A Novel Algorithm of Target Pseudo-Color Fusion Based on Image Features

Author

Qin, Qingwang ; Xu, Tingfa ; Xiao, Manjun ; Ni, Guoqiang

Author_Institution

Dept. of Opt. Eng., Beijing Inst. of Technol., Beijing

fYear

2008

fDate

22-24 Oct. 2008

Firstpage

1

Lastpage

5

Abstract

A novel target pseudo-color image fusion algorithm for visual and infrared images is proposed in this paper based on image features in wavelet domain. After wavelet decomposed from source images, edge features are extracted from each low frequency component. The fusion rules are defined by the edge information, using local modulus maximum rule for edge pixels and its sub-band neighboring pixels, and weighted mean coefficient rule for non-edge pixels. The interested targets are extracted respectively by threshold segmentation method for infrared image and moving targets detection method for motion image sequences. Fusion result is mapped into local pseudo-color image in HSV color space, in order to highlight infrared hot targets and moving targets. The simulation experiments show that the fusion image has good visual effect, and also has good performance on the objective evaluation and anti-noise ability.

Keywords

edge detection; feature extraction; image colour analysis; image fusion; image motion analysis; image segmentation; image sequences; infrared imaging; object detection; wavelet transforms; HSV color space; antinoise ability; edge feature extraction; edge information; edge pixels; image features; image fusion; infrared hot targets; infrared images; local modulus maximum rule; motion image sequences; moving target detection; target pseudocolor fusion; threshold segmentation method; visual effect; visual images; wavelet decomposition; wavelet domain; weighted mean coefficient rule; Data mining; Feature extraction; Frequency; Image edge detection; Image fusion; Image segmentation; Infrared detectors; Infrared imaging; Object detection; Wavelet domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2008. CCPR '08. Chinese Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-2316-3

Type

conf

DOI

10.1109/CCPR.2008.39

Filename

4662992