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 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.
Keywordsprobabilistische 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
PublisherKIT Scientific Publishing
Publication date and placeKarlsruhe, 2022
ImprintKIT Scientific Publishing
SeriesForschungsberichte aus der Industriellen Informationstechnik, 25