Tag: M.Mirmehdi

SPHERE – a Sensor Platform for HEalthcare in a Residential Environment

Posted on by mc13306

Sphere Project main objective is to develop a multimodality sensing platform, based on low-cost devices: ranging from on-body sensors, environmental sensors and video based sensors. The SPHERE platform is aiming at efficiently tackling the problem of healthcare monitoring at home. Its vision is not to develop fundamentally-new sensors for individual health conditions but rather to impact all these healthcare needs simultaneously through data-fusion and pattern-recognition from a common platform of non-medical/environmental sensors at home. The system will be general-purpose, low-cost and hence scalable. Sensors will be entirely passive, requiring no action by the user and hence suitable for all patients including the most vulnerable. A central hypothesis is that deviations from a user’s established pattern of behaviour in their own home have particular, unexploited, diagnostic value.

Computer Vision in Sphere: WP2 (Vision Team)

The main objectives of WP2 consist of developing an efficient, real-time multi-camera system for activity monitoring in the home environment. The system will be based on low cost cameras and depth sensors to estimate client’s position and to analyse their movements to extract features for use for action understanding and activity recognition.

The vision team are developing a video based action recognition and multi-user tracking system for the house environment. This solution will allow the system to estimate the activity/inactivity level of the user during their daily life. The platform has been tested in SPHERE’s house and integrated with the other sensor systems; providing a unique multisensory system for data collection. On-going video work includes a collaboration with respiratory physicians in Bristol developing and validating video-based systems for monitoring breathing.

vision

Related Projects

Online quality assessment of human movements from skeleton data
The objective of this project is to evaluate the quality of human movements from visual information. This has use in a broad range of applications, such as diagnosis and rehabilitation.

Real Time RGB-D tracker: DS-KCF 
The objective of this project is develop a real time RGB-D tracker based on Kernelised Correlation Filters

WP2 Publications

2015
  • Massimo Camplani, Sion Hannuna,  Majid Mirmehdi, Dima Damen, Adeline Paiement, Lili Tao, Tilo Burghardt. Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. British Machine Vision Conference, September 2015.
  • N. Zhu, T. Diethe, M. Camplani, L. Tao, A. Burrows, N. Twomey, D. Kaleshi, M. Mirmehdi, P. Flach, I. Craddock, Bridging eHealth and the Internet of Things: The SPHERE Project, IEEE Intelligent Systems, (to appear).
  • A Multi-modal Sensor Infrastructure for Healthcare in a Residential Environment. P. Woznowski, X. Fafoutis, T. Song, S. Hannuna, M. Camplani, L. Tao, A. Paiement, E. Mellios, M. Haghighi, N. Zhu, G. Hilton, D. Damen, T. Burghardt, M. Mirmehdi, R. Piechocki, D. Kaleshi and I. Craddock. IEEE International Conference on Communications (ICC), Workshop on ~ICT-enabled services and technologies for eHealth and Ambient Assisted Living.
2014
  • A. Paiment, L. Tao, S. Hannuna, M. Camplani, D. Damen and M. Mirmehdi, Majid (2014). Online quality assessment of human movement from skeleton data. British Machine Vision Conference (BMVC), Nottingham, UK

Object Modelling From Sparse And Misaligned 3D and 4D Data

Posted on by apaiement

Object modelling from 3D and 4D sparse and misaligned data has important applications in medical imaging, where visualising and characterising the shape of, e.g., an organ or tumor, is often needed to establish a diagnosis or to plan surgery. Two common issues in medical imaging are the presence of large gaps between the 2D image slices which make a dataset, and misalignments between these slices, due to patient’s movements between their respective acquisitions. These gaps and misalignments make the automatic analysis of the data particularly challenging. In particular, they require interpolation and registration in order to recover a complete shape of the object. This work focuses on the integrated registration, segmentation and interpolation of such sparse and misaligned data. We developed a framework which is flexible enough to model objects of various shapes, from data having arbitrary spatial configuration and from a variety of imaging modalities (e.g. CT-scan, MRI).

ISISD: Integrated Segmentation and Interpolation of Sparse Data

We present a new, general purpose, level set framework which can handle sparse data, by simultaneously segmenting the data and interpolating automatically its gaps. In this new framework, the level set implicit function is interpolated by Radial Basis Functions (RBFs), and its interface can propagate in a sparse volume, using data information where available, and RBF based interpolation of its speeds in the gaps. Any segmentation criteria may be used, thus allowing the framework to process any imaging modalities. Different modalities can be handled simultaneously due to the method interpolating the level set contour rather than the image intensities. This new level set framework benefits from a better robustness to noise in the images, and can segment sparse volumes by integrating the shape of the objects in the gaps.

