Dr Jean-Yves Guillemaut

Research Fellow

Email:
Phone: Work: 01483 68 3958
Room no: 10 AB 05

Further information

Publications

Highlights

  • Hilton ADM, Guillemaut J-Y, Kilner JJ, Grau O, Thomas G. (2011) '3D-TV Production from Conventional Cameras for Sports Broadcast'. IEEE IEEE Transactions Broadcasting, 57 (2), pp. 462-476.
    doi: 10.1109/TBC.2011.2131870
  • Guillemaut J-Y, Hilton A. (2011) 'Joint Multi-Layer Segmentation and Reconstruction for Free-Viewpoint Video Applications'. Springer International Journal of Computer Vision, 93 (1), pp. 73-100.
    doi: 10.1007/s11263-010-0413-z
    Full text is available at: http://epubs.surrey.ac.uk/110829/
  • Kilner J, Starck J, Guillemaut JY, Hilton A. (2009) 'Objective quality assessment in free-viewpoint video production'. ELSEVIER SCIENCE BV SIGNAL PROCESSING-IMAGE COMMUNICATION, 24 (1-2), pp. 3-16.
    doi: 10.1016/j.image.2008.10.004
    Full text is available at: http://epubs.surrey.ac.uk/527084/
  • Guillemaut J-Y, Illingworth J. (2008) 'The normalised image of the absolute conic and its application for zooming camera calibration'. PERGAMON-ELSEVIER SCIENCE LTD PATTERN RECOGNITION, 41 (12), pp. 3624-3635.
    doi: 10.1016/j.patcog.2008.05.021
    Full text is available at: http://epubs.surrey.ac.uk/527083/

Journal articles

  • Kim H, Guillemaut J-Y, Takai T, Sarim M, Hilton A. (2012) 'Outdoor Dynamic 3D Scene Reconstruction'. IEEE IEEE Transactions on Circuits and Systems for Video Technology, 22 (11), pp. 1611-1622.
    doi: 10.1109/TCSVT.2012.2202185
  • Casas D, Tejera M, Guillemaut J-Y, Hilton A. (2012) 'Parametric animation of performance-captured mesh sequences'. Wiley Computer Animation and Virtual Worlds, 23 (2), pp. 101-111.
    doi: 10.1002/cav.1430
  • Hilton ADM, Guillemaut J-Y, Kilner JJ, Grau O, Thomas G. (2011) '3D-TV Production from Conventional Cameras for Sports Broadcast'. IEEE IEEE Transactions Broadcasting, 57 (2), pp. 462-476.
    doi: 10.1109/TBC.2011.2131870
  • Sarim M, Hilton A, Guillemaut J-Y. (2011) 'Temporal trimap propagation for video matting using inferential statistics'. Proceedings - International Conference on Image Processing, ICIP, , pp. 1745-1748.
    doi: 10.1109/ICIP.2011.6115797
  • Guillemaut J-Y, Hilton A. (2011) 'Joint Multi-Layer Segmentation and Reconstruction for Free-Viewpoint Video Applications'. Springer International Journal of Computer Vision, 93 (1), pp. 73-100.
    doi: 10.1007/s11263-010-0413-z
    Full text is available at: http://epubs.surrey.ac.uk/110829/
  • Kilner J, Starck J, Guillemaut JY, Hilton A. (2009) 'Objective quality assessment in free-viewpoint video production'. ELSEVIER SCIENCE BV SIGNAL PROCESSING-IMAGE COMMUNICATION, 24 (1-2), pp. 3-16.
    doi: 10.1016/j.image.2008.10.004
    Full text is available at: http://epubs.surrey.ac.uk/527084/
  • Guillemaut J-Y, Illingworth J. (2008) 'The normalised image of the absolute conic and its application for zooming camera calibration'. PERGAMON-ELSEVIER SCIENCE LTD PATTERN RECOGNITION, 41 (12), pp. 3624-3635.
    doi: 10.1016/j.patcog.2008.05.021
    Full text is available at: http://epubs.surrey.ac.uk/527083/
  • Guillemaut JY, Aguado AS, Illingworth J. (2005) 'Using points at infinity for parameter decoupling in camera calibration'. IEEE COMPUTER SOC IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 27 (2), pp. 265-270.
    doi: 10.1109/TPAMI.2005.41
    Full text is available at: http://epubs.surrey.ac.uk/527082/

