A GAUSSIAN PROCESS BASED MULTI-PERSON INTERACTION MODEL
Online multi-person tracking in image sequences is commonly guided by recursive filters, whose predictive models define the expected positions of future states. When a predictive model deviates too much from the true motion of a pedestrian, which is often the case in crowded scenes due to unpredicte...
Main Authors: | T. Klinger, F. Rottensteiner, C. Heipke |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2016-06-01
|
Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/III-3/271/2016/isprs-annals-III-3-271-2016.pdf |
Similar Items
-
PROBABILISTIC MULTI-PERSON TRACKING USING DYNAMIC BAYES NETWORKS
by: T. Klinger, et al.
Published: (2015-08-01) -
A Dynamic Bayes Network for visual Pedestrian Tracking
by: T. Klinger, et al.
Published: (2014-08-01) -
CONTEXT MODELS FOR CRF-BASED CLASSIFICATION OF MULTITEMPORAL REMOTE SENSING DATA
by: T. Hoberg, et al.
Published: (2012-07-01) -
TRANSFORMER MODELS FOR MULTI-TEMPORAL LAND COVER CLASSIFICATION USING REMOTE SENSING IMAGES
by: M. Voelsen, et al.
Published: (2023-12-01) -
USING REDUNDANT INFORMATION FROM MULTIPLE AERIAL IMAGES FOR THE DETECTION OF BOMB CRATERS BASED ON MARKED POINT PROCESSES
by: C. Kruse, et al.
Published: (2020-08-01)