Share Email Print

Proceedings Paper

Polynomial background estimation using visible light video streams for robust automatic detection in a maritime environment
Author(s): Tanja Y. C. van Valkenburg-van Haarst; Krispijn A. Scholte
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

For naval surveillance, automatic detection of surface objects, like vessels, in a maritime environment is an important contribution of the Electro-Optical (EO) sensor systems on board. Based on previous research using single images, a background estimation approach using low-order polynomials is proposed for the automatic detection of objects in a maritime environment. The polynomials are fitted to the intensity values in the image after which the deviation between the fitted intensity values and the measured intensity values are used for detection. The research presented in this paper, includes the time information by using video streams instead of single images. Hereby, the level of fusing time information and the number of frames necessary for stable detection and tracking behaviour are analysed and discussed. The performance of the detection approach is tested on a, during the fall of 2007, collected extensive dataset of maritime pictures in the Mediterranean Sea and in the North Sea on board of an Air Defence Command frigate, HNLMS Tromp.

Paper Details

Date Published: 30 September 2009
PDF: 8 pages
Proc. SPIE 7482, Electro-Optical Remote Sensing, Photonic Technologies, and Applications III, 748209 (30 September 2009); doi: 10.1117/12.830212
Show Author Affiliations
Tanja Y. C. van Valkenburg-van Haarst, CAMS - Force Vision (Netherlands)
Krispijn A. Scholte, CAMS - Force Vision (Netherlands)

Published in SPIE Proceedings Vol. 7482:
Electro-Optical Remote Sensing, Photonic Technologies, and Applications III
Gary J. Bishop; Keith L. Lewis; Gary W. Kamerman; John D. Gonglewski; Richard C. Hollins; Ove K. Steinvall; Thomas J. Merlet, Editor(s)

© SPIE. Terms of Use
Back to Top