Conference papers

  • Guillemaut J-Y, Hilton A. (2012) 'Space-time joint multi-layer segmentation and depth estimation'. Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012, , pp. 440-447.
    doi: 10.1109/3DIMPVT.2012.44
  • Casas D, Tejera M, Guillemaut J-Y, Hilton A. (2012) '4D parametric motion graphs for interactive animation'. Proceedings - I3D 2012: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, , pp. 103-110.
    doi: 10.1145/2159616.2159633
  • Imre E, Guillemaut J-Y, Hilton A. (2012) 'Through-the-lens multi-camera synchronisation and frame-drop detection for 3D reconstruction'. Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012, , pp. 395-402.
    doi: 10.1109/3DIMPVT.2012.31
  • Casas D, Tejera M, Guillemaut J-Y, Hilton A. (2011) 'Parametric control of captured mesh sequences for real-time animation'. Springer Lecture Notes in Computer Science: Motion in Games, Edinburgh, UK: MIG 2011: 4th International Conference 7060, pp. 242-253.
    doi: 10.1007/978-3-642-25090-3
  • Imre E, Guillemaut J-Y, Hilton A. (2011) 'Calibration of nodal and free-moving cameras in dynamic scenes for post-production'. Proceedings - 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011, , pp. 260-267.
    doi: 10.1109/3DIMPVT.2011.40
    Full text is available at: http://epubs.surrey.ac.uk/110185/

    Abstract

    In film production, many post-production tasks require the availability of accurate camera calibration information. This paper presents an algorithm for through-the-lens calibration of a moving camera for a common scenario in film production and broadcasting: The camera views a dynamic scene, which is also viewed by a set of static cameras with known calibration. The proposed method involves the construction of a sparse scene model from the static cameras, with respect to which the moving camera is registered, by applying the appropriate perspective-n-point (PnP) solver. In addition to the general motion case, the algorithm can handle the nodal cameras with unknown focal length via a novel P2P algorithm. The approach can identify a subset of static cameras that are more likely to generate a high number of scene-image correspondences, and can robustly deal with dynamic scenes. Our target applications include dense 3D reconstruction, stereoscopic 3D rendering and 3D scene augmentation, through which the success of the algorithm is demonstrated experimentally. © 2011 IEEE.

  • Guillemaut J, Sarim M, Hilton A. (2010) 'Stereoscopic Content Production of Complex Dynamic Scenes Using a Wide-Baseline Monoscopic Camera Set-Up'. Hong Kong: Proc. International Conference on Image Processing (ICIP 2010), Special Session on Image Processing for Stereo Digital Cinema Production, pp. 9-12.
    doi: 10.1109/ICIP.2010.5652901
    Full text is available at: http://epubs.surrey.ac.uk/111048/

    Abstract

    Conventional stereoscopic video content production requires use of dedicated stereo camera rigs which is both costly and lacking video editing flexibility. In this paper, we propose a novel approach which only requires a small number of standard cameras sparsely located around a scene to automatically convert the monocular inputs into stereoscopic streams. The approach combines a probabilistic spatio-temporal segmentation framework with a state-of-the-art multi-view graph-cut reconstruction algorithm, thus providing full control of the stereoscopic settings at render time. Results with studio sequences of complex human motion demonstrate the suitability of the method for high quality stereoscopic content generation with minimum user interaction.

  • Wang T, Guillemaut J, Collomosse J. (2010) 'Multi-label Propagation for Coherent Video Segmentation and Artistic Stylization'. IEEE Proceedings of Intl. Conf. on Image Proc. (ICIP), Hong Kong: ICIP, pp. 3005-3008.
    doi: 10.1109/ICIP.2010.5649291
    Full text is available at: http://epubs.surrey.ac.uk/605300/

    Abstract

    We present a new algorithm for segmenting video frames into temporally stable colored regions, applying our technique to create artistic stylizations (e.g. cartoons and paintings) from real video sequences. Our approach is based on a multilabel graph cut applied to successive frames, in which the color data term and label priors are incrementally updated and propagated over time. We demonstrate coherent segmentation and stylization over a variety of home videos.

