Video-to-Video Face Recognition for Low-Quality Surveillance Data

The availability of video data is an opportunity and a challenge for law enforcement agencies. Face recognition methods can play a key role in the automated search for persons in the data. This work targets efficient representations of low-quality face sequences to enable fast and accurate face sear...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autor: Herrmann, Christian
Médium: Online
Jazyk:angličtina
Vydáno: KIT Scientific Publishing 2021
Témata:
On-line přístup:34193
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
_version_ 1869518027829018624
author Herrmann, Christian
author_browse Herrmann, Christian
author_facet Herrmann, Christian
author_sort Herrmann, Christian
collection Directory of Open Access Books
description The availability of video data is an opportunity and a challenge for law enforcement agencies. Face recognition methods can play a key role in the automated search for persons in the data. This work targets efficient representations of low-quality face sequences to enable fast and accurate face search. Novel concepts for multi-scale analysis, dataset augmentation, CNN loss function, and sequence description lead to improvements over state-of-the-art methods on surveillance video footage.
format Online
id doab-20.500.12854ir-62070
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-620702023-12-20T18:40:44Z Video-to-Video Face Recognition for Low-Quality Surveillance Data Herrmann, Christian QA75.5-76.95 face recognition video Videoverarbeitung Gesichtswiederkennung bic Book Industry Communication::U Computing & information technology::UY Computer science The availability of video data is an opportunity and a challenge for law enforcement agencies. Face recognition methods can play a key role in the automated search for persons in the data. This work targets efficient representations of low-quality face sequences to enable fast and accurate face search. Novel concepts for multi-scale analysis, dataset augmentation, CNN loss function, and sequence description lead to improvements over state-of-the-art methods on surveillance video footage. 2021-02-12T07:41:47Z 2021-02-12T07:41:47Z 2019-07-28 18:37:01 2018 book 34193 18636489 9783731507994 https://directory.doabooks.org/handle/20.500.12854/62070 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/9783731507994 KIT Scientific Publishing 10.5445/KSP/1000083168 10.5445/KSP/1000083168 68fffc18-8f7b-44fa-ac7e-0b7d7d979bd2 9783731507994 IX, 153 p. open access
spellingShingle QA75.5-76.95
face
recognition
video
Videoverarbeitung
Gesichtswiederkennung
bic Book Industry Communication::U Computing & information technology::UY Computer science
Herrmann, Christian
Video-to-Video Face Recognition for Low-Quality Surveillance Data
title Video-to-Video Face Recognition for Low-Quality Surveillance Data
title_full Video-to-Video Face Recognition for Low-Quality Surveillance Data
title_fullStr Video-to-Video Face Recognition for Low-Quality Surveillance Data
title_full_unstemmed Video-to-Video Face Recognition for Low-Quality Surveillance Data
title_short Video-to-Video Face Recognition for Low-Quality Surveillance Data
title_sort video to video face recognition for low quality surveillance data
topic QA75.5-76.95
face
recognition
video
Videoverarbeitung
Gesichtswiederkennung
bic Book Industry Communication::U Computing & information technology::UY Computer science
topic_facet QA75.5-76.95
face
recognition
video
Videoverarbeitung
Gesichtswiederkennung
bic Book Industry Communication::U Computing & information technology::UY Computer science
url 34193
work_keys_str_mv AT herrmannchristian videotovideofacerecognitionforlowqualitysurveillancedata