WWW.DISSERTATION.XLIBX.INFO
FREE ELECTRONIC LIBRARY - Dissertations, online materials
 
<< HOME
CONTACTS



Pages:   || 2 | 3 | 4 | 5 |   ...   | 10 |

«Figure-Ground Segmentation Using Multiple Cues Peter Nordlund Dissertation, May 1998 Computational Vision and Active Perception Laboratory (CVAP) ...»

-- [ Page 1 ] --

KUNGL

VETENSKAP

TEKNISKA

OCH

KONST

HÖGSKOLAN

Department of Numerical Analysis and Computing Science

TRITA-NA-P98/05 • ISSN 1101-2250 • ISRN KTH/NA/P--98/05--SE • CVAP218

Figure-Ground Segmentation

Using Multiple Cues

Peter Nordlund

Dissertation, May 1998

Computational Vision and Active Perception Laboratory (CVAP)

KUNGL

VETENSKAP

TEKNISKA

OCH KONST

HÖGSKOLAN

Department of Numerical Analysis and Computing Science TRITA-NA-P98/05 • ISSN 1101-2250 • ISRN KTH/NA/P--98/05--SE • CVAP218 Figure-Ground Segmentation Using Multiple Cues Peter Nordlund Dissertation, May 1998 Computational Vision and Active Perception Laboratory (CVAP) Akademisk avhandling för teknisk doktorsexamen vid Kungl Tekniska Högskolan Maj 1998 c Peter Nordlund 1998 NADA, KTH, 100 44 Stockholm ISRN KTH/NA/P--98/05--SE ISSN 1101-2250: TRITA-NA-P98/05 ISBN 91-7170-261-X KTH Högskoletryckeriet Stockholm 1998 Abstract The theme of this thesis is figure-ground segmentation. We address the problem in the context of a visual observer, e.g. a mobile robot, moving around in the world and capable of shifting its gaze to and fixating on objects in its environment. We are only considering bottom-up processes, how the system can detect and segment out objects because they stand out from their immediate background in some feature dimension. Since that implies that the distinguishing cues can not be predicted, but depend on the scene, the system must rely on multiple cues. The integrated use of multiple cues forms a major theme of the thesis. In particular, we note that an observer in our real environment has access to 3-D cues. Inspired by psychophysical findings about human vision we try to demonstrate their effectiveness in figure-ground segmentation and grouping also in machine vision.

An important aspect of the thesis is that the problems are addressed from a systems perspective:

it is the performance of the entire system that is important, not that of component algorithms.

Hence, we regard the processes as part of perception-action cycles and investigate approaches that can be implemented for real-time performance.

The thesis begins with a general discussion on the problem of figure-ground segmentation and thereafter the issue of attention is discussed. Experiments showing some implementations of attentional mechanisms with emphasis on real-time performance are presented. We also pro- vide experimental results on closed-loop control of a head-eye system pursuing a moving object.

A system integrating motion detection, segmentation based on motion and segmentation based on stereo is also presented. Maintenance of an already achieved figure-ground segmentation is discussed. We demonstrate how an initially obtained figure-ground segmentation can be maintained by switching to another cue when the initial one disappears. The use of multiple cues is exemplified by a method of segmenting a 2-D histogram using a multi-scale approach. This method is further simplified to suit our real-time performance restrictions. Throughout the thesis the importance of having systems with a capacity of operating continuously on images coming directly from cameras is stressed, thus we prove that our systems consist of a complete processing chain, with no links missing, which is essential when designing working systems.

i Acknowledgments First of all I am grateful to my supervisor Jan-Olof Eklundh, who enthusiastically have guided me through the world of computer vision. Without his support and interest this thesis could not have been made.

I am also very grateful to Tomas Uhlin who has provided lots of invaluable help both as an inspiring collaborator, and also with programming, especially for the MaxVideo and Transputers.

An other person formerly at this laboratory that I wish to especially tribute is my co-author Atsuto Maki, who now has returned to Japan.

