By Topic

Building extraction by fusion of LIDAR data and aerial images

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Jianhua Mao ; Research Centre of Remote Sensing and Spatial Information Science in School of Communication and Information Engineering, Shanghai University, China ; Xuefeng Liu ; Qihong Zeng

It is well know that geometric filters for points cloud can only go so far when removing above-ground phenomena for it's difficult to determine whether a laser point has hit a special object when only spatial analysis is included. And comparing to the discrete points cloud, the high quality, large-coverage images provided by aerial cameras is a very important advantage of photogrammetry, which can be a very important complement data source to the points cloud. And by a process of spectral imagery LIDAR composite, points cloud can be fused with accurate spectral images provided by aerial CCD cameras on the same board. And the points cloud, with both high quality of reflection and geometric properties, can be filtered by integrating the reflectivity and geometric method. In this paper, the measurement characteristics and advantages of reflectivity of laser scanning and CCD cameras for the classification of return points are analyzed, and a building extraction method, integrating the geometric feature and reflectivity information of the return's intensity and the spectral range of CCD camera are presented. In which, the vegetation points are filtered by spectral attributes initially, and then points belonged to the building walls are segmented by a area attributes after constructing the return points' voronoi diagram; and building surface points are filtered by plane-fitting clustering method.

Published in:

2009 Joint Urban Remote Sensing Event

Date of Conference:

20-22 May 2009