Title
Euclidean Path Modeling From Ground And Aerial Views
Abstract
We address the issue of Euclidean path modeling in a single camera for activity monitoring in a multi-camera video surveillance system. The paper proposes a novel linear solution to auto-calibtate any camera observing pedestrians and uses these calibrated cameras to detect unusual object behavior. The input trajectories are metric rectified and the input sequences are registered to the satellite imagery and prototype path models are constructed. During the testing phase, using our simple yet efficient similarity measures, we seek a relation between the input trajectories derived from a sequence and the prototype path models. Real-world pedestrian sequences are used to demonstrate the practicality of the proposed method. © 2007 IEEE.
Publication Date
10-11-2007
Publication Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Number of Pages
-
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2007.383508
Copyright Status
Unknown
Socpus ID
34948889967 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/34948889967
STARS Citation
Junejo, Imran N. and Foroosh, Hassan, "Euclidean Path Modeling From Ground And Aerial Views" (2007). Scopus Export 2000s. 6662.
https://stars.library.ucf.edu/scopus2000/6662