DocumentCode :
1721214
Title :
Hidden Markov Model Filter Banks for Dim Target Detection from Image Sequences
Author :
Lai, John ; Ford, Jason J. ; O´Shea, Peter ; Walker, Rodney
Author_Institution :
Queensland Univ. of Technol., Brisbane, QLD
fYear :
2008
Firstpage :
312
Lastpage :
319
Abstract :
The track-before-detect processing technique has been employed in numerous computer vision based algorithms to address the dim target detection problem. In this processing approach, target information (as often provided by an image processing stage that has emphasised target features or suppressed unwanted noise) is integrated over a period of time before the detection decision is made. In this paper, we compare two Hidden Markov Model (HMM) based track-before-detect temporal filtering approaches for dim target detection that use image data pre-processed with a Preserved-Sign morphological filter. The two compared temporal filtering approaches are: a standard HMM filter (recent studies have shown this to be close to the state-of-the-art) and a novel HMM filter bank approach. Results from our simulation study involving various combinations of target speeds and signal-to-noise ratios show that the proposed novel HMM filter bank approach achieves a higher detection rate than the standard HMM approach.
Keywords :
channel bank filters; computer vision; filtering theory; hidden Markov models; image sequences; object detection; computer vision; dim target detection; hidden Markov model filter bank; image sequence; preserved-sign morphological filter; temporal filtering; track-before-detect processing technique; Bayesian methods; Computer vision; Filter bank; Filtering; Hidden Markov models; Image sequences; Object detection; Target tracking; Viterbi algorithm; Working environment noise; HMM; TBD; dim target detection; filter bank; hidden Markov model; track-before-detect;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Image Computing: Techniques and Applications (DICTA), 2008
Conference_Location :
Canberra, ACT
Print_ISBN :
978-0-7695-3456-5
Type :
conf
DOI :
10.1109/DICTA.2008.61
Filename :
4700037
Link To Document :
بازگشت