnail of Combining A Priori Knowledge And

Research paper thumbnail of ppeared in Proc. IEEE ICCV Workshop on Recognition, Amalysis, and Tracking of

Research paper thumbnail of Mid-Air Interactive Display Real Time Demo Video

Research paper thumbnail of Mid-air interactive display using modulated display light

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011

Display light is modulated using frequencies invisible to human eye. A camera captures images and... more Display light is modulated using frequencies invisible to human eye. A camera captures images and the known light modulation is used to isolate the display generated light. The resulting demodulated images do not depend on the ambient light conditions and the objects close to the display are clearly visible and easy to detect/track. Touch-screen like mid-air interaction with the display can be realized by robustly detecting human hands when they are close to the display.

Research paper thumbnail of Real-Time Implementations of Hough Transform on Simd Architecture

Research paper thumbnail of Approximate Bayesian methods for kernel-based object tracking

Computer Vision and Image Understanding, Jun 1, 2009

Research paper thumbnail of Image based navigation using a topological map

Research paper thumbnail of Inexpensive user tracking using Boltzmann Machines

Research paper thumbnail of Keeping Track of Humans: Have I Seen This Person Before?

Proceedings of the 2005 Ieee International Conference on Robotics and Automation, Apr 18, 2005

Research paper thumbnail of Efficient probabilistic planar robot motion estimation given pairs of images

Research paper thumbnail of The planar two point algorithm

Research paper thumbnail of Hierarchical map building and planning based on graph partitioning

Proceedings 2006 Ieee International Conference on Robotics and Automation 2006 Icra 2006, Feb 1, 2006

Research paper thumbnail of Mapping large environments with an omnivideo camera

Mon Notic Roy Astron Soc, 2008

We study the problem of mapping a large indoor environment using an omnivideo camera. Local featu... more We study the problem of mapping a large indoor environment using an omnivideo camera. Local features from omnivideo images and epipolar geometry are used to compute the relative pose between pairs of images. These poses are then used in an Extended Information Filter using a trajectory based representation where only the robot poses corresponding to captured images are reconstructed. The

Research paper thumbnail of Efficient probabilistic planar robot motion estimation given pairs of images

Robotics: Science and Systems VI, 2010

Research paper thumbnail of Improving the Selection of Feature Points for Tracking

Pattern Analysis and Applications, Jul 1, 2004

Research paper thumbnail of How did we built our hyperbolic mirror omni- directional camera - practical issues and basic geometry

Research paper thumbnail of Recognizing Strokes in Tennis Videos Using Hidden Markov Models

Research paper thumbnail of Visual Object Tracking and Recognition in a Visual Vocabulary Framework

Research paper thumbnail of Combining A Priori Knowledge and Sensor Information for Updating the Global Position of an Autonomous Vehicle

Research paper thumbnail of Toward robust foveated wide field of view people detection

Research paper thumbnail of Combining A Priori Knowledge And