Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Computing Vessel Velocity from Single Perspective Projection Images

Abstract: 

We present an image-based approach to estimate the velocity of moving vessels from their traces on the water surface. Vessels moving at constant heading and speed display a familiar V-shaped pattern which only differs from one to another by the wavelength of their transverse and divergent components. Such wavelength is related to vessel velocity. We use planar homography and natural constraints on the geometry of ships’ wake crests to compute vessel velocity from single optical images acquired by conventional cameras. Experiments show that our approach produces compelling results, which are in accordance with true data available for the observed vessels.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
12 September 2019 - 2:35pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Jose Luis Huillca
Paper Code:
2025
Document Year:
2019
Cite

Document Files

huillca_fernandes-icip-2019-poster.pdf

(7)

Subscribe

[1] , "Computing Vessel Velocity from Single Perspective Projection Images", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4572. Accessed: Sep. 16, 2019.
@article{4572-19,
url = {http://sigport.org/4572},
author = { },
publisher = {IEEE SigPort},
title = {Computing Vessel Velocity from Single Perspective Projection Images},
year = {2019} }
TY - EJOUR
T1 - Computing Vessel Velocity from Single Perspective Projection Images
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4572
ER -
. (2019). Computing Vessel Velocity from Single Perspective Projection Images. IEEE SigPort. http://sigport.org/4572
, 2019. Computing Vessel Velocity from Single Perspective Projection Images. Available at: http://sigport.org/4572.
. (2019). "Computing Vessel Velocity from Single Perspective Projection Images." Web.
1. . Computing Vessel Velocity from Single Perspective Projection Images [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4572