Detecting multiple moving objects in crowded environments with coherent motion regions
Abstract
Coherent motion regions extend in time as well as space, enforcing consistency in detected objects over long time periods and making the algorithm robust to noisy or short point tracks. As a result of enforcing the constraint that selected coherent motion regions contain disjoint sets of tracks defined in a three-dimensional space including a time dimension. An algorithm operates directly on raw, unconditioned low-level feature point tracks, and minimizes a global measure of the coherent motion regions. At least one discrete moving object is identified in a time series of video images based on the trajectory similarity factors, which is a measure of a maximum distance between a pair of feature point tracks.
- Inventors:
- Issue Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1084203
- Patent Number(s):
- 8462987
- Application Number:
- 12/489,589
- Assignee:
- UT-Battelle, LLC (Oak Ridge, TN)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
G - PHYSICS G06 - COMPUTING G06K - RECOGNITION OF DATA
- DOE Contract Number:
- ACO5-000R22725
- Resource Type:
- Patent
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Cheriyadat, Anil M., and Radke, Richard J. Detecting multiple moving objects in crowded environments with coherent motion regions. United States: N. p., 2013.
Web.
Cheriyadat, Anil M., & Radke, Richard J. Detecting multiple moving objects in crowded environments with coherent motion regions. United States.
Cheriyadat, Anil M., and Radke, Richard J. Tue .
"Detecting multiple moving objects in crowded environments with coherent motion regions". United States. https://www.osti.gov/servlets/purl/1084203.
@article{osti_1084203,
title = {Detecting multiple moving objects in crowded environments with coherent motion regions},
author = {Cheriyadat, Anil M. and Radke, Richard J.},
abstractNote = {Coherent motion regions extend in time as well as space, enforcing consistency in detected objects over long time periods and making the algorithm robust to noisy or short point tracks. As a result of enforcing the constraint that selected coherent motion regions contain disjoint sets of tracks defined in a three-dimensional space including a time dimension. An algorithm operates directly on raw, unconditioned low-level feature point tracks, and minimizes a global measure of the coherent motion regions. At least one discrete moving object is identified in a time series of video images based on the trajectory similarity factors, which is a measure of a maximum distance between a pair of feature point tracks.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2013},
month = {6}
}
Works referenced in this record:
Moving object detection in video by detecting non-Gaussian regions in subbands and active contours
conference, January 2003
- Gok, M. Y.; Cetin, A. E.
- Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)
Simultaneous Estimation of Segmentation and Shape
conference, January 2005
- Rittscher, J.; Tu, P. H.; Krahnstoever, N.
- 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
Spatio-temporal differentiation and integration in visual motion perception: An experimental and theoretical analysis of calculus-like functions in visual data processing
journal, January 1976
- Johansson, G.
- Psychological Research, Vol. 38, Issue 4
Detecting multiple moving objects in crowded environments with coherent motion regions
conference, June 2008
- Cheriyadat, Anil M.; Bhaduri, Budhendra L.; Radke, Richard J.
- 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops)