摘要
针对复杂背景下的小目标检测问题,提出基于全变分理论的单帧红外图像空域背景杂波抑制算法。分析红外图像背景抑制的最大后验概率模型,引入全变分的概念作为背景图像的先验信息,描述估计背景的平滑度约束,从而转化为泛函极值问题进行求解。估计背景在满足对观测图像数据依赖的同时,能够保留背景图像的边缘信息,有效降低复杂背景灰度值起伏较大处的虚警。通过仿真实验验证了算法的可行性和有效性,分析结果表明其背景抑制性能较传统算法有较大提高,算法架构适用于大数据图像并行处理的工程实现。
An algorithm of spatial background clutter suppression of infrared image based on total variation theory is proposed for small target detection in complicated background. By analyzing the MAP model, the concept of total variation is introduced as prior information constraints the smoothness of background image, converting it to a functional optimization problem. While the data fidelity to observed image holds, the background estimate can still maintain edges, effectively reducing false-alarm where gray level varies dramatically in complicated background. Feasibility and effectiveness of the algorithm is verified by simulation experiments. Analysis o~ the result shows that background suppression performance is remarkably improved compared to traditional methods, with its implementation suitable for engineering fulfillment of mass image data parallel processing.
出处
《航天电子对抗》
2013年第5期30-33,61,共5页
Aerospace Electronic Warfare
关键词
全变分
背景抑制
红外小目标
目标检测
total variation
background suppression
infrared small target
target detection
