Motion Estimation and Segmentation of Natural Phenomena

Research output: Contribution to conferencePaper

70 Downloads (Pure)

Abstract

Dense motion estimation for dynamic natural phenomena (water, smoke, fire, etc.) is a significant open problem. Current approaches tend to be either general, giving poor results, or specialise in one phenomenon and fail to generalise. Segmentation of phenomena is also an open problem. This paper describes an approach to estimate dense motion for dynamic phenomena that is simple, general, and which yields state of the art results. We use our dense motion field to segment phenomena to above state of the art levels. We demonstrate our contributions using lab-based video, video from a public dataset, and from the internet.
Original languageEnglish
Publication statusPublished - 4 Sep 2018
Event29th British Machine Vision Conference 2018 - Northumbria University, Newcastle
Duration: 3 Sep 20186 Sep 2018
http://bmvc2018.org/

Conference

Conference29th British Machine Vision Conference 2018
Abbreviated titleBMVC 2018
CityNewcastle
Period3/09/186/09/18
Internet address

Keywords

  • natutal phenomena, tracking, segmentation

Cite this

Chen, D., Li, W., & Hall, P. (2018). Motion Estimation and Segmentation of Natural Phenomena. Paper presented at 29th British Machine Vision Conference 2018, Newcastle, .

Motion Estimation and Segmentation of Natural Phenomena. / Chen, Da; Li, Wenbin; Hall, Peter.

2018. Paper presented at 29th British Machine Vision Conference 2018, Newcastle, .

Research output: Contribution to conferencePaper

Chen, D, Li, W & Hall, P 2018, 'Motion Estimation and Segmentation of Natural Phenomena' Paper presented at 29th British Machine Vision Conference 2018, Newcastle, 3/09/18 - 6/09/18, .
Chen D, Li W, Hall P. Motion Estimation and Segmentation of Natural Phenomena. 2018. Paper presented at 29th British Machine Vision Conference 2018, Newcastle, .
Chen, Da ; Li, Wenbin ; Hall, Peter. / Motion Estimation and Segmentation of Natural Phenomena. Paper presented at 29th British Machine Vision Conference 2018, Newcastle, .
@conference{6a69c678d27c4aa7bb0d37ad42acd8b9,
title = "Motion Estimation and Segmentation of Natural Phenomena",
abstract = "Dense motion estimation for dynamic natural phenomena (water, smoke, fire, etc.) is a significant open problem. Current approaches tend to be either general, giving poor results, or specialise in one phenomenon and fail to generalise. Segmentation of phenomena is also an open problem. This paper describes an approach to estimate dense motion for dynamic phenomena that is simple, general, and which yields state of the art results. We use our dense motion field to segment phenomena to above state of the art levels. We demonstrate our contributions using lab-based video, video from a public dataset, and from the internet.",
keywords = "natutal phenomena, tracking, segmentation",
author = "Da Chen and Wenbin Li and Peter Hall",
year = "2018",
month = "9",
day = "4",
language = "English",
note = "29th British Machine Vision Conference 2018, BMVC 2018 ; Conference date: 03-09-2018 Through 06-09-2018",
url = "http://bmvc2018.org/",

}

TY - CONF

T1 - Motion Estimation and Segmentation of Natural Phenomena

AU - Chen, Da

AU - Li, Wenbin

AU - Hall, Peter

PY - 2018/9/4

Y1 - 2018/9/4

N2 - Dense motion estimation for dynamic natural phenomena (water, smoke, fire, etc.) is a significant open problem. Current approaches tend to be either general, giving poor results, or specialise in one phenomenon and fail to generalise. Segmentation of phenomena is also an open problem. This paper describes an approach to estimate dense motion for dynamic phenomena that is simple, general, and which yields state of the art results. We use our dense motion field to segment phenomena to above state of the art levels. We demonstrate our contributions using lab-based video, video from a public dataset, and from the internet.

AB - Dense motion estimation for dynamic natural phenomena (water, smoke, fire, etc.) is a significant open problem. Current approaches tend to be either general, giving poor results, or specialise in one phenomenon and fail to generalise. Segmentation of phenomena is also an open problem. This paper describes an approach to estimate dense motion for dynamic phenomena that is simple, general, and which yields state of the art results. We use our dense motion field to segment phenomena to above state of the art levels. We demonstrate our contributions using lab-based video, video from a public dataset, and from the internet.

KW - natutal phenomena, tracking, segmentation

M3 - Paper

ER -