Throughout my work at the Computational Vision and Active Perception laboratory I have been working with the head-eye system designed and constructed by Kourosh Pahlavan without which lots of this work had not been possible to carry out.

I would also like to thank Daniel Fagerström for long and interesting discussions over the years, Jonas Gårding for being a constant source of good ideas, Magnus Andersson, Demetrios Betsis, Henrik Christensen, Ambjörn Naeve, Stefan Carlsson, Lars Bretzner, Niklas Nordström, Göran Olofsson, Tony Lindeberg, Kjell Brunnström, Mengxiang Li, Antônio Fransisco, Antonis Argyros, Anders Orebäck, Mattias Lindström, Mårten Björkman, Jorge Dias, Fredrik Bergholm, Pär Fornland, Peter Nillius, Kristian Simsarian and David Jacobs for stimulating discussions.

I would like to thank Harald Winroth and Matti Rendahl for their support in all matters concerning programming and computers. Carsten Bräutigam is another member of the group that I would like to thank for his tremendous patience regarding my L TEX questions.

A I would like to thank Elenore Janson for proof-reading, and for her whole-hearted support during the time of writing this thesis.





In one of my first projects I had the exciting opportunity to collaborate with Jean-Paul Bernoville, Henri Lamarre and Yann Le Guilloux, Michel Dhome, Jean-Tierry Lapreste and Jean-Marc Lavest.

This work has in part been supported by TFR, The Swedish Research Council for Engineering Science. It has during its latter stages also received support from CAS, The Centre for Autonomous Systems. We gratefully acknowledge this support.

Finally I would like to mention all the other members and former members of the group, Birgit Ekberg-Eriksson, Ann Bengtsson, Lars Olsson, Anders Lundquist, Kiyoyuki Chinzei, Kenneth Johansson, Kazutoshi Okamoto, Anna Thorsson, Pascal Grostabussiat, Akihiro Horii, Wei Zhang, Cornelia Fermüller, Yannis Aloimonos, Carla Capurro, Mattias Bratt, Björn Sjödin, Martin Eriksson, Danica Kragic, Lars Petersson, Danny Roobaert, Mikael Rosbacke, Hedvig Sidenbladh, Daniel Svedberg, Dennis Tell, Maria Ögren, Ron Arkin, Patric Jensfelt, Oliver Mertschat, Olle Wijk, Andres Almansa, Svante Barck-Holst, Josef Bigün, Jørgen Bjørnstrup, Henrik Juul-Hansen, Rosario Cretella and Uwe Schneider. Thank you all.

–  –  –

This thesis also exists in a long version with the papers below included. This version of the thesis only contains part one, the summary.

Paper A Nordlund, P. and Uhlin, T. (1996). Closing the loop: Detection and pursuit of a moving object by a moving observer, Image and Vision Computing 14(4): 265–275.

Paper B Uhlin, T., Nordlund, P., Maki, A. and Eklundh, J.-O. (1995a). Towards an active visual observer, Proc. 5th International Conference on Computer Vision, Cambridge, MA, pp. 679–686.

Paper C Uhlin, T., Nordlund, P., Maki, A. and Eklundh, J.-O. (1995b). Towards an active visual observer, Technical Report ISRN KTH/NA/P--95/08--SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden. Shortened version in Proc. 5th International Conference on Computer Vision pp 679–686.

Paper D Maki, A., Nordlund, P. and Eklundh, J.-O. (1998). Attentional Scene Segmentation: Integrating Depth and Motion from Phase, Extended version of tech report ISRN KTH/NA/PSE submitted to Computer Vision and Image Understanding.

Paper E Nordlund, P. and Eklundh, J.-O. (1997b). Towards a seeing agent, First Int. Workshop on Cooperative Distributed Vision, Kyoto, Japan, pp. 93–123. Also in tech report ISRN KTH/NA/PSE.

