研究了毫米波雷达和CCD摄像机两种传感器信息的D-S融合方法,论述了毫米波雷达信息采集、滤波、计算障碍物的距离和方位及判别障碍物是否在无人地面平台ROI(Region of interested)内;CCD摄像机的信息处理、分割和障碍物的宽度、高度和方...研究了毫米波雷达和CCD摄像机两种传感器信息的D-S融合方法,论述了毫米波雷达信息采集、滤波、计算障碍物的距离和方位及判别障碍物是否在无人地面平台ROI(Region of interested)内;CCD摄像机的信息处理、分割和障碍物的宽度、高度和方位角的计算。通过建立坐标系和坐标系间的齐次变换实现其空间配准。按D-S融合方法首先建立障碍物鉴别框架,通过实验确定它们对应于鉴别框架中障碍物指数的基本概率分配值,再根据D-S证据方法的组合规则计算所有证据联合作用下的融合结果,得到障碍物在无人地面平台ROI内的距离、方位和大小。在无人地面平台ROI内进行验证,本文的研究成果可行,并且具有较好的鲁棒性。展开更多
With the development of mobile technology, Internet and GIS, LBS plays an important role in various applications. From the perspective of LBS, it is one of the main tasks of matching 3-dimensional spatial-temporal tra...With the development of mobile technology, Internet and GIS, LBS plays an important role in various applications. From the perspective of LBS, it is one of the main tasks of matching 3-dimensional spatial-temporal trajectories. We present an interpoiation based Modified Hausdorff Distance algorithm for 3-dimensional spatial-temporal Trajectory Matching （IMHD-ST）. It adopts interpolation algorithm to shield the impact to the distance between trajectories due to different position updating porices, sampling granularity, initial position and so on in Moving Object Database （MOD）. Besides, it uses MHD to deal with the implicit spatial information and structural information of weighted position updating points in various trajectories and reflects the discrepancy of moving results through the spatial distance between trajectories. In addition, it adopts temporal distance corresponding to the spatial distance between trajectories to reflect the differences including direction, speed and so on during moving process. The experimental results show that the algorithrn can reflect the trajectory similarity between 3-dimensional mobile objects more correctly, accurately and robustly.展开更多
文摘研究了毫米波雷达和CCD摄像机两种传感器信息的D-S融合方法,论述了毫米波雷达信息采集、滤波、计算障碍物的距离和方位及判别障碍物是否在无人地面平台ROI(Region of interested)内;CCD摄像机的信息处理、分割和障碍物的宽度、高度和方位角的计算。通过建立坐标系和坐标系间的齐次变换实现其空间配准。按D-S融合方法首先建立障碍物鉴别框架,通过实验确定它们对应于鉴别框架中障碍物指数的基本概率分配值,再根据D-S证据方法的组合规则计算所有证据联合作用下的融合结果,得到障碍物在无人地面平台ROI内的距离、方位和大小。在无人地面平台ROI内进行验证,本文的研究成果可行,并且具有较好的鲁棒性。
文摘With the development of mobile technology, Internet and GIS, LBS plays an important role in various applications. From the perspective of LBS, it is one of the main tasks of matching 3-dimensional spatial-temporal trajectories. We present an interpoiation based Modified Hausdorff Distance algorithm for 3-dimensional spatial-temporal Trajectory Matching （IMHD-ST）. It adopts interpolation algorithm to shield the impact to the distance between trajectories due to different position updating porices, sampling granularity, initial position and so on in Moving Object Database （MOD）. Besides, it uses MHD to deal with the implicit spatial information and structural information of weighted position updating points in various trajectories and reflects the discrepancy of moving results through the spatial distance between trajectories. In addition, it adopts temporal distance corresponding to the spatial distance between trajectories to reflect the differences including direction, speed and so on during moving process. The experimental results show that the algorithrn can reflect the trajectory similarity between 3-dimensional mobile objects more correctly, accurately and robustly.