  • Imre HE, Guillemaut J-Y, Hilton ADM. (2010) 'Moving Camera Registration for Multiple Camera Setups in Dynamic Scenes'. Proceedings of the 21st British Machine Vision Conference, Aberystwyth, UK: BMVC 2010
    doi: 10.5244/C.24.38
    Full text is available at: http://epubs.surrey.ac.uk/111014/

    Abstract

    Many practical applications require an accurate knowledge of the extrinsic calibration (\ie, pose) of a moving camera. The existing SLAM and structure-from-motion solutions are not robust to scenes with large dynamic objects, and do not fully utilize the available information in the presence of static cameras, a common practical scenario. In this paper, we propose an algorithm that addresses both of these issues for a hybrid static-moving camera setup. The algorithm uses the static cameras to build a sparse 3D model of the scene, with respect to which the pose of the moving camera is estimated at each time instant. The performance of the algorithm is studied through extensive experiments that cover a wide range of applications, and is shown to be satisfactory.

  • Guillemaut J-Y, Kilner J, Hilton A. (2010) 'Robust Graph-Cut Scene Segmentation and Reconstruction for Free-Viewpoint Video of Complex Dynamic Scenes'. IEEE 2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), Kyoto, JAPAN: 12th IEEE International Conference on Computer Vision, pp. 809-816.
    doi: 10.1109/ICCV.2009.5459299
    Full text is available at: http://epubs.surrey.ac.uk/527100/
  • Kilner J, Guillemaut J-Y, Hilton A. (2010) 'Summarised hierarchical Markov models for speed-invariant action matching'. 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, Kyoto: IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1065-1072.
    doi: 10.1109/ICCVW.2009.5457584
    Full text is available at: http://epubs.surrey.ac.uk/527102/

    Abstract

    Action matching, where a recorded sequence is matched against, and synchronised with, a suitable proxy from a library of animations, is a technique for generating a synthetic representation of a recorded human activity. This proxy can then be used to represent the action in a virtual environment or as a prior on further processing of the sequence. In this paper we present a novel technique for performing action matching in outdoor sports environments. Outdoor sports broadcasts are typically multi-camera environments and as such reconstruction techniques can be applied to the footage to generate a 3D model of the scene. However due to poor calibration and matting this reconstruction is of a very low quality. Our technique matches the 3D reconstruction sequence against a predefined library of actions to select an appropriate high quality synthetic representation. A hierarchical Markov model combined with 3D summarisation of the data allows a large number of different actions to be matched successfully to the sequence in a rate-invariant manner without prior segmentation of the sequence into discrete units. The technique is applied to data captured at rugby and soccer games. ©2009 IEEE.

  • Kilner J, Guillemaut J-Y, Hilton A. (2010) '3D action matching with key-pose detection'. 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1-8.
    doi: 10.1109/ICCVW.2009.5457724
    Full text is available at: http://epubs.surrey.ac.uk/527101/

    Abstract

    This paper addresses the problem of human action matching in outdoor sports broadcast environments, by analysing 3D data from a recorded human activity and retrieving the most appropriate proxy action from a motion capture library. Typically pose recognition is carried out using images from a single camera, however this approach is sensitive to occlusions and restricted fields of view, both of which are common in the outdoor sports environment. This paper presents a novel technique for the automatic matching of human activities which operates on the 3D data available in a multi-camera broadcast environment. Shape is retrieved using multi-camera techniques to generate a 3D representation of the scene. Use of 3D data renders the system camera-pose-invariant and allows it to work while cameras are moving and zooming. By comparing the reconstructions to an appropriate 3D library, action matching can be achieved in the presence of significant calibration and matting errors which cause traditional pose detection schemes to fail. An appropriate feature descriptor and distance metric are presented as well as a technique to use these features for key-pose detection and action matching. The technique is then applied to real footage captured at an outdoor sporting event. ©2009 IEEE.

