运动目标检测的红外与可见光图像融合方法  

Fusion scheme ofinfrared and visible images for moving object detection

作　　者：封子军[1,2] 张晓玲[1] 张慧杰[2] 

机构地区：[1]电子科技大学电子工程学院,成都611731 [2]东北师范大学计算机科学与信息技术学院,长春130117

出　　处：《计算机工程与应用》2012年第7期9-11,共3页Computer Engineering and Applications

基　　金：高等学校博士学科点专项科研基金资助课题(No.20100043120012);东北师范大学自然科学青年基金资助(No.20090302)

摘　　要：在弱可见光条件下,对同一场景监控的红外与可见光图像进行融合,使融合图像即显示红外目标,又能保留可见光图像的细节结构信息,方便观察者对场景的观察与监控。充分利用红外成像的特点,热目标与背景的温度差会使目标在红外图像中的灰度值更大。使用红外序列建立稳定的背景模型,当前帧与背景的差得到运动目标区域,然后,将目标区域内的红外目标融合到可见光图像中,达到对红外运动目标检测的目的。It is important that the fused image should show the objects coming from infrared image and preserve the spatial details of the same scene derived from visible image under poor lighting conditions. Infrared sensors, which are useful tools because of their individual modalities, can detect relative differences in the amount of the thermal energy reflected objects in the scene. Moving object regions are identified by comparison of the current image with the robust background model that is built from an infrared image sequence. The proposed fusion shceme is very suitable for image fusion ofinfrared and visible images because it displays moving objects in the nature scene, which is helpful for the human visual system.

关 键 词：目标检测 图像融合 红外图像 可见光图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]