目前,高光谱异常检测的典型方法有:Reed和Xiaoli Yu提出的RX方法[1]和基于光谱混合模型的低概率检测(Low Probability Detection,LPD)方法[2]。
基于6个网页-相关网页
低概率的检测 low probability of detection
In this paper,we use low probability detection to fuse the data in feature level;then segment the image and detect anomaly elements. The result eliminates much false alarm and improves the detectability.
提出的异常检测算法是利用低概率检测算法对高光谱数据先进行特征层融合 ,再进行分割、提取异常点 ,其结果降低了虚警和漏警。
参考来源 - 基于特征层融合的高光谱图像异常检测算法研究·2,447,543篇论文数据，部分数据来源于NoteExpress
针对低检测概率下的无源定位问题，提出一种基于滑窗批处理的多传感器融合跟踪算法。
For the problem of passive location under low detection probability, a multi-sensor fusion tracking algorithm based on sliding window batch technique is presented.
分析表明，本文提出的伪码序列捕获系统具有检测概率高、虚警概率低和平均捕获时间短的特点。
According to the result of the analysis, the designed digital code acquisition system has higher probability of detection, lower probability of false alarm and shorter average acquisition time.
试验结果表明，采用以上这些方法在低信噪比强窄带干扰情况下，对于LF M信号具有较高的正确检测概率及参数测量精度。
The experiment result proves that high detecting probabilities and parameter measuring accuracy can be obtained by these methods under low SNR and strong narrow jamming conditions.
应用推荐