  • Sarim M, Hilton A, Guillemaut J-Y, Takai T, Kim H. (2010) 'NATURAL IMAGE MATTING FOR MULTIPLE WIDE-BASELINE VIEWS,'. Hong Kong: ICIP (International Conference on Image Processing)
  • Sarim M, Hilton A, Guillemaut J-Y, Kim H, Takai T. (2010) 'Wide-Baseline Multi-View Video Segmentation For 3D Reconstruction'. ACM Proceedings of the 1st international workshop on 3D video processing, Firenze, Italy: 3DVP 2010 Workshop: MM '10 ACM Multimedia Conference, pp. 13-16.
  • Sarim M, Hilton A, Guillemaut J, Kim H, Takai T. (2010) 'Multiple view wide-baseline trimap propagation for natural video matting'. IEEE Proc. European Conference on Visual Media Production (CVMP 2010), London, UK: European Conference on Visual Media Production (CVMP 2010), pp. 82-91.
    doi: 10.1109/CVMP.2010.18
  • Sarim M, Hilton A, Guillemaut J-Y, Takai T, Kim H. (2010) 'NATURAL IMAGE MATTING FOR MULTIPLE WIDE-BASELINE VIEWS'. IEEE 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, Hong Kong, PEOPLES R CHINA: IEEE International Conference on Image Processing, pp. 2233-2236.
    doi: 10.1109/ICIP.2010.5651610
  • Kim H, Sarim M, Takai T, Guillemaut J-Y, Hilton A. (2010) 'Dynamic 3D Scene Reconstruction in Outdoor Environments'. IEEE In Proc. IEEE Symp. on 3D Data Processing and Visualization, France: 3DPVT
  • Sarim M, Hilton A, Guillemaut J-Y. (2009) 'Wide-baseline matte propagation for indoor scenes'. CVMP 2009 - The 6th European Conference for Visual Media Production, , pp. 195-204.
    doi: 10.1109/CVMP.2009.6
  • Sarim M, Hilton A, Guillemaut J-Y, Kim H. (2009) 'Non-parametric natural image matting'. Proceedings - International Conference on Image Processing, ICIP, , pp. 3213-3216.
    doi: 10.1109/ICIP.2009.5414367
  • Sarim M, Hilton A, Guillemaut J-Y. (2009) 'Alpha matte estimation of natural images using local and global template correspondence'. 2009 International Conference on Emerging Technologies, ICET 2009, , pp. 229-234.
    doi: 10.1109/ICET.2009.5353170
  • Sarim M, Hilton A, Guillemaut J. (2009) 'Non-parametric patch based video matting'. British Machine Vision Association London, UK: Proc. British Machine Vision Conference (BMVC 2009)
    Full text is available at: http://epubs.surrey.ac.uk/111020/

    Abstract

    In computer vision, matting is the process of accurate foreground estimation in images and videos. In this paper we presents a novel patch based approach to video matting relying on non-parametric statistics to represent image variations in appearance. This overcomes the limitation of parametric algorithms which only rely on strong colour correlation between the nearby pixels. Initially we construct a clean background by utilising the foreground object’s movement across the background. For a given frame, a trimap is constructed using the background and the last frame’s trimap. A patch-based approach is used to estimate the foreground colour for every unknown pixel and finally the alpha matte is extracted. Quantitative evaluation shows that the technique performs better, in terms of the accuracy and the required user interaction, than the current state-of-the-art parametric approaches.

  • Guillemaut J-Y, Drbohlav O, Illingworth J, Sara R, Ranchordas AN, Araujo HJ. (2008) 'A maximum likelihood surface normal estimation algorithm for Helmholtz stereopsis'. INSTICC-INST SYST TECHNOLOGIES INFORMATION CONTROL & COMMUNICATION VISAPP 2008: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 2, Funchal, PORTUGAL: 3rd International Conference on Computer Vision Theory and Applications, pp. 352-359.
  • Guillemaut J-Y, Kilner J, Starck J, Hilton A. (2007) 'Dynamic feathering: Minimising blending artefacts in view-dependent rendering'. IET Conference Publications, (534 CP)
    doi: 10.1049/cp:20070043
  • Guillemaut J-Y, Hilton A, Starck J, Kilner J, Grau O, Godin G, Hebert P, Masuda T, Taubin G. (2007) 'A Bayesian framework for simultaneous matting and 3D reconstruction'. IEEE COMPUTER SOC 3DIM 2007: Sixth International Conference on 3-D Digital Imaging and Modeling, Proceedings, Montreal, CANADA: 6th International Conference on 3-D Digital Imaging and Modeling, pp. 167-174.
    Full text is available at: http://epubs.surrey.ac.uk/527099/
  • Guillemaut J-Y, Kittler J, Sadeghi MT, Christmas WJ, MartinezTrinidad JF, Ochoa JAC, Kittler J. (2006) 'General pose face recognition using frontal face model'. SPRINGER-VERLAG BERLIN PROGRESS IN PATTERN RECOGNITON, IMAGE ANALYSIS AND APPLICATIONS, PROCEEDINGS, Cancun, MEXICO: 11th Iberoamerican Conference in Pattern Recognition 4225, pp. 79-88.
  • Guillemaut JY, Drbohlav O, Sara R, Illingworth J. (2004) 'Helmholtz stereopsis on rough and strongly textured surfaces'. IEEE COMPUTER SOC 2ND INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGS, Thessaloniki, GREECE: 2nd International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVI 2004), pp. 10-17.
    doi: 10.1109/TDPVT.2004.1335135
    Full text is available at: http://epubs.surrey.ac.uk/527098/

