Probabilistic data association methods for tracking complex visual objects

Christopher Rasmussen, Gregory Hager

Research output: Contribution to journalArticle

Abstract

We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: 1) noise-like visual occurrences, 2) persistent, known scene elements (i.e., other tracked objects), or 3) persistent, unknown scene elements. First, we introduce a randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion. The algorithm is applied to three different tracking modalities-homogeneous regions, textured regions, and snakes-and extensibly defined for straightforward inclusion of other methods. Second, we add the capacity to track multiple objects by adapting to vision a joint PDAF which oversees correspondence choices between same-modality trackers and image features. We then derive a related technique that allows mixed tracker modalities and handles object overlaps robustly. Finally, we represent complex objects as conjunctions of cues that are diverse both geometrically (e.g., parts) and qualitatively (e.g., attributes). Rigid and hinge constraints between part trackers and multiple descriptive attributes for individual parts render the whole object more distinctive, reducing susceptibility to mistracking. Results are given for diverse objects such as people, microscopic cells, and chess pieces.

Original languageEnglish (US)
Pages (from-to)560-576
Number of pages17
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume23
Issue number6
DOIs
StatePublished - Jun 2001

Fingerprint

Data Association
Hinges
Modality
Attribute
Filter
Snakes
Clutter
Ambiguous
Missing Data
Susceptibility
Vision
Object
Overlap
Correspondence
Inclusion
Unknown
Motion
Cell

Keywords

  • Color regions
  • Data association
  • Snakes
  • Textured regions
  • Visual tracking

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Probabilistic data association methods for tracking complex visual objects. / Rasmussen, Christopher; Hager, Gregory.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, 06.2001, p. 560-576.

Research output: Contribution to journalArticle

@article{149db45ad4b649c4814d7920a0ddaaba,
title = "Probabilistic data association methods for tracking complex visual objects",
abstract = "We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: 1) noise-like visual occurrences, 2) persistent, known scene elements (i.e., other tracked objects), or 3) persistent, unknown scene elements. First, we introduce a randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion. The algorithm is applied to three different tracking modalities-homogeneous regions, textured regions, and snakes-and extensibly defined for straightforward inclusion of other methods. Second, we add the capacity to track multiple objects by adapting to vision a joint PDAF which oversees correspondence choices between same-modality trackers and image features. We then derive a related technique that allows mixed tracker modalities and handles object overlaps robustly. Finally, we represent complex objects as conjunctions of cues that are diverse both geometrically (e.g., parts) and qualitatively (e.g., attributes). Rigid and hinge constraints between part trackers and multiple descriptive attributes for individual parts render the whole object more distinctive, reducing susceptibility to mistracking. Results are given for diverse objects such as people, microscopic cells, and chess pieces.",
keywords = "Color regions, Data association, Snakes, Textured regions, Visual tracking",
author = "Christopher Rasmussen and Gregory Hager",
year = "2001",
month = "6",
doi = "10.1109/34.927458",
language = "English (US)",
volume = "23",
pages = "560--576",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - Probabilistic data association methods for tracking complex visual objects

AU - Rasmussen, Christopher

AU - Hager, Gregory

PY - 2001/6

Y1 - 2001/6

N2 - We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: 1) noise-like visual occurrences, 2) persistent, known scene elements (i.e., other tracked objects), or 3) persistent, unknown scene elements. First, we introduce a randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion. The algorithm is applied to three different tracking modalities-homogeneous regions, textured regions, and snakes-and extensibly defined for straightforward inclusion of other methods. Second, we add the capacity to track multiple objects by adapting to vision a joint PDAF which oversees correspondence choices between same-modality trackers and image features. We then derive a related technique that allows mixed tracker modalities and handles object overlaps robustly. Finally, we represent complex objects as conjunctions of cues that are diverse both geometrically (e.g., parts) and qualitatively (e.g., attributes). Rigid and hinge constraints between part trackers and multiple descriptive attributes for individual parts render the whole object more distinctive, reducing susceptibility to mistracking. Results are given for diverse objects such as people, microscopic cells, and chess pieces.

AB - We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: 1) noise-like visual occurrences, 2) persistent, known scene elements (i.e., other tracked objects), or 3) persistent, unknown scene elements. First, we introduce a randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion. The algorithm is applied to three different tracking modalities-homogeneous regions, textured regions, and snakes-and extensibly defined for straightforward inclusion of other methods. Second, we add the capacity to track multiple objects by adapting to vision a joint PDAF which oversees correspondence choices between same-modality trackers and image features. We then derive a related technique that allows mixed tracker modalities and handles object overlaps robustly. Finally, we represent complex objects as conjunctions of cues that are diverse both geometrically (e.g., parts) and qualitatively (e.g., attributes). Rigid and hinge constraints between part trackers and multiple descriptive attributes for individual parts render the whole object more distinctive, reducing susceptibility to mistracking. Results are given for diverse objects such as people, microscopic cells, and chess pieces.

KW - Color regions

KW - Data association

KW - Snakes

KW - Textured regions

KW - Visual tracking

UR - http://www.scopus.com/inward/record.url?scp=0035363738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035363738&partnerID=8YFLogxK

U2 - 10.1109/34.927458

DO - 10.1109/34.927458

M3 - Article

AN - SCOPUS:0035363738

VL - 23

SP - 560

EP - 576

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 6

ER -