Color image fusion method for enhancing situation awareness of ICA

Luo Yuan; Zhang Ke; Ji Ming

doi:10.3788/IRLA201645.S126002

Airborne sensors reconnaissance and ground data fusion processing is the fourth grade of UAV situation awareness that planned by USA Office of the Secretary of Defense. Independent Component Analysis(ICA) that applied to the image processing field is a novel method of transform domain in the analysis of human visual system characteristics based on sparse coding theory, with multiple directions, excellent characteristic extraction and edge modeling feature. Color transfer is the best way to get natural sense color fusion image. The combination of studies highlighted the band characteristics of the natural sense color fusion method so as to enhance UAV situation awareness. Training image database was established according to the scene and the independent band feature information was extracted to construct ICA domain analysis kernel and synthesis kernel. In the ICA domain, the gray fusion image was generated applying area energy fusion rules, the gray fusion image color information was given using source image linear projection to the color channel. The various channels of source color fusion image and color reference image were multi-resolution decomposed using steerable pyramid, each channel transfer mean and variance were independently completed. Finally a similar color fusion image was obtained. Eye perception and objective evaluation show that outstanding band features and natural color enhance detail information to further improve the airborne platforms scene perception.

Color image fusion method for enhancing situation awareness of ICA

1. College of Astronautics,Northwestern Polytechnical University,Xi'an 710072,China;

2. Xi'an Institute of Applied Optics,Xi'an 710065,China

Received Date: 2016-01-10

Rev Recd Date: 2016-02-20

Publish Date: 2016-05-25

Key words:

Abstract: Airborne sensors reconnaissance and ground data fusion processing is the fourth grade of UAV situation awareness that planned by USA Office of the Secretary of Defense. Independent Component Analysis(ICA) that applied to the image processing field is a novel method of transform domain in the analysis of human visual system characteristics based on sparse coding theory, with multiple directions, excellent characteristic extraction and edge modeling feature. Color transfer is the best way to get natural sense color fusion image. The combination of studies highlighted the band characteristics of the natural sense color fusion method so as to enhance UAV situation awareness. Training image database was established according to the scene and the independent band feature information was extracted to construct ICA domain analysis kernel and synthesis kernel. In the ICA domain, the gray fusion image was generated applying area energy fusion rules, the gray fusion image color information was given using source image linear projection to the color channel. The various channels of source color fusion image and color reference image were multi-resolution decomposed using steerable pyramid, each channel transfer mean and variance were independently completed. Finally a similar color fusion image was obtained. Eye perception and objective evaluation show that outstanding band features and natural color enhance detail information to further improve the airborne platforms scene perception.

HTML

Reference (12)

[1]	Goshtasby A A, Nikolov S. image fusion:advances in the state of the art[J]. Information Fusion, 2008, 8(2):114-118.
[2]	Office of the Secretary of Defense. Unmanned aircraft systems road map 2005-2030[M]. USA:Office of the Secretary of Defense, 2005:47-48.
[3]	Hill P, Canagarajah N, Bull D. Image fusion using complex wavelets[C]//Proceedings of the 13th British Machine Vision Conference, 2002.
[4]	Pajares G, de la Cruz J M. A wavelet-based image fusion tutorial[J]. Pattern Recognition, 2004, 37(9):1855-1872.
[5]	Luo Xiaoyan, Zhang Jun, Dai Qionghai. A regional image fusion based on similarity characteristics[J]. Signal Processing, 2012, 92:1268-1280.
[6]	Toet A, Franken E M. Perceptual evaluation of different image fusion schemes[J]. Display, 2003, 24(1):25-37.
[7]	Vinje W E, Gallant J L. Sparse coding and decorrelation in primary visual cortex during natural vision[J]. Science, 2000, 287:1273-1276.
[8]	Aapo Hyvarinen. Fast and robust fixed-point algorithms for independent component analysis[J]. IEEE Trans on Neural Networks. 1999, 10(3):626-634.
[9]	Mitianoudis N, Stathaki T. Optimal contrast for color image fusion using ICA bases[C]//Proc of the 11th International Conference on Information Fusion, 2008:4632419.
[10]	Shi Shiming, Wang Lingxue, Jin Weiqi, et al. A dual-band color imaging system for visible and thermal IR image based on transfer in YUV color space[J]. Acta Armamentarii, 2009, 30(1):30-35.(in Chinese) 史世明, 王岭雪, 金伟其, 等. 基于YUV空间色彩传递的双通道视频实时融合系统[J]. 兵工学报, 2009, 30(1):30-35.
[11]	Yuan Yihui, Zhang Junju, Chang Benkang, et al. Objective quality evaluation of visible and infrared color fusion image[J]. Optical Engineering, 2011, 50(3):033202.
[12]	Gao Shaoshu, Jin Weiqi, Wang Lingxue. Quality assessment for visible and infrared color fusion images of typical scenes[J]. Chinese Optics Letters, 2012, 10(8):081101.

Color image fusion method for enhancing situation awareness of ICA

doi: 10.3788/IRLA201645.S126002

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views