University of Bristol > Visual Information Laboratory > Adeline Paiement
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 analysis and assessment of the quality of movements from RGB-depth images, with applications in rehabilitation and elderly people monitoring.
I also completed my PhD at the University of Bristol, 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.
- August 2014: The release version of the ISISD and IReSISD code is now ready for download here.
- July 2014: Our article "Online quality assessment of human movement from skeleton data" has been accepted in BMVC 2014. Its dataset is available for download here.
- May 2014: I have been awarded the PhD degree by the University of Bristol with the Faculty of Engineering Commendation.
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.
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.
Journal PapersAdeline 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. [External information]
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 reviewAdeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton: Registration and Modeling from Spaced and Misaligned Image Volumes. IEEE Transactions on Pattern Analysis and Machine Intelligence, Under review, Submitted in September 2014.
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. IEEE Transactions on Pattern Analysis and Machine Intelligence, Under review, Submitted in December 2014.
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), Under review, Submitted in February 2015.
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, Under review, Submitted in March 2015.
Peer-reviewed Conference PapersPrzemyslaw 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, Accepted in March 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 PapersC. 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 AbstractsAdeline 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. Rank Prize Symposium on Medical Imaging Meets Computer Vision, March 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.
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.
Department of Computer Science
+44 (0)117 33 15233