33 / 64
of asset matching using three different image
feature descriptors. Methods to reduce
feature extraction and matching complexity
were developed. Performance and accuracy
tradeoffs were studied, domain specific
problems were identified, and optimizations
for mobile platforms were made. The results
show that the proposed methods reduce the
complexity of asset matching by 67% when
compared to the matching process using
unmodified image feature
descriptors. The next phase
of the project will focus on
developing augmented reality
extensions to overlay server
health data on the asset being
monitored.
Asset management is a time consuming and
error prone process. Information Technology
(IT) personnel typically perform this task
manually by visually inspecting the assets
to identify any misplaced assets. If this
process is automated and provided to IT
personnel it would prove very useful in
maintaining and keeping track of assets in a
server rack. A mobile/tablet based solution
is developed to automate the process of
asset identification. The asset management
application on the tablet captures the images
of assets and searches an annotated database
to identify the asset. We evaluate the
matching performance and time complexity
Asset Identification Using Image
Descriptors
Hari Kalva, PI
l
Students: Reena Fridel
and Oscar Figeruoa
Asset management is a time consuming and error prone process.
Information Technology (IT) personnel typically perform this task manually
by visually inspecting the assets to identify any misplaced assets. If this
process is automated and provided to IT personnel it would prove very
useful in maintaining and keeping track of assets in a server rack. A
mobile/tablet based solution is developed to automate the process of asset
identification. The asset management application on the tablet captures the
images of assets and searches an annotated database to identify the asset.
We evaluate the matching performance and time complexity of asset
matching using three different image feature descriptors. Methods to reduce
feature extraction and matching
complexity
were
developed.
Performa ce an accuracy tradeoffs
were studied, domain specific
problems were identified, and
optimizations for mobile platforms
were made. The results show that
the proposed methods reduce the
complexity of asset matching by
67% when compared to the
m tching process using unmodified
image feature descriptors. The next
phase of the project will focus on
developing
augmented
reality
extensions to verlay server health
data on the asset being monitored.
p ro j e ct 2
Industry
partner
interested in
this project:
Avocent/
Emerson
3 3