Bild från Syndetics
Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
Materialtyp:
ArtikelSerie: Utgivningsinformation: Karlsruhe KIT Scientific Publishing KIT Scientific Publishing [Imprint] 2022Beskrivning: 1 electronic resource (204 p.)Innehållstyp: - text
- computer
- online resource
- 9783731511779
- Technology, Engineering, Agriculture, Industrial processes
- Energy technology and engineering
- Electrical engineering
- Agriculture
- Engineering
- Industrial processes
- Netzwerk von 3D-Sensoren
- T Technology
- TH Energy technology and engineering
- THR Electrical engineering
- Tiefenbilder
- depth sensor indoor surveillance
- inverses Problem
- joint multi-view person detection
- mean-field variational inference
- probabilistische Personendetektion
- thema EDItEUR
- vertical top-view indoor pedestrian detection
Inga fysiska exemplar för denna post
Open Access Unrestricted online access star
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.
Accessibility options of PDF file not available
Creative Commons Licence cc by-sa cc http://creativecommons.org/licenses/by-sa/4.0
eng
Freely available e-book