CAJ | 학술논문

针对可见光和红外图像融合问题，提出一种有效的融合方法。首先，将多尺度分解后的高频系数分为高低两层，并针对各层系数的特点，分别采用基于像素和基于区域特征加权的融合算法合成得到融合图像的高频系数；为了进一步提升融合图像的整体对比度，提高目标的指示能力，提出通过区域平均梯度特征自适应加权的方法得到融合图像的低频系数；最后，对融合的低频和高频系数进行多尺度逆变换得到融合图像。通过主观观察以及客观指标对比证明，该方法的融合性能优于经典的融合方法。
침대가견광화홍외도상융합문제，제출일충유효적융합방법。수선，장다척도분해후적고빈계수분위고저량층，병침대각층계수적특점，분별채용기우상소화기우구역특정가권적융합산법합성득도융합도상적고빈계수；위료진일보제승융합도상적정체대비도，제고목표적지시능력，제출통과구역평균제도특정자괄응가권적방법득도융합도상적저빈계수；최후，대융합적저빈화고빈계수진행다척도역변환득도융합도상。통과주관관찰이급객관지표대비증명，해방법적융합성능우우경전적융합방법。
Aiming to fusion question on the infrared and visible images, a novel effective image fusion method was proposed in this paper. Firstly, the high frequency coefficient after multiscale decomposition was divided into low and high layers, and then, according to the characteristics of each layer, the high frequency coefficient of the fused image was obtained by method based on pixel and method based on feature weighted respectively. Secondly, in order to further enhance the overall contrast of the fused image, and the capabilities of target indication, the low frequency coefficient of the fused image was obtained by adaptive weighted method based on regional average gradient. Finally, the fused image was obtained by inverse multi -scale transformation. The subjective observation and the comparison of the image′ s objective indexes prove together that the method proposed in this paper is better than the classical methods.