MSc Dissertation Proposal 2016/2017
The use of endoscopes in medical diagnosis and in minimal invasive surgery is a common technique adopted by doctors. The endoscopes have several limitations related with weak depth perception. Additionally, organs and tissues are non-rigid bodies which difficult the 3D reconstruction using standard methods. Plenoptic cameras allow to estimate depth from a single image by analysis of their epipolar geometry, which may allow to overcome some of the current endoscope limitations.
The objectives of this work are:
1.
- Plenoptic camera model
definition and calibration.
2.
- Depth range limits definition
for a plenoptic camera.
3.
- Depth estimation using the
camera epipolar geometry.
4. - Mosaicking and 3D reconstruction from a
tubular shape and comparison with standard methods.
N.A.
ISR / IST
The use of endoscopes in medical diagnosis and in minimal invasive
surgery is a common technique adopted by doctors. The endoscopes have several
limitations that include limited field of view and reduced capacity to perceive
shape. These limitations are related with a weak depth perception.
The monocular endoscope is the most common. The strategies to obtain
a 3D reconstruction are based on shape from motion and shape from shading.
Nonetheless, the 3D reconstruction is very complex since the scene being observed
presents organs and tissues that are highly deformable bodies.
Plenoptic cameras give more information than conventional cameras.
Namely, these cameras give information about the direction and contribution of
each ray to the total amount of light captured on an image. These cameras allow
to estimate depth from a single image by analysis of
their epipolar geometry, which may allow to overcome
some of the current endoscope limitations.
There are other types of endoscopes, like the stereo endoscope, that
has a similar setup to the setup of the plenoptic
camera. These stereo endoscopes are recent and not well studied, but their
small baseline requires computing image correspondences and still do not give
the desired depth range for medical applications. The depth range for plenoptic cameras is unknown for plenoptic
cameras. Thus, we want to define the depth range limits for a plenoptic camera.
Plenoptic cameras make a trade-off between spatial and angular
resolution which normally results in images with low spatial resolution,
similarly to the endoscope images. To overcome this limitation we aim to create
a lightfield mosaic and perform a 3D reconstruction
from a tubular shape mimicking the conditions that the endoscope camera has to
face.
The workplan consists on the study of the plenoptic camera model and calibration, and implementation of a standard mosaicking and depth estimation algorithms for conventional and plenoptic cameras. These methods will be applied to real datasets acquired on a tubular shape structure. The results for the plenoptic camera will be compared to the results from a conventional camera.
More MSc dissertation proposals on Computer and Robot Vision in:
http://omni.isr.ist.utl.pt/~jag