Title
On the effect of feedback in multilevel representation spaces for visual surveillance tasks
Abstract
In this work we propose a general top-down feedback scheme between adjacent description levels to interpret video sequences. This scheme distinguishes two types of feedback: repair-oriented feedback and focus-oriented feedback. With the first it is possible to improve the system's performance and produce more reliable and consistent information, and with the second it is possible to adjust the computational load to match the aims. Finally, the general feedback scheme is used in different examples for a visual surveillance application which improved the final result of each description level by using the information in the higher adjacent level.
Year
DOI
Venue
2009
10.1016/j.neucom.2008.06.013
Neurocomputing
Keywords
Field
DocType
visual surveillance systems,general top-down feedback scheme,consistent information,description level,different example,general feedback scheme,repair-oriented feedback,feedback between description levels,adjacent description level,predictive diagnosis task,visual surveillance task,computational load,higher adjacent level,multilevel representation space,video sequence interpretation,focus-oriented feedback,high level vision,top down
Computer science,High level vision,Artificial intelligence,Visual surveillance,Machine learning
Journal
Volume
Issue
ISSN
72
4-6
Neurocomputing
Citations 
PageRank 
References 
7
0.58
13
Authors
6
Name
Order
Citations
PageRank
Enrique J. Carmona126614.01
Mariano Rincón2737.67
Margarita Bachiller3172.82
Javier Martínez-Cantos4824.17
Rafael Martínez-Tomás58911.14
José Mira654371.44