基于星载SAR与AIS综合的舰船目标监视关键技术研究
发布时间:2018-11-20 19:30
【摘要】:随着海洋监视需求与日俱增,海洋监视技术发展受到越来越多国家的重视。星载合成孔径雷达(Synthetic Aperture Radar,SAR)已广泛应用于大范围海洋监视,特别地,其全天时、全天候和宽覆盖的工作能力使其成为监视远洋舰船目标的首选。然而,星载SAR图像舰船目标分类识别难度较大,极大地影响了舰船目标监视效率。针对SAR海洋监视应用的迫切需求与实际困难,瞄准国内外先进技术发展趋势,结合“十二五”武器装备预研项目,本文以自动识别系统(Automatic Identification System,AIS)辅助提高星载SAR图像舰船目标解译能力为研究出发点,对基于星载SAR与AIS综合的舰船目标监视关键技术进行研究与探索。基于星载SAR与AIS综合的舰船目标监视本质上是信息融合问题。本文在对基于星载SAR与AIS综合的舰船目标监视技术的研究背景、研究现状及发展趋势归纳、总结与分析的基础上,对基于星载SAR与AIS综合的舰船目标监视关键技术进行了正确地定位,从特征层信息融合考虑,重点对面向融合的星载SAR与AIS信息预处理、星载SAR与AIS数据关联以及星载SAR与AIS信息舰船目标融合检测与识别三项关键技术进行研究。面向融合的星载SAR与AIS信息预处理是研究基础。为了得到精确的舰船特征信息,研究了星载SAR图像舰船目标信息提取和AIS信息解码技术。针对复杂海况条件下星载SAR图像舰船目标检测问题,提出了一种高分辨率星载SAR图像舰船目标自适应恒虚警率检测算法,较好地解决了海面不均匀SAR图像舰船检测虚警率高的问题。在此基础上对舰船几何、地理与运动参数提取方法进行了归纳总结。研究实现了星载AIS“天拓一号”和岸基AIS信息解码及校验方法。在对星载SAR图像数据质量及定位误差水平分析基础上,实验研究了星载SAR与AIS信息时空校准方法。星载SAR与AIS数据关联是研究核心。首先研究了基于位置特征信息的星载SAR与AIS数据关联方法。在分析影响星载SAR与AIS数据关联主要因素的基础上对其三个关键环节——位置投影、位置预测与搜索匹配进行了实验分析。为了增强基于位置特征信息的星载SAR与AIS数据关联的鲁棒性,分别对其三个关键环节进行改进。针对复杂海况及舰船非线性运动的情况,提出了改进的舰船运动预测模型,包括航向变化航位预测模型以及航位灰色预测模型。针对星载SAR图像运动舰船目标存在多普勒位移现象,在分析影响多普勒位移精度因素及其误差的基础上,提出了多普勒位移估计中投影航向与投影航速估计的改进方法。针对系统误差较大以及高密度航行等情况,提出了基于空间拓扑结构特征的星载SAR与AIS数据关联算法——基于一致性点漂移(Coherent Point Drift,CPD)的数据关联方法,实验评估了算法性能。在对基于位置特征信息的星载SAR与AIS数据关联研究基础上,对基于位置与属性特征信息融合的星载SAR与AIS数据关联算法进行了研究探索。提出了基于位置与属性特征信息融合的星载SAR与AIS数据关联方法,具体分析了其关键技术——融合特征选择、融合决策准则与决策结果评估。重点针对融合决策准则,实验研究对比分析了加权平均、非线性乘积、Dempster-Shafer(DS)证据理论推理以及模糊综合四种融合决策方法的特点。星载SAR与AIS信息舰船目标融合检测与识别是研究目的。与星载SAR图像舰船目标检测与识别相比,有效地提高了舰船目标监视效率。首先提出了星载SAR与AIS信息舰船目标融合检测与识别模型,为融合检测与识别提供了技术路线与方案。特别地,提出了一种基于层次分析法的高分辨率星载SAR图像舰船目标分类识别方法,建立了舰船特征选择和分类决策中新的客观评价准则,并利用TerraSAR-X数据实验验证了其有效性,为星载SAR与AIS信息舰船目标融合识别研究提供了技术支撑。最后利用实测数据进行了星载SAR与AIS信息舰船目标融合检测与识别实验,实验分析验证了星载SAR与AIS信息舰船目标融合检测与识别技术方案的可行性。
[Abstract]:With the increasing demand of the ocean monitoring, the development of ocean monitoring technology has been paid more and more attention by more and more countries. The star-borne synthetic aperture radar (SAR) has been widely used in the wide range of ocean surveillance, and in particular, it is the first choice to monitor the target of the ocean-going ship all day, all-weather and wide coverage. however, that recognition difficulty of the target classification of the star-borne SAR image is great, and the target monitoring efficiency of the ship is greatly influenced. Aiming at the urgent demand and practical difficulties of the application of SAR's marine surveillance, aiming at the development trend of advanced technology at home and abroad, and combining with the pre-research project of the 鈥,
本文编号:2345776
[Abstract]:With the increasing demand of the ocean monitoring, the development of ocean monitoring technology has been paid more and more attention by more and more countries. The star-borne synthetic aperture radar (SAR) has been widely used in the wide range of ocean surveillance, and in particular, it is the first choice to monitor the target of the ocean-going ship all day, all-weather and wide coverage. however, that recognition difficulty of the target classification of the star-borne SAR image is great, and the target monitoring efficiency of the ship is greatly influenced. Aiming at the urgent demand and practical difficulties of the application of SAR's marine surveillance, aiming at the development trend of advanced technology at home and abroad, and combining with the pre-research project of the 鈥,
本文编号:2345776
本文链接:https://www.wllwen.com/kejilunwen/dizhicehuilunwen/2345776.html