论文部分内容阅读
针对因复杂背景导致低信噪比的弱点目标探测率降低的问题,首先分析了从红外图像中探测弱点目标时,由于复杂和缓变背景下潜在目标探测率不同,而导致目标探测率降低的理论依据;并在该分析的基础上,提出了一种基于背景自适应调整的红外点目标探测算法。该方法利用鲁宾逊(Robinson)保护滤波器从经过预处理的图像中提取潜在目标;通过复杂背景模糊隶属度函数将图像映射到模糊特征平面,并由该特征平面计算背景调整因子,以对提取的潜在目标进行加权调整,从而降低了复杂背景的影响。实验结果表明,该算法可以显著提高复杂背景下红外点目标的检测概率,并且能够探测出信噪比为1的目标。
Aiming at the problem of low detection rate of target caused by complex background, this paper first analyzes the theory that when the target is detected from the infrared image, the detection rate of the target decreases due to the different target detection rate in the complex and slowly changing background Based on this analysis, an infrared point target detection algorithm based on background adaptive adjustment was proposed. The method extracts the potential target from the preprocessed image by using the Robinson filter, maps the image to the fuzzy feature plane through the complex background fuzzy membership function, and calculates the background adjustment factor from the feature plane, The potential targets extracted are weighted to reduce the impact of complex backgrounds. The experimental results show that this algorithm can significantly improve the detection probability of infrared point targets in complex background and can detect the target with signal to noise ratio of 1.