Adaptive background modeling for land and water composition scenes

Loading...
Thumbnail Image
Supplementary material
Other Title
Authors
Zhao, Jing (Jane)
Pang, Shaoning
Hartill, B.
Sarrafzadeh, Hossein
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2015-09
Supervisors
Type
Conference Contribution - Paper in Published Proceedings
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
marine traffic
marine boat ramps
moving object detection
background modelling
land and water composition scene
dynamic learning rate
ANZSRC Field of Research Code (2020)
Citation
Zhao, J., Pang, S., Hartill. B., & Sarrafzadeh, A. (2015, September). Adaptive Background Modeling for Land and Water Composition Scenes. Vittorio Murino, Enrico Puppo, Gianni Vernazza (Ed.),18th International Conference on Image Analysis and Processing, ICIAP2015 (pp.200-211).
Abstract
In the context of maritime boat ramps surveillance, this paper proposes an Adaptive Background Modeling method for Land and Water composition scenes (ABM-lw) to interpret the traffic of boats passing across boat ramps. We compute an adaptive learning rate to account for changes on land and water composition scenes, in which the portion of water changes over time due to tidal dynamics and other environmental influences. Experimental comparative tests and quantitative performance evaluations of real-world boat-flow monitoring traffic sequences demonstrate the benefits of the proposed algorithm.
Publisher
International Conference on Image Analysis and Processing (ICIAP)
Link to ePress publication
DOI
Copyright holder
International Conference on Image Analysis and Processing (ICIAP)
Copyright notice
All rights reserved
Copyright license
Available online at
This item appears in: