【作者】 夏日辉； 刘冬梅； 何昕； 王东鹤；

【Author】 Xia Rihui~1 Liu Dongmei~1 He Xin~2 Wang Donghe~(2,3) (1 Changchun University Science and Technology Changchun 130022 China;2 Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Science Changchun 130033 China;3 School of Graduate Chinese Academy of Science Beijing 100049 China)

【机构】 长春理工大学； 中国科学院长春光学精密机械与物理研究所； 中国科学院研究生院；

【摘要】 本文提出了一种形态学的图像分割方法,用于复杂背景下较小飞机目标的提取。首先使用顶帽变换与底帽变换消除不均匀亮度背景,并通过将二者做差取绝对值的方法来完成对目标的分割。分析云层对目标分割的影响,确定选取阈值的原则。试验证明该方法能够较好的从大视场复杂背景下提取较小的飞机目标。更多还原

【Abstract】 This paper proposed a method for extracting small plane target from complex background based on a morphological transform.First top-hat and bottom-hat transformation are applied to eliminate variant illumination of image take the absolute value of the two transformation result Then choose a threshold to complete segmentation of target.Through the analysis of impact of cloud to determine the principle of choosing threshold The experiment proved this method is able to obtain fine segmentation effect of the small plane target from big field of view and complex background.更多还原