基于建筑物提取的精细尺度人口估算研究

以精细尺度的人口估算为目标，提出一种根据居民区建筑物属性估算人口数量的方法。首先基于Dempster-Shafer证据理论，结合LiDAR数据和高分辨率遥感影像进行建筑物的自动提取。根据土地利用分类图排除提取结果中的非居民区建筑后，按照线性回归的思想，通过对居民建筑物的数量、面积、体积等几何属性的优化选择建立人口估算模型。实验表明，利用该估算模型能够获得较高精度的小面积目标区域上的估算结果。该方法提高了人口估算的精细程度和自动化程度。

Investigation on Small-area Population Estimation Based on Building Extraction

In order to estimate the population of small area,a new population estimation method based on residential building attributes is presented.Firstly,buildings are extracted combining LiDAR data with high-resolution remote sensing images,using Dempster-Shafer theory of evidence.Then,all the non-residential buildings are excluded from extraction results according to land use classification map,and the population estimation model is generated by optimization choice of geometric attributes of residential buildings,such as building counts,building areas,and building volumes,based on linear regression method.The results demonstrated that proposed model yielded good small\|area population estimation results,and the proposed method improved the precision and automatic of population estimation.