A new point-tree data structure genetic programming (PTGP) method is proposed. For the discontinuous function regression problem, the proposed method is able to identify both the function structure and discontinuities...A new point-tree data structure genetic programming (PTGP) method is proposed. For the discontinuous function regression problem, the proposed method is able to identify both the function structure and discontinuities points simultaneously. It is also easy to be used to solve the continuous function's regression problems. The numerical experiment results demonstrate that the point-tree GP is an efficient alternative way to the complex function identification problems.展开更多
红树林是重要的碳汇生态系统。激光雷达LiDAR (Light Detection And Ranging)是获取林木三维结构参数进行生物量估算的重要技术手段。针对仅利用机载LiDAR难以完整描述红树林三维结构的问题,本文以广东省湛江市英罗港和广西壮族自治区...红树林是重要的碳汇生态系统。激光雷达LiDAR (Light Detection And Ranging)是获取林木三维结构参数进行生物量估算的重要技术手段。针对仅利用机载LiDAR难以完整描述红树林三维结构的问题,本文以广东省湛江市英罗港和广西壮族自治区茅尾海红树林保护区为研究区,利用无人机载和手持式LiDAR获取的点云数据,提出了一种红树冠层下部约束聚类分割方法,对木榄、红海榄、桐花树等不同类型红树的单木分割以及树高、冠幅的进行提取,并与传统单木分割算法进行了对比和分析。结果表明:本文提出的结合空地LiDAR数据的单木分割算法,在不同类型红树单木分割中均取得了较高的单木检出率,与传统的冠层高度模型分割法相比较,单木检出率提升了13.4%—26.7%。其次,有效提高了红树树高的提取精度。3种红树树高参数提取值与实测值之间的R2提高了1.8%—42.2%,RMSE降低了3.4%—55.3%。此外,由于红树冠幅分割结果存在提取值偏小的规律,本研究将能够表征红树冠层交叠密集程度的点云密度变量作为修正因子,经修正后的RMSE降低了45.25%—53.33%。因此,本文提出的联合空地LiDAR的红树林单木生长参数提取方法,可以实现精确的红树单木点云分割并有效提升红树生长参数提取精度,为红树林生物量估算及碳汇能力评估提供了技术和数据支撑。展开更多
基金Supported by the National Natural Science Foundation(60173046)and the Natural Science Foundation of Province(2002AB040)
文摘A new point-tree data structure genetic programming (PTGP) method is proposed. For the discontinuous function regression problem, the proposed method is able to identify both the function structure and discontinuities points simultaneously. It is also easy to be used to solve the continuous function's regression problems. The numerical experiment results demonstrate that the point-tree GP is an efficient alternative way to the complex function identification problems.
文摘红树林是重要的碳汇生态系统。激光雷达LiDAR (Light Detection And Ranging)是获取林木三维结构参数进行生物量估算的重要技术手段。针对仅利用机载LiDAR难以完整描述红树林三维结构的问题,本文以广东省湛江市英罗港和广西壮族自治区茅尾海红树林保护区为研究区,利用无人机载和手持式LiDAR获取的点云数据,提出了一种红树冠层下部约束聚类分割方法,对木榄、红海榄、桐花树等不同类型红树的单木分割以及树高、冠幅的进行提取,并与传统单木分割算法进行了对比和分析。结果表明:本文提出的结合空地LiDAR数据的单木分割算法,在不同类型红树单木分割中均取得了较高的单木检出率,与传统的冠层高度模型分割法相比较,单木检出率提升了13.4%—26.7%。其次,有效提高了红树树高的提取精度。3种红树树高参数提取值与实测值之间的R2提高了1.8%—42.2%,RMSE降低了3.4%—55.3%。此外,由于红树冠幅分割结果存在提取值偏小的规律,本研究将能够表征红树冠层交叠密集程度的点云密度变量作为修正因子,经修正后的RMSE降低了45.25%—53.33%。因此,本文提出的联合空地LiDAR的红树林单木生长参数提取方法,可以实现精确的红树单木点云分割并有效提升红树生长参数提取精度,为红树林生物量估算及碳汇能力评估提供了技术和数据支撑。
