基于四象限探测器的地面形变特征提取算法  

The study of feature extraction algorithm of ground deformation based on four quadrant detector

作　　者：杨自香[1] YANG Zixiang(School of Information and Artificial Intelligence,Wuhu Polytechnic Institute,Wuhu Anhui 241006)

机构地区：[1]芜湖职业技术学院信息与人工智能学院,安徽芜湖241006

出　　处：《宁夏师范学院学报》2023年第7期93-100,共8页Journal of Ningxia Normal University

摘　　要：由于现有特征提取方法没有充分考虑噪声信号的影响,导致提取结果中存在大量冗余数据,提取结果存在一定的偏差,且特征提取耗时较长,为此提出一种基于四象限探测器的地面形变特征提取算法.采用四象限探测器对地面形变位置进行定位,运用小波变换方法去除由环境噪声与相关设备干扰形成的噪声信号,去除其中的冗余信息.根据噪声去除结果基于激光点云建立地面形变特征提取模型,实现地面形变特征提取.实验结果表明,该方法的特征提取结果偏差比例始终低于4%,远低于传统方法,且特征提取耗时较短,充分说明该方法的应用价值.The existing feature extraction methods do not fully consider the influence of the noise signal,and there are a large number of redundant data in the results and time-consuming.These limitations can be addressed by a ground deformation feature extraction algorithm based on the four-quadrant.The four-quadrant detector is used to locate the ground deformation position.The wavelet transform method is used to remove the noise signal and other redundant information which is formed by the environmental noise and related equipment interference.The noise extraction results and the laser point cloud are employed to set up a ground deformation feature extraction model.The results show that the method was featured by lower deviation proportion and shorter extraction time,which is suitable for the application.

关 键 词：四象限探测器 地面形变 激光点云 小波变换 去噪 

分 类 号：P237[天文地球—摄影测量与遥感]