Object tracking with a pan, tilt and zoom camera

This thesis reviews the existing work done on tracking with pan/tilt/zoom cameras and proposes a novel method of multiscale block tracking with perspective cameras using principles and methods from both computer vision and computer graphics. The theory of perspective transforms in 3D graphics is rev...

Full description

Bibliographic Details
Main Author: Sinclair, Mark Macdonald
Published: University of Edinburgh 2005
Subjects:
Online Access:http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.661970
id ndltd-bl.uk-oai-ethos.bl.uk-661970
record_format oai_dc
spelling ndltd-bl.uk-oai-ethos.bl.uk-6619702016-06-21T03:22:27ZObject tracking with a pan, tilt and zoom cameraSinclair, Mark Macdonald2005This thesis reviews the existing work done on tracking with pan/tilt/zoom cameras and proposes a novel method of multiscale block tracking with perspective cameras using principles and methods from both computer vision and computer graphics. The theory of perspective transforms in 3D graphics is reviewed as well as relating real world cameras to synthetic cameras through camera calibration. Conventional 2D block tracking methods are reviewed and the expanded to track under pan, tilt and zoom conditions. Two methods of pan/tilt/zoom tracking are developed and then applied to blocks and blobs (connected regions of pixels). A novel offline technique of fitting contours to these track points is then explored with and without the presence of pan, tilt and zoom. A method of updating the multiscale reference block is presented and the tracker is evaluated without block updating (feed forward) and with block updating and position filtering. Experimental results for people following are presented using synthetic ray-traced data with absolute ground truth and real sequences taken with a commercial pan/tilt/zoom camera with hand estimated ground truth. All sequences were processed offline, however, with optimisation it appears to be feasible to implement a real-time solution. Applying position filtering and predictions, using a Kalman filter, improves results and robustness. The application of this method to existing vision techniques is discussed as well as the possible methods for real-time implementation of these algorithms.530.0724University of Edinburghhttp://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.661970http://hdl.handle.net/1842/14426Electronic Thesis or Dissertation
collection NDLTD
sources NDLTD
topic 530.0724
spellingShingle 530.0724
Sinclair, Mark Macdonald
Object tracking with a pan, tilt and zoom camera
description This thesis reviews the existing work done on tracking with pan/tilt/zoom cameras and proposes a novel method of multiscale block tracking with perspective cameras using principles and methods from both computer vision and computer graphics. The theory of perspective transforms in 3D graphics is reviewed as well as relating real world cameras to synthetic cameras through camera calibration. Conventional 2D block tracking methods are reviewed and the expanded to track under pan, tilt and zoom conditions. Two methods of pan/tilt/zoom tracking are developed and then applied to blocks and blobs (connected regions of pixels). A novel offline technique of fitting contours to these track points is then explored with and without the presence of pan, tilt and zoom. A method of updating the multiscale reference block is presented and the tracker is evaluated without block updating (feed forward) and with block updating and position filtering. Experimental results for people following are presented using synthetic ray-traced data with absolute ground truth and real sequences taken with a commercial pan/tilt/zoom camera with hand estimated ground truth. All sequences were processed offline, however, with optimisation it appears to be feasible to implement a real-time solution. Applying position filtering and predictions, using a Kalman filter, improves results and robustness. The application of this method to existing vision techniques is discussed as well as the possible methods for real-time implementation of these algorithms.
author Sinclair, Mark Macdonald
author_facet Sinclair, Mark Macdonald
author_sort Sinclair, Mark Macdonald
title Object tracking with a pan, tilt and zoom camera
title_short Object tracking with a pan, tilt and zoom camera
title_full Object tracking with a pan, tilt and zoom camera
title_fullStr Object tracking with a pan, tilt and zoom camera
title_full_unstemmed Object tracking with a pan, tilt and zoom camera
title_sort object tracking with a pan, tilt and zoom camera
publisher University of Edinburgh
publishDate 2005
url http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.661970
work_keys_str_mv AT sinclairmarkmacdonald objecttrackingwithapantiltandzoomcamera
_version_ 1718312598953263104