Probabilistic color matching and tracking of human subjects

Abdeq M. Abdi, Mendel Schmiedekamp, Shashi Phoha

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Pattern discovery algorithms based on the computational mechanics (CM) method have been shown to succinctly describe underlying patterns in data through the reconstruction of minimum probabilistic finite state automata (PFSA). We apply the CM approach toward the tracking of human subjects in real time by matching and tracking the underlying color pattern as observed from a fixed camera. Objects are extracted from a video sequence, and then raster scanned, decomposed with a one-dimensional Haar wavelet transform, and symbolized with the aid of a red-green-blue (RGB) color cube. The clustered causal state algorithm is then used to reconstruct the corresponding PFSA. Tracking is accomplished by generating the minimum PFSA for each subsequent frame, followed by matching the PFSAs to the previous frame. Results show that there is an optimum alphabet size and segmentation of the RGB color cube for efficient tracking.

Original languageEnglish (US)
Pages (from-to)4926-4935
Number of pages10
JournalApplied Optics
Volume49
Issue number26
DOIs
StatePublished - Sep 10 2010

Fingerprint

Color matching
Finite automata
Computational mechanics
computational mechanics
Color
color
alphabets
Wavelet transforms
Cameras
wavelet analysis
cameras

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Electrical and Electronic Engineering

Cite this

Abdi, Abdeq M. ; Schmiedekamp, Mendel ; Phoha, Shashi. / Probabilistic color matching and tracking of human subjects. In: Applied Optics. 2010 ; Vol. 49, No. 26. pp. 4926-4935.
@article{a66bee95eafd485dab1c3976563eff50,
title = "Probabilistic color matching and tracking of human subjects",
abstract = "Pattern discovery algorithms based on the computational mechanics (CM) method have been shown to succinctly describe underlying patterns in data through the reconstruction of minimum probabilistic finite state automata (PFSA). We apply the CM approach toward the tracking of human subjects in real time by matching and tracking the underlying color pattern as observed from a fixed camera. Objects are extracted from a video sequence, and then raster scanned, decomposed with a one-dimensional Haar wavelet transform, and symbolized with the aid of a red-green-blue (RGB) color cube. The clustered causal state algorithm is then used to reconstruct the corresponding PFSA. Tracking is accomplished by generating the minimum PFSA for each subsequent frame, followed by matching the PFSAs to the previous frame. Results show that there is an optimum alphabet size and segmentation of the RGB color cube for efficient tracking.",
author = "Abdi, {Abdeq M.} and Mendel Schmiedekamp and Shashi Phoha",
year = "2010",
month = "9",
day = "10",
doi = "10.1364/AO.49.004926",
language = "English (US)",
volume = "49",
pages = "4926--4935",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "The Optical Society",
number = "26",

}

Probabilistic color matching and tracking of human subjects. / Abdi, Abdeq M.; Schmiedekamp, Mendel; Phoha, Shashi.

In: Applied Optics, Vol. 49, No. 26, 10.09.2010, p. 4926-4935.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Probabilistic color matching and tracking of human subjects

AU - Abdi, Abdeq M.

AU - Schmiedekamp, Mendel

AU - Phoha, Shashi

PY - 2010/9/10

Y1 - 2010/9/10

N2 - Pattern discovery algorithms based on the computational mechanics (CM) method have been shown to succinctly describe underlying patterns in data through the reconstruction of minimum probabilistic finite state automata (PFSA). We apply the CM approach toward the tracking of human subjects in real time by matching and tracking the underlying color pattern as observed from a fixed camera. Objects are extracted from a video sequence, and then raster scanned, decomposed with a one-dimensional Haar wavelet transform, and symbolized with the aid of a red-green-blue (RGB) color cube. The clustered causal state algorithm is then used to reconstruct the corresponding PFSA. Tracking is accomplished by generating the minimum PFSA for each subsequent frame, followed by matching the PFSAs to the previous frame. Results show that there is an optimum alphabet size and segmentation of the RGB color cube for efficient tracking.

AB - Pattern discovery algorithms based on the computational mechanics (CM) method have been shown to succinctly describe underlying patterns in data through the reconstruction of minimum probabilistic finite state automata (PFSA). We apply the CM approach toward the tracking of human subjects in real time by matching and tracking the underlying color pattern as observed from a fixed camera. Objects are extracted from a video sequence, and then raster scanned, decomposed with a one-dimensional Haar wavelet transform, and symbolized with the aid of a red-green-blue (RGB) color cube. The clustered causal state algorithm is then used to reconstruct the corresponding PFSA. Tracking is accomplished by generating the minimum PFSA for each subsequent frame, followed by matching the PFSAs to the previous frame. Results show that there is an optimum alphabet size and segmentation of the RGB color cube for efficient tracking.

UR - http://www.scopus.com/inward/record.url?scp=77957605133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957605133&partnerID=8YFLogxK

U2 - 10.1364/AO.49.004926

DO - 10.1364/AO.49.004926

M3 - Article

VL - 49

SP - 4926

EP - 4935

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 26

ER -