一种修正的基于混沌预测误差的目标检测算法  

A Modified Algorithm of Target Detection Based on Chaotic Prediction Error

作　　者：张亚飞[1] 朱敏慧[1] 谢明鸿[2] 

机构地区：[1]中国科学院电子学研究所微波成像技术国家重点实验室,北京100080 [2]中国科学院研究生院,北京100049

出　　处：《测试技术学报》2007年第3期236-240,共5页Journal of Test and Measurement Technology

摘　　要：基于混沌预测误差的目标检测算法是检测混沌背景下目标的算法.本文对该算法的检测结果进行了分析,分析结果表明其检测到的目标区域比实际的目标区域大.针对这个问题,对基于混沌预测误差的目标检测结果进行了修正,修正后的结果更接近于目标的真实大小.用Lorenz混沌系统产生的仿真数据和实测的机载海面合成孔径雷达(Synthetic Aperture Radar,SAR)图像进行了实验.实验结果与理论分析的结果一致,从而证明了理论分析的正确性.The detection algorithm based on chaotic prediction error is used to detect objects under a chaotic background. The detection result of this algorithm is analyzed in this paper. The analysis result shows that the target region detected according to the algorithm is larger than the actual one. Aiming at the problem, the detection result based on chaotic prediction error is modified. The modified result is much closer to the real size of a target. The experiment was performed with simulation data generated by the Lorenz chaos system and the real ocean image data collected by airborne Synthetic Aperture Radar （SAR）. Experimental results accord with that of the theoretical analysis. The validity of theoretical analysis is proved.

关 键 词：混沌 神经网络 预测误差 目标检测 

分 类 号：TN911.23[电子电信—通信与信息系统]