On 3-D motion estimation from feature tracks in 2-D FS sonar video

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Visual odometry involves the computation of 3-D motion and (or) trajectory by tracking features in the video or image sequences recorded by the camera(s) on some autonomous terrestrial, aerial, and marine robotics platform. For exploration, mapping, inspection, and surveillance operations within turbid waters, high-frequency 2-D forward-scan sonar systems offer a significant advantage over cameras by providing both imagery with target details and attractive tradeoff in range, resolution, and data rate. Operating these at grazing incidence gives larger scene coverage and improved image quality due to the dominance of diffuse backscattered reflectance but induces cast shadows that are typically more distinct than brightness patterns due to the direct reflectance of casting objects. For the computation of 3-D motion by automatic video processing, the estimation accuracy and robustness can be enhanced by integrating the visual cues from shadow dynamics with the image flow of stationary 3-D objects, both induced by sonar motion. In this paper, we present the mathematical models of image flow for 3-D objects and their cast shadows, utilize them in devising various 3-D sonar motion estimation solutions, and study their robustness. We present results of experiments with both synthetic and real data in order to assess the accuracy and performance of these methods.

Original languageEnglish
Article number6522179
Pages (from-to)1016-1030
Number of pages15
JournalIEEE Transactions on Robotics
Volume29
Issue number4
DOIs
StatePublished - Jun 6 2013

Fingerprint

Sonar
Motion estimation
Cameras
Image quality
Luminance
Casting
Robotics
Inspection
Trajectories
Mathematical models
Antennas
Processing
Water
Experiments

Keywords

  • 2-D forward-scan sonar video
  • 3-D motion estimation
  • Benthic habitat mapping
  • marine robotics
  • visual odometry

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

On 3-D motion estimation from feature tracks in 2-D FS sonar video. / Negahdaripour, Shahriar.

In: IEEE Transactions on Robotics, Vol. 29, No. 4, 6522179, 06.06.2013, p. 1016-1030.

Research output: Contribution to journalArticle

@article{161899b428f848e082a27a48d3d6fb04,
title = "On 3-D motion estimation from feature tracks in 2-D FS sonar video",
abstract = "Visual odometry involves the computation of 3-D motion and (or) trajectory by tracking features in the video or image sequences recorded by the camera(s) on some autonomous terrestrial, aerial, and marine robotics platform. For exploration, mapping, inspection, and surveillance operations within turbid waters, high-frequency 2-D forward-scan sonar systems offer a significant advantage over cameras by providing both imagery with target details and attractive tradeoff in range, resolution, and data rate. Operating these at grazing incidence gives larger scene coverage and improved image quality due to the dominance of diffuse backscattered reflectance but induces cast shadows that are typically more distinct than brightness patterns due to the direct reflectance of casting objects. For the computation of 3-D motion by automatic video processing, the estimation accuracy and robustness can be enhanced by integrating the visual cues from shadow dynamics with the image flow of stationary 3-D objects, both induced by sonar motion. In this paper, we present the mathematical models of image flow for 3-D objects and their cast shadows, utilize them in devising various 3-D sonar motion estimation solutions, and study their robustness. We present results of experiments with both synthetic and real data in order to assess the accuracy and performance of these methods.",
keywords = "2-D forward-scan sonar video, 3-D motion estimation, Benthic habitat mapping, marine robotics, visual odometry",
author = "Shahriar Negahdaripour",
year = "2013",
month = "6",
day = "6",
doi = "10.1109/TRO.2013.2260952",
language = "English",
volume = "29",
pages = "1016--1030",
journal = "IEEE Transactions on Robotics",
issn = "1552-3098",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - On 3-D motion estimation from feature tracks in 2-D FS sonar video

AU - Negahdaripour, Shahriar

PY - 2013/6/6

Y1 - 2013/6/6

N2 - Visual odometry involves the computation of 3-D motion and (or) trajectory by tracking features in the video or image sequences recorded by the camera(s) on some autonomous terrestrial, aerial, and marine robotics platform. For exploration, mapping, inspection, and surveillance operations within turbid waters, high-frequency 2-D forward-scan sonar systems offer a significant advantage over cameras by providing both imagery with target details and attractive tradeoff in range, resolution, and data rate. Operating these at grazing incidence gives larger scene coverage and improved image quality due to the dominance of diffuse backscattered reflectance but induces cast shadows that are typically more distinct than brightness patterns due to the direct reflectance of casting objects. For the computation of 3-D motion by automatic video processing, the estimation accuracy and robustness can be enhanced by integrating the visual cues from shadow dynamics with the image flow of stationary 3-D objects, both induced by sonar motion. In this paper, we present the mathematical models of image flow for 3-D objects and their cast shadows, utilize them in devising various 3-D sonar motion estimation solutions, and study their robustness. We present results of experiments with both synthetic and real data in order to assess the accuracy and performance of these methods.

AB - Visual odometry involves the computation of 3-D motion and (or) trajectory by tracking features in the video or image sequences recorded by the camera(s) on some autonomous terrestrial, aerial, and marine robotics platform. For exploration, mapping, inspection, and surveillance operations within turbid waters, high-frequency 2-D forward-scan sonar systems offer a significant advantage over cameras by providing both imagery with target details and attractive tradeoff in range, resolution, and data rate. Operating these at grazing incidence gives larger scene coverage and improved image quality due to the dominance of diffuse backscattered reflectance but induces cast shadows that are typically more distinct than brightness patterns due to the direct reflectance of casting objects. For the computation of 3-D motion by automatic video processing, the estimation accuracy and robustness can be enhanced by integrating the visual cues from shadow dynamics with the image flow of stationary 3-D objects, both induced by sonar motion. In this paper, we present the mathematical models of image flow for 3-D objects and their cast shadows, utilize them in devising various 3-D sonar motion estimation solutions, and study their robustness. We present results of experiments with both synthetic and real data in order to assess the accuracy and performance of these methods.

KW - 2-D forward-scan sonar video

KW - 3-D motion estimation

KW - Benthic habitat mapping

KW - marine robotics

KW - visual odometry

UR - http://www.scopus.com/inward/record.url?scp=84882453186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882453186&partnerID=8YFLogxK

U2 - 10.1109/TRO.2013.2260952

DO - 10.1109/TRO.2013.2260952

M3 - Article

AN - SCOPUS:84882453186

VL - 29

SP - 1016

EP - 1030

JO - IEEE Transactions on Robotics

JF - IEEE Transactions on Robotics

SN - 1552-3098

IS - 4

M1 - 6522179

ER -