    Abstract

    Helmholtz Stereopsis (HS) has recently been explored as a promising technique for capturing shape of objects with unknown reflectance. So far, it has been widely applied to objects of smooth geometry and piecewise uniform Bidirectional Reflectance Distribution Function (BRDF). Moreover, for nonconvex surfaces the inter-reflect ion effects have been completely neglected. We extend the method to surfaces which exhibit strong texture, nontrivial geometry and are possibly nonconvex. The problem associated with these surface features is that Helmholtz reciprocity is apparently violated when point-based measurements are used independently to establish the matching constraint as in the standard HS implementation. We argue that the problem is avoided by computing radiance measurements on image regions corresponding exactly to projections of the same surface point neighbourhood with appropriate scale. The experimental results demonstrate the success of the novel method proposed on real objects.

  • Brujic-Okretic V, Guillemaut J, Hitchin L, Michielen M, Parker G. (2004) 'Real-time scene reconstruction for remote vehicle navigation'. Nashboro Press Geometric Modeling and Computing: Seattle 2003, Seattle, USA: SIAM Conference on Geometric Design and Computing, pp. 113-123.
  • Guillemaut JY, Aguado AS, Illingworth J, Kawada S. (2003) 'Calibration of a zooming camera using the Normalized Image of the Absolute Conic'. IEEE COMPUTER SOC FOURTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, BANFF, CANADA: 4th International Conference on 3-D Digital Imaging and Modeling (3-DIM 2003), pp. 225-232.
    doi: 10.1109/IM.2003.1240254
    Full text is available at: http://epubs.surrey.ac.uk/527097/
  • Brujic-Okretic V, Guillemaut J, Hitchin L, Michielen M, Parker G. (2003) 'Remote vehicle manoeuvring using augmented reality'. Guildford, UK: International Conference on Visual Information Engineering (VIE 2003), pp. 186-189.
  • Guillemaut J, Aguado A, Illingworth J. (2002) 'Using points at infinity for parameter decoupling in camera calibration'. Cardiff, UK: British Machine Vision Conference (BMVC) 1, pp. 263-272.
    Full text is available at: http://epubs.surrey.ac.uk/527096/

Book chapters

  • Hilton A, Guillemaut J, Kilner J, Grau O, Thomas G. (2010) 'Free-Viewpoint Video for TV Sport Production'. in Ronfard R, Taubin G (eds.) Image and Geometry Processing for 3-D Cinematography Springer 5
    doi: 10.1007/978-3-642-12392-4_4

Theses and dissertations

  • Guillemaut J. (2006) Contributions to Image-Based Object Reconstruction: Geometric and Photometric Aspects. University of Surrey, Guildford, UK
    Full text is available at: http://epubs.surrey.ac.uk/527103/

Stay Connected

Contact Us

Accessibility | Contacting the University | Cookies | Disclaimer | Freedom of Information

© University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom. +44 (0)1483 300800

Page Owner: ees1jg
Page Created: Wednesday 22 September 2010 11:53:56 by lb0014
Last Modified: Tuesday 4 October 2011 15:23:44 by lb0014
Expiry Date: Thursday 22 December 2011 11:53:10
Assembly date: Tue Mar 26 22:38:48 GMT 2013
Content ID: 38002
Revision: 3
Community: 1379