DocumentCode
305293
Title
"Optical filter fusion for object detection"
Author
Casasent, David
Author_Institution
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Volume
1
fYear
1996
fDate
18-21 Nov. 1996
Abstract
No one algorithm is felt to be appropriate for detection. Thus to achieve this, first and most important, and most computationally intensive operation in image processing, we consider the use of several detection algorithms and fusion of their outputs to reduce false alarms PFA while retaining high detection rates P/sub D/. The detection algorithms must be shift-invariant, since multiple objects can be present and since object location is not known. Thus, correlation filters are attractive (they are shift-invariant and provide processing gain).
Keywords
image processing; object detection; optical correlation; physics computing; spatial filters; wavelet transforms; computationally intensive operation; correlation filters; detection algorithms; false alarm reduction; high detection rates; image processing; multiple objects; object detection; object location; optical filter fusion; processing gain; shift-invariant; spatial filters; Constraint optimization; Data processing; Detection algorithms; Gabor filters; Image processing; Logic; Object detection; Optical distortion; Optical filters; Wavelet transforms;
fLanguage
English
Publisher
ieee
Conference_Titel
Lasers and Electro-Optics Society Annual Meeting, 1996. LEOS 96., IEEE
Conference_Location
Boston, MA, USA
Print_ISBN
0-7803-3160-5
Type
conf
DOI
10.1109/LEOS.1996.565245
Filename
565245
Link To Document