| |
|
Image correspondence/registration is the problem of automatically matching/aligning features in one image to their corresponding features in
another image. Although reasonably successful solutions have found in restricted image domains, it has been shown
that a general solution does not exist, due to the ambiguity in the matching process.
PVG researchers: M. Toews, R. Brooks, F. Riggi and T. Arbel
Collaborators: D. L. Collins, X. Morandi, R. Comeau and D. Precup
MRI-ultrasound registration for the correction of intra-operative brain shift
Researchers: Tal Arbel, Xavier Morandi and D. Louis Collins
In this project, we explore the use of acquiring intra-operative ultrasound (US)
images for the quantification of and the correction for non-linear brain deformations. We develop a multi-modal
image registration strategy that involves (i) building "predicted-ultrasound" prior to surgery based on segmented MRI
and (ii) automatically matching the predicted US images to real intra-operative US images. By providing the surgeon
with a set of updated MRI images for surgical guidance, surgical procedures can be performed with higher precision
thus improving surgical outcomes and overall patient care.
For more information, see the project website.
Entropy-of-likelihood feature selection for image correspondence
Researchers: Matthew Toews and Tal Arbel
We have developed a means of
evaluating which image points can be matched with the least ambiguity, given a particular image domain and matching
process. Based on this development, we envision improving the reliability, generality and speed of matching, as well
as increasing our understanding of the correspondence task.
MAP local histogram estimation for image registration
Fundamental matrix estimation via TIP: Transfer of Invariant Parameters
Generalizing inverse compositional image alignment
Fast image alignment using anytime algorithms
|
|
The ill-posedness of many computer vision problems stems from the loss of information incurred when a 3D scene is projected on a 2D image.
This causes ambiguities to arise. For instance, in the context of object recognition, from certain points of view, different objects can be
undistinguishable. Active vision methods can be used to alleviate such ambiguities. These methods actively change the sensor parameters
(e.g. viewpoint, focus, etc.) in order to facilitate disambiguation and converge to a correct solution to the vision problem.
PVG researchers: T. Arbel, C. Laporte and R. Brooks
Collaborators: S. Skaff, F. P. Ferrie and J. J. Clark
Entropy based gaze planning
Researchers: Tal Arbel and Frank P. Ferrie
This work introduces a probabilistic active object recognition system capable of identifying an object from a known
database based on the information gathered sequentially from different points of view, by moving the camera in curvilinear
arcs around a viewsphere centered about the object. The notion of entropy map is introduced as a means of encoding prior knowledge
about the discriminability of objects as a function of viewing position. Empirical results show how entropy maps can be used
to guide a sensor towards informative viewpoints, leading to confident assertions about the identity of the unknown object in a
short number of steps.
For more information, see the project website.
Interactive visual dialog
Researchers: Tal Arbel and Frank P. Ferrie
In this work, an interactive engine was built that recognizes objects waved in front of a television camera by a human.
The context is that of a supermarket checkout scenario in which objects presented by the operator to a camera are automatically tallied.
In order to improve the recognition, the system provides feedback to the operator about which objects it currently believes he might be holding
with an indication as to how each of these objects should next be presented to the system to minimize ambiguity. Experiments show that this
human-machine dialog mechanism leads to accurate recognition results in a small number of iterations.
For more information, see the project website.
Active Bayesian colour constancy with non-uniform sensors
Efficient viewpoint selection for active object recognition and pose estimation
Researchers: Catherine Laporte, Rupert Brooks and Tal Arbel
In this work, a new criterion for viewpoint selection in the context of active Bayesian object recognition and pose
estimation was developped. Recognition and pose estimation are jointly performed by probabilistically fusing successive
observations, taking into account the dependencies between the observed scene, the data and the observation parameters, thereby
acquiring knowledge about the structure of the observed objects. Based on the system's current belief state, the new observation
selection criterion associates high utility with observations whose outcome predictably facilitates distinction between pairs of
competing hypotheses. The algorithm has relatively low complexity and lends itself to various simplifications.
Experiments show that this approach achieves
comparable recognition performance to the widely used mutual information maximization approach at a much lower computational
cost.
For more information, see the project website.
|
|
Statistical models of image formation and image appearance are essential for several applications including classification,
segmentation, indexing and simulation. Such models describe how entities behave given some imaging process, as well as the
possible variations in behaviour with their relative probabilities.
PVG researchers: M. Toews, R. Harmouche, C. Laporte and T. Arbel
Collaborators: D. L. Collins, D. Arnold, S. Francis and J. J. Clark
Bayesian MS lesion classification modeling
regional and local spatial information
Researchers: Rola Harmounche, D. Louis Collins, Douglas Arnold,
Simon Francis and Tal Arbel
A fully automatic Bayesian method for multiple sclerosis (MS) lesion classification is presented. The posterior probability distribution is used to determine voxel labels for regular tissue as well as T1-hypointense lesions and T2-hyperintense lesions, and to provide experts with a confidence level in the classification. Spatial variability in intensity distributions over the brain is explicitly modeled by segmenting the brain into distinct anatomical regions and building the likelihood distributions of each tissue class in each region based on multimodal magnetic resonance image (MRI) intensities. Local smoothness is ensured by incorporating neighboring voxel information in the prior probability via Markov random fields. Validation is done for both lesion types on real data from ten patients with MS. Lesion classification results are compared to five expert raters and two other automatic classification techniques, using volume count and overlap. The classification results obtained with the presented method are comparable to manual classifications in both the cerebral hemispheres and posterior fossa.
For more information, see the project
website.
Detection over viewpoint via the Object Class Invariant
Statistical parts-based appearance modeling of inter-subject variability
Multi-dimensional scatterer distribution models for ultrasound image simulation
|
|
