A Genetic Programming (GP) method uses multiple runs,
data decomposition stages, to evolve a hierarchical set
of vehicle detectors for the automated inspection of
infrared line scan imagery that has been obtained by a
low flying aircraft. The performance on the scheme
using two different sets of GP terminals (all are
rotationally invariant statistics of pixel data) is
compared on 10 images. The discrete Fourier transform
set is found to be marginally superior to the simpler
statistics set that includes an edge detector. An
analysis of detector formulae provides insight on
vehicle detection principles. In addition, a promising
family of algorithms that take advantage of the GP
method's ability to prescribe an advantageous solution
architecture is developed as a post-processor. These
algorithms selectively reduce false alarms by exploring
context, and determine the amount of contextual
information that is required for this task.
%0 Journal Article
%1 howard:2006:PRL
%A Howard, Daniel
%A Roberts, Simon C.
%A Ryan, Conor
%D 2006
%J Pattern Recognition Letters
%K Discrete Fourier Machine Method Object Reconnaissance, Vehicle algorithms, detection, genetic of programming, stages, transform, vision
%N 11
%P 1275--1288
%R doi:10.1016/j.patrec.2005.07.025
%T Pragmatic Genetic Programming strategy for the problem
of vehicle detection in airborne reconnaissance
%V 27
%X A Genetic Programming (GP) method uses multiple runs,
data decomposition stages, to evolve a hierarchical set
of vehicle detectors for the automated inspection of
infrared line scan imagery that has been obtained by a
low flying aircraft. The performance on the scheme
using two different sets of GP terminals (all are
rotationally invariant statistics of pixel data) is
compared on 10 images. The discrete Fourier transform
set is found to be marginally superior to the simpler
statistics set that includes an edge detector. An
analysis of detector formulae provides insight on
vehicle detection principles. In addition, a promising
family of algorithms that take advantage of the GP
method's ability to prescribe an advantageous solution
architecture is developed as a post-processor. These
algorithms selectively reduce false alarms by exploring
context, and determine the amount of contextual
information that is required for this task.
@article{howard:2006:PRL,
abstract = {A Genetic Programming (GP) method uses multiple runs,
data decomposition stages, to evolve a hierarchical set
of vehicle detectors for the automated inspection of
infrared line scan imagery that has been obtained by a
low flying aircraft. The performance on the scheme
using two different sets of GP terminals (all are
rotationally invariant statistics of pixel data) is
compared on 10 images. The discrete Fourier transform
set is found to be marginally superior to the simpler
statistics set that includes an edge detector. An
analysis of detector formulae provides insight on
vehicle detection principles. In addition, a promising
family of algorithms that take advantage of the GP
method's ability to prescribe an advantageous solution
architecture is developed as a post-processor. These
algorithms selectively reduce false alarms by exploring
context, and determine the amount of contextual
information that is required for this task.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Howard, Daniel and Roberts, Simon C. and Ryan, Conor},
biburl = {https://www.bibsonomy.org/bibtex/23f8002961864c5d87e5b1fe3414820de/brazovayeye},
doi = {doi:10.1016/j.patrec.2005.07.025},
interhash = {e07cd686688b1f109b0bc217a5e85508},
intrahash = {3f8002961864c5d87e5b1fe3414820de},
journal = {Pattern Recognition Letters},
keywords = {Discrete Fourier Machine Method Object Reconnaissance, Vehicle algorithms, detection, genetic of programming, stages, transform, vision},
month = {August},
note = {Evolutionary Computer Vision and Image Understanding},
number = 11,
pages = {1275--1288},
timestamp = {2008-06-19T17:41:51.000+0200},
title = {Pragmatic Genetic Programming strategy for the problem
of vehicle detection in airborne reconnaissance},
volume = 27,
year = 2006
}