Abstract: Robots
are becoming increasingly important to human life. Apart from
their long well established achievements in industrial applications,
one that is currently emerging is domestic robot application.
However, robotic vision using visual information is still
considered unsuccessful. Recovering 3D shape from its 2D image by
means of stereo fails when the object is textured less.
Therefore, methods such as structured light stripe, or tactile
sensor are commonly used in order to resolve ambiguity. In
contrast, vision remains the richest human source of information.
For this reason, this research tries to explore this visual
information to recover an object's depth in order for a robot to
manipulate and avoid obstacles. A few preliminary results of
stereo reconstruction with homography and Shape from Shading (SFS) are
shown.
About the Speaker: Effendi
is a postrgraduate research student with the department of Electrical
and Computer Systems Engineering at Monash University Clayton.
Location Change: This seminar will be held in Room 132, Building 72
Visitors Information
A map
of the Clayton Campus of Monash University indicates the venue,
Building 72, and visitor parking on the top floor of the North carpark,
Building 76.
Limited
reserved parking spaces are available for visitors attending the
seminar. (Requests for parking should be made in advance)