Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking

This work proposes a feature-based probabilistic data association and tracking approach (FBPDATA) for multi-object tracking. FBPDATA is based on re-identification and tracking of individual video image points (feature points) and aims at solving the problems of partial, split (fragmented), bloated o...

Full description

Saved in:
Bibliographic Details
Main Author: Grinberg, Michael
Format: Online
Language:English
Published: KIT Scientific Publishing 2021
Subjects:
Online Access:34219
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1869528471204528128
author Grinberg, Michael
author_browse Grinberg, Michael
author_facet Grinberg, Michael
author_sort Grinberg, Michael
collection Directory of Open Access Books
description This work proposes a feature-based probabilistic data association and tracking approach (FBPDATA) for multi-object tracking. FBPDATA is based on re-identification and tracking of individual video image points (feature points) and aims at solving the problems of partial, split (fragmented), bloated or missed detections, which are due to sensory or algorithmic restrictions, limited field of view of the sensors, as well as occlusion situations.
format Online
id doab-20.500.12854ir-47470
institution Directory of Open Access Books
language eng
publishDate 2021
publishDateRange 2021
publishDateSort 2021
publisher KIT Scientific Publishing
publisherStr KIT Scientific Publishing
record_format ojs
spelling doab-20.500.12854ir-474702023-12-20T18:40:51Z Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking Grinberg, Michael QA75.5-76.95 gestörte Detektionenfeature-based probabilistic merkmalsbasiert probabilistisch Datenassoziation object tracking corrupted detections data association Objektverfolgung bic Book Industry Communication::U Computing & information technology::UY Computer science This work proposes a feature-based probabilistic data association and tracking approach (FBPDATA) for multi-object tracking. FBPDATA is based on re-identification and tracking of individual video image points (feature points) and aims at solving the problems of partial, split (fragmented), bloated or missed detections, which are due to sensory or algorithmic restrictions, limited field of view of the sensors, as well as occlusion situations. 2021-02-11T13:31:22Z 2021-02-11T13:31:22Z 2019-07-28 18:37:01 2018 book 34219 18636489 9783731507819 https://directory.doabooks.org/handle/20.500.12854/47470 eng Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe image/jpeg Attribution-ShareAlike 4.0 International https://www.ksp.kit.edu/9783731507819 KIT Scientific Publishing 10.5445/KSP/1000081430 10.5445/KSP/1000081430 68fffc18-8f7b-44fa-ac7e-0b7d7d979bd2 9783731507819 XXII, 256 p. open access
spellingShingle QA75.5-76.95
gestörte Detektionenfeature-based
probabilistic
merkmalsbasiert
probabilistisch
Datenassoziation
object tracking
corrupted detections
data association
Objektverfolgung
bic Book Industry Communication::U Computing & information technology::UY Computer science
Grinberg, Michael
Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking
title Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking
title_full Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking
title_fullStr Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking
title_full_unstemmed Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking
title_short Feature-Based Probabilistic Data Association for Video-Based Multi-Object Tracking
title_sort feature based probabilistic data association for video based multi object tracking
topic QA75.5-76.95
gestörte Detektionenfeature-based
probabilistic
merkmalsbasiert
probabilistisch
Datenassoziation
object tracking
corrupted detections
data association
Objektverfolgung
bic Book Industry Communication::U Computing & information technology::UY Computer science
topic_facet QA75.5-76.95
gestörte Detektionenfeature-based
probabilistic
merkmalsbasiert
probabilistisch
Datenassoziation
object tracking
corrupted detections
data association
Objektverfolgung
bic Book Industry Communication::U Computing & information technology::UY Computer science
url 34219
work_keys_str_mv AT grinbergmichael featurebasedprobabilisticdataassociationforvideobasedmultiobjecttracking