论文部分内容阅读
复杂背景下的红外小目标检测是红外成像系统的核心技术之一,不同的背景和目标特征对检测算法的要求各有差别。为了降低系统运算量、提高小目标检测的实时性,针对扫描型红外预警系统,在分析红外小目标图像特征的基础上,提出了根据固定邻域内种子像素的属性分割图像,并结合前景和背景之间的对比度关系,进行噪声抑制和对比度增强的图像预处理方法。实验证明:该方法能够提高红外小目标图像的信噪比,降低系统后续处理的数据量,对小目标检测算法具有较好的辅助作用。
Infrared small target detection under complex background is one of the core technologies of infrared imaging system. Different background and target features have different requirements on detection algorithms. In order to reduce the computational complexity of the system and improve the real-time performance of small target detection, based on the analysis of infrared small target image features, based on the analysis of the characteristics of infrared small target image, the segmentation of images based on the attributes of seed pixels in a fixed neighborhood is proposed. Combining the foreground and background Contrast between the contrast, noise suppression and contrast enhancement image preprocessing method. Experimental results show that this method can improve the signal-to-noise ratio of small infrared target images and reduce the amount of data to be processed by the system. It is a good assistant to the small target detection algorithm.