An intelligent model for visual scene analysis and compression
Joint Authors
Source
The International Arab Journal of Information Technology
Issue
Vol. 10, Issue 2 (31 Mar. 2013)11 p.
Publisher
Publication Date
2013-03-31
Country of Publication
Jordan
No. of Pages
11
Main Subjects
Abstract EN
This paper presents an improved approach for indicating visually salient regions of an image based upon a known visual search task.
The proposed approach employs a robust model of instantaneous visual attention (i.
e.
“bottom-up”) combined with a pixel probability map derived from the automatic detection of a previously-seen object (task-dependent i.
e.
top-down”).
The objects to be recognized are parameterized quickly in advance by a viewpoint-invariant spatial distribution of Speeded up Robust Features (SURF) interest-points.
The bottom-up and top-down object probability images are fused to produce a task-dependent saliency map.
The proposed approach is validated using observer eye-tracker data collected under object search-and-count tasking.
Proposed approach shows 13 % higher overlap with true attention areas under task compared to bottom-up saliency alone.
The new combined saliency map is further used to develop a new intelligent compression technique which is an extension of Discrete Cosine Transform (DCT) encoding.
The proposed approach is demonstrated on surveillance-style footage throughout.
American Psychological Association (APA)
Rahman, Amjad& Saba, Tanzila. 2013. An intelligent model for visual scene analysis and compression. The International Arab Journal of Information Technology،Vol. 10, no. 2.
https://search.emarefa.net/detail/BIM-311944
Modern Language Association (MLA)
Rahman, Amjad& Saba, Tanzila. An intelligent model for visual scene analysis and compression. The International Arab Journal of Information Technology Vol. 10, no. 2 (Mar. 2013).
https://search.emarefa.net/detail/BIM-311944
American Medical Association (AMA)
Rahman, Amjad& Saba, Tanzila. An intelligent model for visual scene analysis and compression. The International Arab Journal of Information Technology. 2013. Vol. 10, no. 2.
https://search.emarefa.net/detail/BIM-311944
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references.
Record ID
BIM-311944