Paper F Nordlund, P. and Eklundh, J.-O. (1998). Real-time figure-ground segmentation, Technical Report ISRN KTH/NA/P--98/04--SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden. Will be submitted to Int. Conf. on Vision Systems, Jan 99.

When any of the papers above are cited, the citation is in boldface. Some of the papers also exist

as technical reports or conference contribution, here are these references:

Paper A Nordlund, P. and Uhlin, T. (1995). Closing the loop: Pursuing a moving object by a moving observer, Technical Report ISRN KTH/NA/P--95/06--SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden. Shortened version in Proc. 6th International Conf. on Computer Analysis of Images and Patterns. Also in Image and Vision Computing vol. 14, no 4, May 1996, pp 265–275.

Nordlund, P. and Uhlin, T. (1995). Closing the loop: Pursuing a moving object by a moving observer, in V. Klavᡠand R. Šára (eds), Proc. 6th International Conf. on Computer Analysis of c Images and Patterns, Prague, Czech Republic, pp. 400–407.

1 Paper D Maki, A., Nordlund, P. and Eklundh, J.-O. (1996). A computational model of depth-based attention, Technical Report ISRN KTH/NA/P--96/05--SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden. Shortened version in Proc. 13th International Conference on Pattern Recognition.

Maki, A., Nordlund, P. and Eklundh, J.-O. (1996). A computational model of depth-based attention, Proc. 13th International Conference on Pattern Recognition, Vol. IV, IEEE Computer Society Press, Vienna, Austria, pp. 734–739.

Paper E Nordlund, P. and Eklundh, J.-O. (1997). Maintenance of figure-ground segmentation by cue-selection, Technical Report ISRN KTH/NA/P--97/05--SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden. Also in First Int. Workshop on Cooperative Distributed Vision 1997, Kyoto, Japan, pp 93–123.

–  –  –

Introduction Humans looking around in the world can seemingly without effort segment out and distinguish different objects in the world. Despite this, the corresponding capability has largely eluded the efforts of researchers in computer vision. Figure-ground segmentation, or as it is generally considered in computer vision, image segmentation remains a difficult problem even when a more precise definition is given. Of course, it is worth noting that most work in computer vision concerns pictorial vision, i.e. analysis of (usually pre-recorded) images, and not any kind of natural vision, in which the observer directly samples the three dimensional world. One can argue that figure-ground segmentation is different in the two cases. Indeed, the work presented in this thesis supports this view. Nevertheless, one can often assume that very much the same information is available in the two cases and that the discrepancy in performance between humans and machines therefore may appear puzzling.

In this work we are not considering the segmentation or grouping problems in their full scope.

Rather we are investigating the applicability in computer vision of psychophysical results about the human visual system indicating that three dimensional cues play an important role in such processes (see e.g. Nakayama and Silverman, 1986). More generally, there are findings indicating that the percepts, and not only the retinal information as such, are crucial. A recent collection of results in this direction is given in (Rock, 1997), and an example described in Chapter 2.2.

A second and central theme of our work deals with the use of multiple cues. A human observer is normally gifted with a visual apparatus that can process binocular and monocular information as well as motion, color and form (see e.g. Zeki, 1993, for a deliberation on this multifunctional structure). Hence, it is reasonable to conclude that a machine vision system capable of functioning in a real environment analogously should be able to capitalize on whatever information the world offers and also to integrate this information. If we expect to achieve even a fraction of human performance in an unknown world we should consider systems that have similar capabilities.

