World Library  


Add to Book Shelf
Flag as Inappropriate
Email this Book

Probabilistic Multi-person Tracking Using Dynamic Bayes Networks : Volume Ii-3/W5, Issue 1 (20/08/2015)

By Klinger, T.

Click here to view

Book Id: WPLBN0004013937
Format Type: PDF Article :
File Size: Pages 8
Reproduction Date: 2015

Title: Probabilistic Multi-person Tracking Using Dynamic Bayes Networks : Volume Ii-3/W5, Issue 1 (20/08/2015)  
Author: Klinger, T.
Volume: Vol. II-3/W5, Issue 1
Language: English
Subject: Science, Isprs, Annals
Collections: Periodicals: Journal and Magazine Collection, Copernicus GmbH
Historic
Publication Date:
2015
Publisher: Copernicus Gmbh, Göttingen, Germany
Member Page: Copernicus Publications

Citation

APA MLA Chicago

Heipke, C., Rottensteiner, F., & Klinger, T. (2015). Probabilistic Multi-person Tracking Using Dynamic Bayes Networks : Volume Ii-3/W5, Issue 1 (20/08/2015). Retrieved from http://www.ebooklibrary.org/


Description
Description: Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Hannover, Germany. Tracking-by-detection is a widely used practice in recent tracking systems. These usually rely on independent single frame detections that are handled as observations in a recursive estimation framework. If these observations are imprecise the generated trajectory is prone to be updated towards a wrong position. In contrary to existing methods our novel approach uses a Dynamic Bayes Network in which the state vector of a recursive Bayes filter, as well as the location of the tracked object in the image are modelled as unknowns. These unknowns are estimated in a probabilistic framework taking into account a dynamic model, and a state-of-the-art pedestrian detector and classifier. The classifier is based on the Random Forest-algorithm and is capable of being trained incrementally so that new training samples can be incorporated at runtime. This allows the classifier to adapt to the changing appearance of a target and to unlearn outdated features. The approach is evaluated on a publicly available benchmark. The results confirm that our approach is well suited for tracking pedestrians over long distances while at the same time achieving comparatively good geometric accuracy.

Summary
PROBABILISTIC MULTI-PERSON TRACKING USING DYNAMIC BAYES NETWORKS

 

Click To View

Additional Books


  • Automatic Creation of Structural Models ... (by )
  • 3D Data Acquisition for Indoor Assets Us... (by )
  • Trees Detection from Laser Point Clouds ... (by )
  • Measurement of Rotor Blade Deformations ... (by )
  • A New Feature Descriptor for Lidar Image... (by )
  • Robust Feature Tracking in Image Sequenc... (by )
  • 3D Modeling from Gnomonic Projections : ... (by )
  • Integration of Image and Range-based Tec... (by )
  • A Topological Framework for the Temporal... (by )
  • Design, Implementation and Applications ... (by )
  • Robust Classification and Segmentation o... (by )
  • Modelling Vague Knowledge for Decision S... (by )
Scroll Left
Scroll Right

 



Copyright © World Library Foundation. All rights reserved. eBooks from World eBook Library are sponsored by the World Library Foundation,
a 501c(4) Member's Support Non-Profit Organization, and is NOT affiliated with any governmental agency or department.