Automatic Extraction and Tracking of Complex Contours

Koichi Hata, Jun Ohya, Fumio Kishino, Ryouhei Nakatsu

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we propose an algorithm to extract and track complex contours with occlusions such as the contours of the human body. In this algorithm, complex contours are assumed to be composed of contour segments which have smooth variation of the intensity gradient normal to the contour direction. Moreover, the contour segments are modeled using B splines, and contours in the image are extracted and tracked by the contour segments. In the first frame, contour segments are extracted using only the edge pixels. In the tracking of contour segments of the next frame, we use Snakes. For frames after the second frame, the contour segments are redetected using the tracking result and edge pixels. After that, extraction and tracking are repeatedly applied to each frame. Moreover, a method of classification of contour segments which is based on movement is described and the possibility of human action description is investigated. Finally, experimental and classification results obtained by means of this algorithm on synthesized and real images are given.

Original languageEnglish
Pages (from-to)40-49
Number of pages10
JournalSystems and Computers in Japan
Volume30
Issue number8
Publication statusPublished - 1999 Jul
Externally publishedYes

Fingerprint

Pixels
Splines
Pixel
Snakes
B-spline
Occlusion
Gradient

Keywords

  • Active contour model (Snakes)
  • Akaike's information criterion
  • Automatic system
  • B spline
  • Contour extraction and tracking

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science

Cite this

Hata, K., Ohya, J., Kishino, F., & Nakatsu, R. (1999). Automatic Extraction and Tracking of Complex Contours. Systems and Computers in Japan, 30(8), 40-49.

Automatic Extraction and Tracking of Complex Contours. / Hata, Koichi; Ohya, Jun; Kishino, Fumio; Nakatsu, Ryouhei.

In: Systems and Computers in Japan, Vol. 30, No. 8, 07.1999, p. 40-49.

Research output: Contribution to journalArticle

Hata, K, Ohya, J, Kishino, F & Nakatsu, R 1999, 'Automatic Extraction and Tracking of Complex Contours', Systems and Computers in Japan, vol. 30, no. 8, pp. 40-49.
Hata, Koichi ; Ohya, Jun ; Kishino, Fumio ; Nakatsu, Ryouhei. / Automatic Extraction and Tracking of Complex Contours. In: Systems and Computers in Japan. 1999 ; Vol. 30, No. 8. pp. 40-49.
@article{7577f1e2259c435ca761ba35c3a6866f,
title = "Automatic Extraction and Tracking of Complex Contours",
abstract = "In this paper, we propose an algorithm to extract and track complex contours with occlusions such as the contours of the human body. In this algorithm, complex contours are assumed to be composed of contour segments which have smooth variation of the intensity gradient normal to the contour direction. Moreover, the contour segments are modeled using B splines, and contours in the image are extracted and tracked by the contour segments. In the first frame, contour segments are extracted using only the edge pixels. In the tracking of contour segments of the next frame, we use Snakes. For frames after the second frame, the contour segments are redetected using the tracking result and edge pixels. After that, extraction and tracking are repeatedly applied to each frame. Moreover, a method of classification of contour segments which is based on movement is described and the possibility of human action description is investigated. Finally, experimental and classification results obtained by means of this algorithm on synthesized and real images are given.",
keywords = "Active contour model (Snakes), Akaike's information criterion, Automatic system, B spline, Contour extraction and tracking",
author = "Koichi Hata and Jun Ohya and Fumio Kishino and Ryouhei Nakatsu",
year = "1999",
month = "7",
language = "English",
volume = "30",
pages = "40--49",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "8",

}

TY - JOUR

T1 - Automatic Extraction and Tracking of Complex Contours

AU - Hata, Koichi

AU - Ohya, Jun

AU - Kishino, Fumio

AU - Nakatsu, Ryouhei

PY - 1999/7

Y1 - 1999/7

N2 - In this paper, we propose an algorithm to extract and track complex contours with occlusions such as the contours of the human body. In this algorithm, complex contours are assumed to be composed of contour segments which have smooth variation of the intensity gradient normal to the contour direction. Moreover, the contour segments are modeled using B splines, and contours in the image are extracted and tracked by the contour segments. In the first frame, contour segments are extracted using only the edge pixels. In the tracking of contour segments of the next frame, we use Snakes. For frames after the second frame, the contour segments are redetected using the tracking result and edge pixels. After that, extraction and tracking are repeatedly applied to each frame. Moreover, a method of classification of contour segments which is based on movement is described and the possibility of human action description is investigated. Finally, experimental and classification results obtained by means of this algorithm on synthesized and real images are given.

AB - In this paper, we propose an algorithm to extract and track complex contours with occlusions such as the contours of the human body. In this algorithm, complex contours are assumed to be composed of contour segments which have smooth variation of the intensity gradient normal to the contour direction. Moreover, the contour segments are modeled using B splines, and contours in the image are extracted and tracked by the contour segments. In the first frame, contour segments are extracted using only the edge pixels. In the tracking of contour segments of the next frame, we use Snakes. For frames after the second frame, the contour segments are redetected using the tracking result and edge pixels. After that, extraction and tracking are repeatedly applied to each frame. Moreover, a method of classification of contour segments which is based on movement is described and the possibility of human action description is investigated. Finally, experimental and classification results obtained by means of this algorithm on synthesized and real images are given.

KW - Active contour model (Snakes)

KW - Akaike's information criterion

KW - Automatic system

KW - B spline

KW - Contour extraction and tracking

UR - http://www.scopus.com/inward/record.url?scp=0042127017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042127017&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0042127017

VL - 30

SP - 40

EP - 49

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 8

ER -