Saliency-based automatic target detection in forward looking infrared images

Author

Li, Wei ; Pan, Chunhong ; Liu, Li-xiong

Author_Institution

Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China

fYear

2009

fDate

7-10 Nov. 2009

Firstpage

957

Lastpage

960

Abstract

A saliency-based target detection method for forward looking infrared (FLIR) image is proposed. Firstly, saliency map is computed using scale-space representation and separated into dark saliency map (DSM) and bright saliency map (BSM). Secondly, dark and bright regions of interest (ROI) are detected by respective type of saliency map using marker-based maximally stable extremal regions (MSER) detection algorithm. Finally, shape matching algorithm is applied after grouping of the two types of ROI for object detection. Experimental results show that this work provides a promising way to solve the problems caused by salient dark parts of target.

Keywords

image representation; infrared imaging; object detection; forward looking infrared images; maximally stable extremal regions; object detection; saliency map; saliency-based automatic target detection; scale-space representation; Automation; Computer science; Detection algorithms; Infrared detectors; Infrared imaging; Laboratories; Object detection; Pattern recognition; Shape; Signal processing algorithms; forward looking infrared; region of interest; saliency map; shape matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2009 16th IEEE International Conference on

Conference_Location

Cairo

ISSN

1522-4880

Print_ISBN

978-1-4244-5653-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2009.5414028

Filename

5414028