More details and results may be found here.

The method is described in:

  • 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.

IReSISD: Integrated Registration, Segmentation and Interpolation of Sparse Data

A new registration method, Registration_SA_LAalso based on level set, has been developed and integrated to the previous RBF interpolated level set framework. Thus, the new framework can correct misalignments in the data, at the same time as it segments and interpolates it. The integration of all three processes of registration, segmentation and interpolation into a same framework allows them to benefit from each others. Notably registration exploits the shape information provided by the segmentation stage, in order to be robust to local minima and to limited intersections between the images of a dataset.

More details and results may be found here.

The method is described in:

  • Adeline Paiement, Majid Mirmehdi, Xianghua Xie, Mark Hamilton, Registration and Modeling from Spaced and Misaligned Image Volumes. Submitted to IEEE Transactions on Image Processing.

The tables in the article are reported in the graphs below:

stack1

stack2

slice1slice2

slice3

slice4

jaccard

Published Work

  1. 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.
  2. 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, 173 Kbytes.

Download Software

The latest version of the code for ISISD and IReSISD can be downloaded here (Version 1.3).

Earlier versions:

Exploratory analysis in phMRI

Posted on by dagrafiotis

Working in collaboration with the Psychopharmacology Unit, we are investigating and developing exploratory, data-driven methods for the analysis of pharmacological MRI (phMRI). The data produced in these studies can be thought of as 3D movies of the brain, where we seek to discover both the temporal and spatial effects of a drug, especially in cases where the expected neural response is not well established.

 

       

Generic motion based object segmentation for assisted navigation

Posted on by papadoma

CASBliP – Computer Aided System for the Blind

casIn the CASBliP project, a robust approach to annotating independently moving objects captured by head mounted stereo cameras that are worn by an ambulatory (and visually impaired) user is proposed. Initially, sparse optical flow is extracted from a single image stream, in tandem with dense depth maps. Then, using the assumption that apparent movement generated by camera egomotion is dominant, flow corresponding to independently moving objects (IMOs) is robustly segmented using MLESAC. Next, the mode depth of the feature points defining this flow (the foreground) are obtained by aligning them with the depth maps. Finally, a bounding box is scaled proportionally to this mode depth and robustly fit to the foreground points such that the number of inliers is maximised. The system runs at around 8 fps and has been tested by visually impaired volunteers.

For more information, see CASBliP – Computer Aided System for the Blind.

Active contours

Posted on by hc0639

Majid Mirmehdi, Xianghua Xie, Ronghua Yang

Active contours finding boundaries in the brainActive contour models, commonly known as snakes, have been widely used for object localisation, shape recovery, and visual tracking due to their natural handling of shape variations. The introduction of the Level Set method into snakes has greatly enhanced their potential in real world applications.

Since 2002, we have developed some novel active contour models. The first one aims to bridge (image gradient) boundary based approach and region-based approach. In this work, a level set based geometric snake, enhanced for more tolerance towards weak edges and noise, is introduced. It is based on the principle of the conjunction of the traditional gradient flow forces with new region constraints. We refer to this as the Region-aided Geometric Snake or RAGS. The image gradient provides local information of object boundaries, while the region information offers global definition of boundaries. In this framework, the region constrains can be conveniently customerised and plugged into the snake model.

The second model, called Charged Contour Model (CCM),is a migration of Charged Particle Model (CPM) into the active contour framework. The basic idea is to introduce particle dynamics into contour based deformable models. CCM performs better than CPM in the sense that it guarantees closed contours, i.e. it eliminates the ambiguities in contour reconstruction. Also, CCM is much more efficient. In comparison to geodesic snake, CCM is more robust to weak edges and less sensitive to noise interference.

The third model, CACE (Charged Active Contour model based on Electrostatics), is a further development of the CCM. The snake, implicitly embedded in level sets, propagates under the joint influence of a boundary attraction force and a boundary competition force. Its vector field dynamically adapts by updating itself when a contour reaches a boundary (which differs from CCM). The model is then more invariant to initialisation and possesses better convergence abilities. Analytical and comparative results are presented on synthetic and real images.

MAC model is a result of our most recent effort in developing new active contour models. The proposed external force field that is based on magnetostatics and hypothesized magnetic interactions between the active contour and object boundaries. The major contribution of the method is that the interaction of its forces can greatly improve the active contour in capturing complex geometries and dealing with difficult initializations, weak edges and broken boundaries. The proposed method is shown to achieve significant improvements when compared against six well-known and state-of-the-art shape recovery methods, including the geodesic snake, the generalized version of GVF snake, the combined geodesic and GVF snake, and the charged particle model.

For more information, please see our active contours site.