CAJ | 학술논문

为实现UCAV认知导航对地形空间环境感知信息的表征，提出了一种基于 IHDR 树的位置细胞构建方法。利用SURF算法提取环境中高鲁棒性的特征点，以特征点描述矢量及其在地理空间中的位置组合为路标信息，生成训练样本，以IHDR建树原则对路标信息双重聚类，然后将聚类后的叶子节点作为表征对应地形空间环境的位置细胞，完成位置细胞的构建。仿真结果表明，该方法构建的位置细胞能有效表征地形空间环境，对一定噪声干扰下的地形空间环境也具有识别能力。
위실현UCAV인지도항대지형공간배경감지신식적표정，제출료일충기우 IHDR 수적위치세포구건방법。이용SURF산법제취배경중고로봉성적특정점，이특정점묘술시량급기재지리공간중적위치조합위로표신식，생성훈련양본，이IHDR건수원칙대로표신식쌍중취류，연후장취류후적협자절점작위표정대응지형공간배경적위치세포，완성위치세포적구건。방진결과표명，해방법구건적위치세포능유효표정지형공간배경，대일정조성간우하적지형공간배경야구유식별능력。
In order to realize the representation of perceptual information of terrain space environment for UCAV cognitive navigation,a method is proposed to construct place cells based on IHDR tree.SURF al-gorithm is used to extract high robustness feature points in environment,the landmarks'information are combined by the description vector of feature point and its position in geographic space,so the training samples are obtained,and the double clustering of landmarks'information is achieved according to the IHDR algorithm,and the leaf nodes of clustering are regarded as place cells to represent the terrain space environment.Finally,the place cells are constructed .The simulation results show that the place cells con-structed by this method can represent the terrain space environment effectively,and have the ability of rec-ognizing terrain space environment under condition of certain noise interference.