TY - GEN
T1 - Adaptive selection of visual and infra-red image fusion rules
AU - Yang, Guang
AU - Yin, Yafeng
AU - Man, Hong
PY - 2010
Y1 - 2010
N2 - The fusion of images captured from Electrical-Optical (EO) and Infra-Red (IR) cameras has been extensively studied for military applications in recent years. In this paper, we propose a novel wavelet-based framework for online fusion of EO and IR image sequences. The proposed framework provides multiple fusion rules for image fusion as well as a novel edge-based evaluation method to select the optimal fusion rule with respect to different practical scenarios. In the fusion step, EO and IR images are decomposed into different levels by 2D discrete wavelet transform. The wavelet coefficients at each level are combined by a set of fusion rules, such as min-max selection, mean-value, weighted summations, etc. Various fused images are obtained by inverse wavelet transform of combined coefficients. In the evaluation step, Sobel operator is applied on both the fused images and original images. Compared with original images, the remaining edge information in the fused each image is calculated as the fusion quality assessment. Finally, the fused image with the highest assessment value will be selected as the fusion result. In addition, the proposed method can adaptively select the best fusion rule for EO and IR images under different scenarios.
AB - The fusion of images captured from Electrical-Optical (EO) and Infra-Red (IR) cameras has been extensively studied for military applications in recent years. In this paper, we propose a novel wavelet-based framework for online fusion of EO and IR image sequences. The proposed framework provides multiple fusion rules for image fusion as well as a novel edge-based evaluation method to select the optimal fusion rule with respect to different practical scenarios. In the fusion step, EO and IR images are decomposed into different levels by 2D discrete wavelet transform. The wavelet coefficients at each level are combined by a set of fusion rules, such as min-max selection, mean-value, weighted summations, etc. Various fused images are obtained by inverse wavelet transform of combined coefficients. In the evaluation step, Sobel operator is applied on both the fused images and original images. Compared with original images, the remaining edge information in the fused each image is calculated as the fusion quality assessment. Finally, the fused image with the highest assessment value will be selected as the fusion result. In addition, the proposed method can adaptively select the best fusion rule for EO and IR images under different scenarios.
UR - http://www.scopus.com/inward/record.url?scp=79956271746&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79956271746&partnerID=8YFLogxK
U2 - 10.1109/AIPR.2010.5759689
DO - 10.1109/AIPR.2010.5759689
M3 - Conference contribution
AN - SCOPUS:79956271746
SN - 9781424488339
T3 - Proceedings - Applied Imagery Pattern Recognition Workshop
BT - 2010 IEEE 39th Applied Imagery Pattern Recognition Workshop, AIPR 2010
T2 - 2010 IEEE 39th Applied Imagery Pattern Recognition Workshop, AIPR 2010
Y2 - 13 October 2010 through 15 October 2010
ER -