自然背景中人造目标的自适应检测

Adaptive Detection of Man-Made Objects in Natural Background

本文介绍了一种在可见光和红外图像中，自动检测自然背景中人造目标的方法。该方法以分形结构做为自然背景的数学模型，利用自然背景和人造目标在分形特征上的固有相对差异检测人造目标。本文还介绍了自适应分形特征增强和组合图像检测方法，并以对实际图像的处理结果。

A procedure of detecting man-made objects in natural background from a visible image is presented,in which the fractals with self-similarity property is employed to model natural background,and the intrinsic difference in fractal characters between man-made objects and natural background is used to identify man-made objects.The methods of adaptive enhancement for fractal features and composite image segmentation are also discussed.Some experimental results for real images show that the procedure in this paper is applicable.