The third major theme of the thesis concerns the systems perspective. Much of the traditional work in computer vision uses a reductionist approach and in isolation addresses specific visual problems, such as reconstruction of the scene from stereo-pairs of images, segmentation of an image into sets of regions optimizing some criterion, or, recognition of faces or objects seen against a simple background. Such approaches provide us with valuable insights into the limits of machine perception and the feasibility of algorithms. However, often this work only superficially touches upon questions about to what processes or system (possibly a human interpreter) this information is going, or even from where it emanates. Therefore, it does not directly tell us how to design systems that can see in the sense of a human observer or even a seeing robot. In this work, which forms part of the longstanding work on active vision within the CVAP group (see e.g. IJCV, Vol 17:2, Eklundh, 1996), we are interested in processes that work in an integrated system of the latter type, and ultimately in a system that functions in a closed loop with the environment. Truly, not all the work we report here has this emphasis, but the perspective is such. In particular, the work forms an attempt to support the general claim that from a systems perspective many of

31.1. OUTLINE OF OUR APPROACH

the difficult problems arising in machine vision can be solved, and that the algorithms required sometimes are both simple and coarse, and exactly because of that also robust. The ESPRITprojects VAP I and II formed a step towards demonstrating this principle (see e.g. Crowley and Christensen, 1995, especially the introduction). The work described here continues in the same spirit.

1.1 Outline of our approach The main theme in this thesis is figure-ground segmentation. We approach this problem by using multiple cues, especially 3-D cues, in order to utilize the fact that the world is rich on information.

We also apply a systems approach to these problems, in the spirit of earlier work by Pahlavan (1993) and Uhlin (1996) in our laboratory, who had a focus on systems operational in real-time in

interaction with the environment. Our goals have been:

1. To demonstrate that robust figure-ground segmentation can be achieved through the use of 3-D cues.

2. To demonstrate that integration of multiple cues is essential in this context.



Pages:   || 2 | 3 | 4 | 5 |   ...   | 10 |


Similar works:

«Many of the following comments are taken from a sermon given by Dr. Ed DeVires on August 10, 1998 at King James Baptist Church in Arlington, Texas. Some editing has been done for clarity purposes. We have endeavored to insure that the original meaning of the sermon remains intact. All scriptural references’ are from the King James version of the Bible. Let us begin with a basic scripture which teaches us to glorify God in our bodies, as well as our spirits. I COR 6:19-20 What? know ye not...»

«The Trillion-Dollar Vision of Dee Hock “We are at that very point in time when a 400-year-old age is dying and another is struggling to be born a shifting of culture, science, society, and institutions enormously greater than the world has ever experienced. Ahead, the possibility of the regeneration of individuality, liberty, community, and ethics such as the world has never known, and a harmony with nature, with one another, and with the divine intelligence such as the world has never...»

«Jellinek anti-hagiográfiája Jellinek's anti-hagiography MÁRK MÓNIKA – BRETTNER ZSUZSANNA „A tapasztalt utas mögött nem marad nyom.” (Lao-ce) Összefoglalás A korszerű addiktológia alapelvei döntően az alkoholizmussal kapcsolatban alakultak ki. Modern addiktológiai tudás pedig aligha képzelhető el az alkohológiát önálló tudományág rangjára emelő E. M. Jellinek és a nevéhez fűződő betegségkoncepció ismerete nélkül. A jelen tanulmány az alkohológia...»

«Corning® Matrigel® Matrix Frequently Asked Questions. What is Corning Matrigel matrix? Corning Matrigel matrix is a reconstituted basement membrane preparation that is extracted from the Engelbreth-Holm-Swarm (EHS) mouse sarcoma, a tumor rich in extracellular matrix proteins. This material, once isolated, is approximately 60% laminin, 30% collagen IV, and 8% entactin. Entactin is a bridging molecule that interacts with laminin and collagen IV, and contributes to the structural organization of...»

«1 Spring has sprung. Contents Spring has sprung and with that come warmer temperatures, Spring has sprung flowering trees and plants and, hopefully, some migrating birds! Time to dust off the binoculars and go out there and do Thank you, Old Mutual! some birding. Why not go and visit a virgin pentad and do Bird Ringers’ Get-together: Farm Wiese 3-6 May 2012 2 some atlasing? Dwerg maar man! Once again we have an issue that is jam-packed with interesting titbits of information. Jessica gives us...»

