Contour Tracking in 2D Images Using Particle Filtering

Angelova, D and Konstantinova, P and Mihaylova, L (2007) Contour Tracking in 2D Images Using Particle Filtering. In: Proc. of the International Radar Symposium, 2007-09-052007-09-07.

PDF (Contour_extraction_IRS07.pdf)

Download (563kB)


A Monte Carlo algorithm for extracting contours in 2D images is proposed in this paper. A multiple model Particle Filter (PF) for progressive contour growing (tracking) from a starting point is designed, accounting for the convex, noncircular form of delineated areas. The algorithm relies on image intensity gradients as measurements and requires information about four manually selected points: the seed point, the starting point, arbitrarily selected on the contour, and two additional points, bounding the measurement formation area around the contour. The filter performance is studied by segmenting contours from series of simulated ultrasound medical images and Ground Penetrating Radar (GPR) images.

Item Type: Contribution to Conference (Paper)
Journal or Publication Title: Proc. of the International Radar Symposium
Uncontrolled Keywords: /dk/atira/pure/researchoutput/libraryofcongress/qa75
Departments: Faculty of Science and Technology > School of Computing & Communications
ID Code: 1185
Deposited By: Dr L Mihaylov
Deposited On: 04 Feb 2008 08:52
Refereed?: Yes
Published?: Published
Last Modified: 25 Jan 2020 05:57

Actions (login required)

View Item View Item