Advanced

Low Complexity Real-Time Feature Extraction Using Image Projections

Kristensen, Fredrik LU ; Cervino, Rafael; Nilsson, Peter LU and Öwall, Viktor LU (2007) Norchip conference, 2007 In [Host publication title missing] p.120-123
Abstract
In this paper it is shown how low complexity image projections can be used to replace the much more memory demanding functions morphology and labeling. The image projections are intended to be used in an automatic real-time surveillance system to detect objects and extract features. The projection unit operates directly on the binary motion mask from the segmentation unit and can extract location, size and center of gravity of the detected objects. To increase the precision, multiple projections are calculated in the Y-direction of the motion mask. To verify the design a demonstrator has been implemented on a Xilinx FPGA, where the effect of different input settings can be evaluated in real-time. Compared to the previous solution with... (More)
In this paper it is shown how low complexity image projections can be used to replace the much more memory demanding functions morphology and labeling. The image projections are intended to be used in an automatic real-time surveillance system to detect objects and extract features. The projection unit operates directly on the binary motion mask from the segmentation unit and can extract location, size and center of gravity of the detected objects. To increase the precision, multiple projections are calculated in the Y-direction of the motion mask. To verify the design a demonstrator has been implemented on a Xilinx FPGA, where the effect of different input settings can be evaluated in real-time. Compared to the previous solution with morpholoqy and labeling, the memory requirement is reduced from O(n(2)) to O(n). (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
[Host publication title missing]
pages
120 - 123
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
Norchip conference, 2007
external identifiers
  • WOS:000257311000028
  • Scopus:50249155819
ISBN
978-1-4244-1516-8
DOI
10.1109/NORCHP.2007.4481053
language
English
LU publication?
yes
id
0aa7ca99-8a82-407a-96a7-318f959c87aa (old id 1033946)
date added to LUP
2008-02-22 12:48:33
date last changed
2016-10-13 04:44:30
@misc{0aa7ca99-8a82-407a-96a7-318f959c87aa,
  abstract     = {In this paper it is shown how low complexity image projections can be used to replace the much more memory demanding functions morphology and labeling. The image projections are intended to be used in an automatic real-time surveillance system to detect objects and extract features. The projection unit operates directly on the binary motion mask from the segmentation unit and can extract location, size and center of gravity of the detected objects. To increase the precision, multiple projections are calculated in the Y-direction of the motion mask. To verify the design a demonstrator has been implemented on a Xilinx FPGA, where the effect of different input settings can be evaluated in real-time. Compared to the previous solution with morpholoqy and labeling, the memory requirement is reduced from O(n(2)) to O(n).},
  author       = {Kristensen, Fredrik and Cervino, Rafael and Nilsson, Peter and Öwall, Viktor},
  isbn         = {978-1-4244-1516-8},
  language     = {eng},
  pages        = {120--123},
  publisher    = {ARRAY(0x8ab3208)},
  series       = {[Host publication title missing]},
  title        = {Low Complexity Real-Time Feature Extraction Using Image Projections},
  url          = {http://dx.doi.org/10.1109/NORCHP.2007.4481053},
  year         = {2007},
}