基于VFGPIR联合特征的决策级加权融合检测方法

车载前视地表成像雷达(VFGPIR)探测浅埋目标时面临虚警率过高问题,可利用序列图像特征的联合检测解决这一问题.首先利用Fisher鉴别比(FDR)定量评估从单帧和序列图像中提取的单个特征的鉴别能力;然后针对单个最优序列特征无法满足探测指标要求提出一种基于决策级加权融合的多特征联合检测方法;最后利用接收机工作特性(ROC)曲线来验证所提方法的有效性.试验结果表明:序列特征比单帧图像特征具有更好的鉴别能力;所提方法性能优于单个最优序列特征、特征向量和多数票融合准则对应的检测结果,有望满足实际探雷应用需求.

A Decision-level Weighting Fusion Detection Method Based on the Joint Multi-features of VFGPIR

The vehicle-mounted forward-looking ground penetrating imaging radar(VFGPIR) is a feasible facility to detect shallow buried objects,but it faces a high false alarm rate.The combined detection,by using the sequence features,is proposed as the key to solve this problem.Firstly,we use the Fisher's discriminating ratio(FDR) to quantificationally evaluate the discriminating power of the individual feature component extracted from the single or serial images.Since the optimal individual sequence feature cannot s...