University of Bristol > Visual Information Laboratory > Adeline Paiement


Adeline Paiement


About Me

I am a post-doctoral researcher in the Visual Information Laboratory at the University of Bristol. I am working within the SPHERE (Sensor Platform for HEalthcare in a Residential Environment) project on automatic methods for the analysis of movements from RGB-depth images, with applications in rehabilitation and elderly people monitoring.

I also completed my PhD at the University of Bristol in February 2014, under the supervision of Prof. Majid Mirmehdi. My PhD research was on the modelling of 3D and 4D objects from multimodal sparse and misaligned data in the frame of the analysis of cardiac cine MRIs.

Me

Latest News

Research Projects

Movement's quality assessment

Skeleton-free body pose estimation for online quality assessment of human movement

This project extends our online quality assessment method for human movement, by replacing the skeleton-based features with features that are extracted directly from the depth image. This allows handling view-points and movements that are not currently supported by the skeleton-based method due to limitations of the skeleton tracking algorithm. A CNN is used to select relevant depth features and to estimate body pose in the pose-space used by the quality assessment method.

Movement's quality assessment

Online quality assessment of human movement from depth based skeleton

The aim of this project is to estimate the quality of movements from Kinect skeleton data and on a frame-by-frame basis. We combine a manifold learning technique (for dimensionality reduction) and statistical models in order to asesss the quality of movements by comparison with a model of normal movement. This methodology may be used to evaluate the gait on stairs, or sitting and standing movements, in order, for example, to assist clinicians in assessing pathologies and monitoring rehabilitation.

Examples of modelling

Integrated Registration, Segmentation, and Interpolation of Sparse and Misaligned 3D/4D Data (IReSISD)

This project aims at investigating new methods to model 3D and 4D objects from datasets made of several, misaligned, acquisitions which do not span the whole imaged volume, and which have arbitrary spatial configurations. I developed a new level set framework which can inherently handle sparse data thanks to the interpolation of the level set implicit function by Radial Basis Functions. This new framework also integrates a registration method, in order to deal with misalignments in the data. It has been applied succesfully to medical images made of 2D image slices having various positions and orientations and gap sizes, as well as to 3D point clouds produced by the Kinect camera.

IReSISD was my PhD project. My PhD thesis can be downloaded here.

Publications

Journal Papers

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Registration and Modeling from Spaced and Misaligned Image Volumes. IEEE Transactions on Image Processing, In press.

Lili Tao, Adeline Paiement, Dima Damen, Majid Mirmehdi, Sion Hannuna, Massimo Camplani, Tilo Burghardt, Ian Craddock: A Comparative Study of Pose Representation and Dynamics Modelling for Online Motion Quality Assessment. Computer Vision and Image Understanding - SI: Assistive Computer Vision and Robotics, Vol. 148, pp. 136-152, 2016. [link]

Adeline Paiement: Integrated Registration, Segmentation, and Interpolation for 3D/4D Sparse Data. Electronic Letters on Computer Vision and Image Analysis - SI: Recent PhD Thesis Dissemination (2014), Vol. 14, Issue 3, pp. 6-8, 2015. [link|pdf]

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Integrated Segmentation and Interpolation of Sparse Data. IEEE Transactions on Image Processing, Vol. 23, Issue 1, pp. 110-125, 2014. [link]

C. M. Boily, T. Padmanabhan, A. Paiement: Regular Black Hole Motion and Stellar Orbital Resonances. Monthly Notices of the Royal Astronomical Society, Vol. 383, Issue 4, pp. 1619-1638, 2008.

Currently under review

Massimo Camplani, Adeline Paiement, Majid Mirmehdi, Dima Damen, Sion Hannuna, Tilo Burghardt, Lili Tao: Multiple Human Detection and Tracking from RGB-D Data: A Survey. Computer Vision and Image Understanding, Under review.

Peer-reviewed Conference Papers

Ben Crabbe, Adeline Paiement, Sion Hannuna, Majid Mirmehdi: Skeleton-free body pose estimation from depth images for movement analysis. ChaLearn LaP workshop at ICCV, December 2015. [pdf]

Przemyslaw Woznowski, Xenofon Fafoutis, Terence Song, Sion Hannuna, Massimo Camplani, Lili Tao, Adeline Paiement, Evangelos Mellios, Mo Haghighi, Ni Zhu, Geoffrey Hilton, Dima Damen, Tilo Burghardt, Majid Mirmehdi, Robert Piechocki, Dritan Kaleshi, Ian Craddock: A Multi-modal Sensor Infrastructure for Healthcare in a Residential Environment. IEEE ICC Workshop on ICT-enabled services and technologies for eHealth and Ambient Assisted Living, June 2015.

Adeline Paiement, Lili Tao, Sion Hannuna, Massimo Camplani, Dima Damen, Majid Mirmehdi: Online quality assessment of human movement from skeleton data. Proceedings of British Machine Vision Conference (BMVC) 2014, September 2014. [pdf]

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Simultaneous Level Set interpolation and segmentation of short- and long-axis MRI. Proceedings of Medical Image Understanding and Analysis (MIUA) 2010, pp. 267-272. July 2010. [pdf]

Other Conference Papers

C. M. Boily, T. Padmanabhan, A. Paiement: Black Hole Motion as Catalyst of Orbital Resonances. Dynamical Evolution of Dense Stellar Systems, Proceedings of the International Astronomical Union Symposium No. 246, Vol. 3, pp. 311-315. 2007.

Conference Abstracts

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Automatic 3D and 4D modelling from spaced and misaligned tomographic data - Application to the analysis of cine cardiac MRIs. IPEM Cardiovascular MRI, March 2015.

Adeline Paiement, Lili Tao, Sion Hannuna, Massimo Camplani, Dima Damen, Majid Mirmehdi: Online quality assessment of human movement from skeleton data - Extended abstract. Proceedings of British Machine Vision Conference (BMVC) 2014, September 2014. [pdf]

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Integrated Registration, Segmentation, and Interpolation of Sparse Medical Data. BVI Young Researchers' Colloquium, June 2013.

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Integrated Registration, Segmentation and Interpolation of Cardiac Cine MRI. British Society of Cardiovascular Imaging Annual Spring Meeting, May 2013.

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Integrated Registration, Segmentation and Interpolation of Sparse Medical Data. Rank Prize Symposium on Medical Imaging Meets Computer Vision, March 2013.

Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Integrated Segmentation and Interpolation of Cardiac MRI. BVI Young Researchers' Colloquium, June 2011.

Isabelle Scholl, Shadia Rifai Habbal, Adeline Paiement: On the Automated Detection of Coronal Holes in Space-Based Data. American Geophysical Union Spring Meeting, May 2008.

Google Scholar

Contact

Department of Computer Science
University of Bristol
1.15 Merchant Venturers Building
Woodland Road, BRISTOL, BS8 1UB
United Kingdom

csatmp@bristol.ac.uk

+44 (0)117 33 15233


updated: 01/06/2016