|
|
|
|
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.
|