«Koncepcja przebiegu zimowej trasy Pomorską Drogą św. Jakuba etapami nr 21 i 22 Łebień – Łeba Izbica Opracowanie przygotowane w ramach projektu „RECReate – Revitalisation of the European Culture Route in the South Baltic Area”, finansowanego z środków Europejskiego Funduszu Rozwoju Regionalnego w ramach Programu Współpracy Transgranicznej Południowy Bałtyk. W latach 2011 – 2014. Lębork 2014 Opracowanie i Redakcja: Tadeusz Krawczyk przy współpracy: J. Bona, E. Boniecka,...»

«Abstracts of MSc theses Completed by ILRI Graduate Fellows 2006–2007 ILRI International Livestock Research Institute Abstracts of MSc theses completed by ILRI Graduate Fellows 2006–2007 ILRI INTERNATIONAL LIVESTOCK RESEARCH INSTITUTE © 2008 ILRI (International Livestock Research Institute). Editing, design and layout—ILRI Publication Unit, Addis Ababa, Ethiopia. Cover image Apollo Habtamu/ILRI. This paper is a compilation of abstracts of MSc theses by ILRI Graduate Fellows during...»

«Financial FDI and Host Countries: New and Old Lessons Linda Goldberg1 Federal Reserve Bank of New York March 6, 2003 Preliminary In the 1990s, foreign direct investment became the largest single source of external finance for many developing countries. For the most part, research into the causes and effects of FDI has mainly focussed on manufacturing and real production activity. This research, interestingly, has been conducted orthogonally to the recent spate of research efforts and methods...»

«EnterText 6.1 FELICIA CHAN Wuxia Cross-dressing and Transgender Identity: The Roles of Brigitte Lin Ching-hsia from Swordsman II to Ashes of Time The act of cross-dressing in the theatrical and cinematic traditions has been consistently employed as a method of transgressing and thus exploring the limits of the boundaries in gender but also in identity and selfhood. In some cases, these transgressions were a response to prevailing institutional, cultural and social restrictions of the day. This...»

«TO BE PUBLISHED IN THE UNITED STATES DISTRICT COURT FOR THE NORTHERN DISTRICT OF IOWA WESTERN DIVISION UNITED STATES OF AMERICA, Plaintiff, No. CR14-4081-MWB vs. REPORT AND RECOMMENDATION ON DEFENDANT’S MOTION TO TERESA ANN SIMEON, SUPPRESS Defendant. I. INTRODUCTION Defendant Teresa Ann Simeon is charged by indictment (Doc. No. 2) with (a) conspiracy to distribute a controlled substance and (b) possession with intent to distribute a controlled substance. She has filed a motion (Doc. No. 23)...»

«~ Thought For The Day ~ ~gathering from the 4 winds~ “come just as you are” Vol. 20 Issue 392 March 27, 2012 Refresh, Restore, Rebuild = Healing Worship Music God Your So GoodPrayer Terry Clark Jesus Mighty FortressLord, I want to set my eyes on the finish line and never lose my focus until I know that I've accomplished the Terry Clark task You have given me to do. I know it's going to take all my spiritual, mental, and physical energies to get this job done. So I am turning to You now,...»

«OFFPRINT FROM Elam and Persia Edited by Javier Álvarez-Mon and Mark B. Garrison Winona Lake, Indiana Eisenbrauns 2011 ç Copyright 2011 by Eisenbrauns. All rights reserved. Printed in the United States of America. www.eisenbrauns.com Library of Congress Cataloging-in-Publication Data Elam and Persia / edited by Javier Álvarez-Mon and Mark B. Garrison p. cm. Includes papers from a meeting of the American Schools of Oriental Research, held in Philadelphia, Pa., 2003. Includes bibliographical...»





 
<<  HOME   |    CONTACTS
2016 www.dissertation.xlibx.info - Dissertations, online materials

Materials of this site are available for review, all rights belong to their respective owners.
If you do not agree with the fact that your material is placed on this site, please, email us, we will within 1-2 business days delete him.