World Library  


Add to Book Shelf
Flag as Inappropriate
Email this Book

Gaussian Process for Activity Modeling and Anomaly Detection : Volume Ii-3/W5, Issue 1 (20/08/2015)

By Liao, W.

Click here to view

Book Id: WPLBN0004013944
Format Type: PDF Article :
File Size: Pages 8
Reproduction Date: 2015

Title: Gaussian Process for Activity Modeling and Anomaly Detection : Volume Ii-3/W5, Issue 1 (20/08/2015)  
Author: Liao, W.
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

Yang, M. Y., Rosenhahn, B., & Liao, W. (2015). Gaussian Process for Activity Modeling and Anomaly Detection : Volume Ii-3/W5, Issue 1 (20/08/2015). Retrieved from http://www.ebooklibrary.org/


Description
Description: Institute for Information Processing, Leibniz University Hannover, Hannover, Germany. Complex activity modeling and identification of anomaly is one of the most interesting and desired capabilities for automated video behavior analysis. A number of different approaches have been proposed in the past to tackle this problem. There are two main challenges for activity modeling and anomaly detection: 1) most existing approaches require sufficient data and supervision for learning; 2) the most interesting abnormal activities arise rarely and are ambiguous among typical activities, i.e. hard to be precisely defined. In this paper, we propose a novel approach to model complex activities and detect anomalies by using non-parametric Gaussian Process (GP) models in a crowded and complicated traffic scene. In comparison with parametric models such as HMM, GP models are nonparametric and have their advantages. Our GP models exploit implicit spatial-temporal dependence among local activity patterns. The learned GP regression models give a probabilistic prediction of regional activities at next time interval based on observations at present. An anomaly will be detected by comparing the actual observations with the prediction at real time. We verify the effectiveness and robustness of the proposed model on the QMUL Junction Dataset. Furthermore, we provide a publicly available manually labeled ground truth of this data set.

Summary
GAUSSIAN PROCESS FOR ACTIVITY MODELING AND ANOMALY DETECTION

 

Click To View

Additional Books


  • 3D Visualisation of Underground Pipeline... (by )
  • Trajectory-based Registration of 3D Lida... (by )
  • Fixed-wing Micro Aerial Vehicle for Accu... (by )
  • The Construction Features of Traditional... (by )
  • Experiment for Integrating Dutch 3D Spat... (by )
  • On the Use of Uavs in Mining and Archaeo... (by )
  • Calibrating and Evaluating a Range Camer... (by )
  • Extracting Mobile Objects in Images Usin... (by )
  • Rigorous Lidar Strip Adjustment with Tri... (by )
  • To Examine the Association Between Oscil... (by )
  • Semantic Segmentation of Aerial Images i... (by )
  • Combined Geometric and Thermal Analysis ... (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.