摘要
研究树林、陆地场景下可见光与红外图像彩色融合中的热目标增强方法.利用拮抗视觉特性在YUV空间融合可见光与红外图像,增强二者的独有特征;在色彩传递阶段,使用3×3大小的十字形窗口定位红外图像的热目标,当窗口的局部均值大于红外图像的整体均值时,确定该像素点处于热目标区,表征红色与亮度(Y)差异的V分量值根据局部均值与整体均值之比进行增强.仿真结果表明,算法用浓烈的红色突出红外图像的热目标,有效地提醒观察者注意感兴趣的目标,同时,可见光图像的场景细节被赋予与白天光照下彩色图像类似的自然色彩,改善了场景的深度感知,提高了形势意识能力.
Hot targets enhancement algorithm for the color fusion of visible and infrared images under trees and land background is presented. Opponent visual model is used to fuse and enhance the complementary information between visible and infrared in YUV space. During the process of color transfer, a crossed window of size 3 × 3 helps to locate the hot target in infrared image. When the local gray mean value of the window is larger than the global mean value of the infrared image, the center pixel is determined in a hot area. Then the V component that represents the difference between luminance （Y） and red color is increased by the ratio of the local gray mean value to the global mean value. Tests showed that this method pops out the hot targets with intense red and is effective on alerting observers to possible interested target. At the same time, the background is rendered a natural color appearance similar to a day-time color image, improves scene depth perception and increases situation awareness.
出处
《北京理工大学学报》
EI
CAS
CSCD
北大核心
2008年第1期1-4,共4页
Transactions of Beijing Institute of Technology
基金
国家部委预研项目(4040550103)
教育部高等学校博士学科点专研科研基金资助课题(20070007022)
