摘要： 提出了一种基于区域目标检测的红外与可见光图像序列融合方法。该方法通过目标检测技术将源图像序列分割成目标和背景区域，并在目标和背景区域里分别采用不同的融合规则，同时使用双树复小波变换方法使每一幅源图像具有移不变多分辨率表示。实验采用了实际图像序列数据。融合结果表明，该方法是可行和高效的，且比其他图像融合方法具有更好的性能。

关键词: 图像序列融合, 区域目标检测, 双树复小波变换, 互信息

Abstract: A new infrared and visible image sequences fusion scheme based on region target detection is proposed. Target detection technique is employed to segment the source image sequences into target and background regions. Different fusion rules are adopted respectively in target and background regions. The dual-tree complex wavelet transform(DT-CWT) method is introduced to achieve shift invariant multi-resolution representation of each source images. Fusion experiments on real world image sequences indicate that the proposed method is effective and efficient, which achieves better performance than the generic fusion method.

Key words: image sequences fusion, region target detection, dual-tree complex wavelet transform(DT-CWT), mutual information

中图分类号: 

• TP391.41