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

Bibliographic Details
Main Author: Wetzel, Johannes
Format: eBook
Language:English
Published: Karlsruhe KIT Scientific Publishing 2022
Series:Forschungsberichte aus der Industriellen Informationstechnik
Subjects:
Online Access:
Collection: Directory of Open Access Books - Collection details see MPG.ReNa
LEADER 02005nma a2200373 u 4500
001 EB002052423
003 EBX01000000000000001196089
005 00000000000000.0
007 cr|||||||||||||||||||||
008 220822 ||| eng
020 |a 9783731511779 
020 |a 1000144094 
100 1 |a Wetzel, Johannes 
245 0 0 |a Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images  |h Elektronische Ressource 
260 |a Karlsruhe  |b KIT Scientific Publishing  |c 2022 
300 |a 1 electronic resource (204 p.) 
653 |a depth sensor indoor surveillance 
653 |a vertical top-view indoor pedestrian detection 
653 |a Netzwerk von 3D-Sensoren 
653 |a mean-field variational inference 
653 |a joint multi-view person detection 
653 |a Electrical engineering / bicssc 
653 |a Tiefenbilder 
653 |a probabilistische Personendetektion 
653 |a inverses Problem 
041 0 7 |a eng  |2 ISO 639-2 
989 |b DOAB  |a Directory of Open Access Books 
490 0 |a Forschungsberichte aus der Industriellen Informationstechnik 
500 |a Creative Commons (cc), by-sa/4.0, http://creativecommons.org/licenses/by-sa/4.0 
024 8 |a 10.5445/KSP/1000144094 
856 4 0 |u https://library.oapen.org/bitstream/20.500.12657/57538/1/9783731511779.pdf  |7 0  |x Verlag  |3 Volltext 
856 4 2 |u https://directory.doabooks.org/handle/20.500.12854/90072  |z DOAB: description of the publication 
082 0 |a 620 
520 |a 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.