You are here
A hybrid color‐based foreground object detection method for automated marine surveillance
| Title: | A hybrid color‐based foreground object detection method for automated marine surveillance. |
 164 views 24 downloads |
|---|---|---|
| Name(s): |
Furht, Borko, creator Kalva, Hari, creator Marques, Oge, creator Culibrk, Dubravko, creator Socek, Daniel, creator |
|
| Type of Resource: | text | |
| Genre: | Article | |
| Issuance: | single unit | |
| Date Issued: | 2005 | |
| Publisher: | Springer Berlin/Heidelberg | |
| Physical Description: | text/pdf [9p] | |
| Language(s): | English | |
| Identifier: | 358420 (digitool), FADT358420 (IID), fau:2123 (fedora), 10.1007/11558484 (doi) | |
| FAU Department/College: | Computer & Electrical Engineering and Computer Science College of Engineering | |
| Note(s): |
This manuscript was published by Springer Berlin/Heidelberg as Daniel Socek, Dubravko Culibrk, Oge Marques, Hari Kalva, Borko Furht. (2005). A hybrid color‐based foreground object detection method for automated marine surveillance, pp. 340‐347 book chapter in Advanced Concepts for Intelligent Vision Systems, volume 3708, Lecture Notes in Computer Science Book Series. This paper proposes a hybrid foreground object detection method suitable for the marine surveillance applications. Our approach combines an existing foreground object detection method with an image color segmentation technique to improve accuracy. The foreground segmentation method employs a Bayesian decision framework, while the color segmentation part is graph-based and relies on the local variation of edges. We also establish the set of requirements any practical marine surveillance algorithm should fulfill, and show that our method conforms to these. Experiments show good results in the domain of marine surveillance sequences. |
|
| Subject(s): |
Computer vision. Automatic tracking. Digital video. Image processing. Optical pattern recognition. |
|
| Persistent Link to This Record: | http://purl.flvc.org/fcla/dt/358420 | |
| Restrictions on Access: | ©2005 Springer Berlin/Heidelberg | |
| Host Institution: | FAU |
