Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο: https://hdl.handle.net/20.500.14279/4280
Τίτλος: Advanced statistical and adaptive threshold techniques for moving object detection and segmentation
Συγγραφείς: Marques, Oge 
Kasparis, Takis 
Christodoulou, Lakis 
metadata.dc.contributor.other: Κασπαρής, Τάκης
Χριστοδούλου, Λάκης
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Λέξεις-κλειδιά: Computer vision;Statistics;Standard deviations;Computer graphics
Ημερομηνία Έκδοσης: 30-Αυγ-2011
Πηγή: 17th International Conference on Digital Signal Processing, 2011, Pages 1-6
Conference: International Conference on Digital Signal Processing 
Περίληψη: The current research project proposes advanced statistical and adaptive threshold techniques for video object detection and segmentation. We present new statistical adaptive threshold techniques to show the advantages, and how these algorithms overcome the limitations and the technical challenges for object motion detection. The algorithm utilizes statistical quantities such as mean, standard deviation, and variance to define a new adaptive and automatic threshold based on two-frame and three-frame differencing. The proposed algorithms were compared with classic statistical thresholding methods on a testing video for human motion detection, and the experimental results show the effectiveness of the algorithms. Furthermore this research shows an evaluation and comparison among all statistical and adaptive algorithms and proves the benefits of the proposed algorithm.
URI: https://hdl.handle.net/20.500.14279/4280
ISBN: 978-1-4577-0274-7
ISSN: 2165-3577
DOI: 10.1109/ICDSP.2011.6004875
Rights: © 2011 IEEE
Type: Conference Papers
Affiliation: Cyprus University of Technology 
Publication Type: Peer Reviewed
Εμφανίζεται στις συλλογές:Κεφάλαια βιβλίων/Book chapters

CORE Recommender
Δείξε την πλήρη περιγραφή του τεκμηρίου

SCOPUSTM   
Citations 50

7
checked on 9 Νοε 2023

Page view(s) 50

475
Last Week
1
Last month
29
checked on 13 Μαρ 2025

Google ScholarTM

Check

Altmetric


Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα