Robust tracking of multiple objects in sector-scan sonar image sequences using optical flow motion estimation

Research output: Contribution to journalArticle

Abstract

The fast update rate and good performance of new generation electronic sector scanning sonars is now allowing practicable use of temporal information for signal processing tasks such as object classification and motion estimation. Problems remain, however, as objects change appearance, merge, maneuver, move in and out of the field of view, and split due to poor segmentation. This paper presents an approach to the segmentation, two-dimensional motion estimation, and subsequent tracking of multiple objects in sequences of sector scan sonar images. Applications such as ROV obstacle avoidance, visual servoing, and underwater surveillance are relevant. Initially, static and moving objects are distinguished in the sonar image sequence using frequency-domain filtering. Optical flow calculations are then performed on moving objects with significant size to obtain magnitude and direction motion estimates. Matches of these motion estimates, and the future positions they predict, are then used as a basis for identifying corresponding objects in adjacent scans. To enhance robustness, a tracking tree is constructed storing multiple possible correspondences and cumulative confidence values obtained from successive compatibility measures. Deferred decision making is then employed to enable best estimates of object tracks to be updated as subsequent scans produce new information. The method is shown to work well, with good tracking performance when objects merge, split, and change shape. The optical flow is demonstrated to give position prediction errors of between 10 and 50 cm (1%-5% of scan range), with no violation of smoothness assumptions using sample rates between 4 and 1 frames/s.

Original languageEnglish
Pages (from-to)31-46
Number of pages16
JournalIEEE Journal of Oceanic Engineering
Volume23
Issue number1
DOIs
Publication statusPublished - Jan 1998

Fingerprint

Optical flows
Sonar
Motion estimation
Visual servoing
Remotely operated vehicles
Collision avoidance
Signal processing
Decision making
Scanning

Keywords

  • Delayed decision
  • Multiple hypothesis
  • Optical flow
  • Sector scan sonar
  • Segmentation
  • Target classification
  • Target tracking

Cite this

@article{929d26a7ee384a80b1e132b973fa40d0,
title = "Robust tracking of multiple objects in sector-scan sonar image sequences using optical flow motion estimation",
abstract = "The fast update rate and good performance of new generation electronic sector scanning sonars is now allowing practicable use of temporal information for signal processing tasks such as object classification and motion estimation. Problems remain, however, as objects change appearance, merge, maneuver, move in and out of the field of view, and split due to poor segmentation. This paper presents an approach to the segmentation, two-dimensional motion estimation, and subsequent tracking of multiple objects in sequences of sector scan sonar images. Applications such as ROV obstacle avoidance, visual servoing, and underwater surveillance are relevant. Initially, static and moving objects are distinguished in the sonar image sequence using frequency-domain filtering. Optical flow calculations are then performed on moving objects with significant size to obtain magnitude and direction motion estimates. Matches of these motion estimates, and the future positions they predict, are then used as a basis for identifying corresponding objects in adjacent scans. To enhance robustness, a tracking tree is constructed storing multiple possible correspondences and cumulative confidence values obtained from successive compatibility measures. Deferred decision making is then employed to enable best estimates of object tracks to be updated as subsequent scans produce new information. The method is shown to work well, with good tracking performance when objects merge, split, and change shape. The optical flow is demonstrated to give position prediction errors of between 10 and 50 cm (1{\%}-5{\%} of scan range), with no violation of smoothness assumptions using sample rates between 4 and 1 frames/s.",
keywords = "Delayed decision, Multiple hypothesis, Optical flow, Sector scan sonar, Segmentation, Target classification, Target tracking",
author = "Lane, {David Michael} and Mike Chantler and Dongyong Dai",
note = "INSPEC Accession Number: 5859500",
year = "1998",
month = "1",
doi = "10.1109/48.659448",
language = "English",
volume = "23",
pages = "31--46",
journal = "IEEE Journal of Oceanic Engineering",
issn = "0364-9059",
publisher = "IEEE",
number = "1",

}

TY - JOUR

T1 - Robust tracking of multiple objects in sector-scan sonar image sequences using optical flow motion estimation

AU - Lane, David Michael

AU - Chantler, Mike

AU - Dai, Dongyong

N1 - INSPEC Accession Number: 5859500

PY - 1998/1

Y1 - 1998/1

N2 - The fast update rate and good performance of new generation electronic sector scanning sonars is now allowing practicable use of temporal information for signal processing tasks such as object classification and motion estimation. Problems remain, however, as objects change appearance, merge, maneuver, move in and out of the field of view, and split due to poor segmentation. This paper presents an approach to the segmentation, two-dimensional motion estimation, and subsequent tracking of multiple objects in sequences of sector scan sonar images. Applications such as ROV obstacle avoidance, visual servoing, and underwater surveillance are relevant. Initially, static and moving objects are distinguished in the sonar image sequence using frequency-domain filtering. Optical flow calculations are then performed on moving objects with significant size to obtain magnitude and direction motion estimates. Matches of these motion estimates, and the future positions they predict, are then used as a basis for identifying corresponding objects in adjacent scans. To enhance robustness, a tracking tree is constructed storing multiple possible correspondences and cumulative confidence values obtained from successive compatibility measures. Deferred decision making is then employed to enable best estimates of object tracks to be updated as subsequent scans produce new information. The method is shown to work well, with good tracking performance when objects merge, split, and change shape. The optical flow is demonstrated to give position prediction errors of between 10 and 50 cm (1%-5% of scan range), with no violation of smoothness assumptions using sample rates between 4 and 1 frames/s.

AB - The fast update rate and good performance of new generation electronic sector scanning sonars is now allowing practicable use of temporal information for signal processing tasks such as object classification and motion estimation. Problems remain, however, as objects change appearance, merge, maneuver, move in and out of the field of view, and split due to poor segmentation. This paper presents an approach to the segmentation, two-dimensional motion estimation, and subsequent tracking of multiple objects in sequences of sector scan sonar images. Applications such as ROV obstacle avoidance, visual servoing, and underwater surveillance are relevant. Initially, static and moving objects are distinguished in the sonar image sequence using frequency-domain filtering. Optical flow calculations are then performed on moving objects with significant size to obtain magnitude and direction motion estimates. Matches of these motion estimates, and the future positions they predict, are then used as a basis for identifying corresponding objects in adjacent scans. To enhance robustness, a tracking tree is constructed storing multiple possible correspondences and cumulative confidence values obtained from successive compatibility measures. Deferred decision making is then employed to enable best estimates of object tracks to be updated as subsequent scans produce new information. The method is shown to work well, with good tracking performance when objects merge, split, and change shape. The optical flow is demonstrated to give position prediction errors of between 10 and 50 cm (1%-5% of scan range), with no violation of smoothness assumptions using sample rates between 4 and 1 frames/s.

KW - Delayed decision

KW - Multiple hypothesis

KW - Optical flow

KW - Sector scan sonar

KW - Segmentation

KW - Target classification

KW - Target tracking

UR - http://www.scopus.com/inward/record.url?scp=0031672599&partnerID=8YFLogxK

U2 - 10.1109/48.659448

DO - 10.1109/48.659448

M3 - Article

VL - 23

SP - 31

EP - 46

JO - IEEE Journal of Oceanic Engineering

JF - IEEE Journal of Oceanic Engineering

SN - 0364-9059

IS - 1

ER -