Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images

In this work, the task of wide-area indoor people detection in a network of depth sensors is examined. In particular, we investigate how the redundant and complementary multi-view information, including the temporal context, can be jointly leveraged to improve the detection performance. We recast th...

Full description

Saved in:
Bibliographic Details
Main Author: Wetzel, Johannes
Format: Online
Language:English
Published: KIT Scientific Publishing 2022
Subjects:
Online Access:ONIX_20220718_9783731511779_115
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1869521373587570688
author Wetzel, Johannes
author_browse Wetzel, Johannes
author_facet Wetzel, Johannes
author_sort Wetzel, Johannes
collection Directory of Open Access Books
description In this work, the task of wide-area indoor people detection in a network of depth sensors is examined. In particular, we investigate how the redundant and complementary multi-view information, including the temporal context, can be jointly leveraged to improve the detection performance. We recast the problem of multi-view people detection in overlapping depth images as an inverse problem and present a generative probabilistic framework to jointly exploit the temporal multi-view image evidence.
format Online
id doab-20.500.12854ir-90072
institution Directory of Open Access Books
language eng
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher KIT Scientific Publishing
publisherStr KIT Scientific Publishing
record_format ojs
spelling doab-20.500.12854ir-900722025-07-30T11:55:44Z Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images Wetzel, Johannes probabilistische Personendetektion Netzwerk von 3D-Sensoren Tiefenbilder inverses Problem joint multi-view person detection depth sensor indoor surveillance mean-field variational inference vertical top-view indoor pedestrian detection thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering In this work, the task of wide-area indoor people detection in a network of depth sensors is examined. In particular, we investigate how the redundant and complementary multi-view information, including the temporal context, can be jointly leveraged to improve the detection performance. We recast the problem of multi-view people detection in overlapping depth images as an inverse problem and present a generative probabilistic framework to jointly exploit the temporal multi-view image evidence. 2022-07-19T04:08:47Z 2022-07-19T04:08:47Z 2022-07-18T11:55:26Z 2022 book ONIX_20220718_9783731511779_115 OCN: 1348375751 2190-6629 https://library.oapen.org/handle/20.500.12657/57538 9783731511779 https://directory.doabooks.org/handle/20.500.12854/90072 eng Forschungsberichte aus der Industriellen Informationstechnik open access image/jpeg image/jpeg image/jpeg image/jpeg n/a n/a n/a n/a https://library.oapen.org/bitstream/20.500.12657/57538/1/9783731511779.pdf https://library.oapen.org/bitstream/20.500.12657/57538/1/9783731511779.pdf https://library.oapen.org/bitstream/20.500.12657/57538/1/9783731511779.pdf https://library.oapen.org/bitstream/20.500.12657/57538/1/9783731511779.pdf KIT Scientific Publishing KIT Scientific Publishing 10.5445/KSP/1000144094 10.5445/KSP/1000144094 68fffc18-8f7b-44fa-ac7e-0b7d7d979bd2 9783731511779 AG Universitätsverlage KIT Scientific Publishing 204 Karlsruhe open access
spellingShingle probabilistische Personendetektion
Netzwerk von 3D-Sensoren
Tiefenbilder
inverses Problem
joint multi-view person detection
depth sensor indoor surveillance
mean-field variational inference
vertical top-view indoor pedestrian detection
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
Wetzel, Johannes
Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
title Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
title_full Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
title_fullStr Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
title_full_unstemmed Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
title_short Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
title_sort probabilistic models and inference for multi view people detection in overlapping depth images
topic probabilistische Personendetektion
Netzwerk von 3D-Sensoren
Tiefenbilder
inverses Problem
joint multi-view person detection
depth sensor indoor surveillance
mean-field variational inference
vertical top-view indoor pedestrian detection
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
topic_facet probabilistische Personendetektion
Netzwerk von 3D-Sensoren
Tiefenbilder
inverses Problem
joint multi-view person detection
depth sensor indoor surveillance
mean-field variational inference
vertical top-view indoor pedestrian detection
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
url ONIX_20220718_9783731511779_115
work_keys_str_mv AT wetzeljohannes probabilisticmodelsandinferenceformultiviewpeopledetectioninoverlappingdepthimages