Share Email Print
cover

Proceedings Paper

A machine learning pipeline for automated registration and classification of 3D lidar data
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Despite the large availability of geospatial data, registration and exploitation of these datasets remains a persis- tent challenge in geoinformatics. Popular signal processing and machine learning algorithms, such as non-linear SVMs and neural networks, rely on well-formatted input models as well as reliable output labels, which are not always immediately available. In this paper we outline a pipeline for gathering, registering, and classifying initially unlabeled wide-area geospatial data. As an illustrative example, we demonstrate the training and test- ing of a convolutional neural network to recognize 3D models in the OGRIP 2007 LiDAR dataset using fuzzy labels derived from OpenStreetMap as well as other datasets available on OpenTopography.org. When auxiliary label information is required, various text and natural language processing filters are used to extract and cluster keywords useful for identifying potential target classes. A subset of these keywords are subsequently used to form multi-class labels, with no assumption of independence. Finally, we employ class-dependent geometry extraction routines to identify candidates from both training and testing datasets. Our regression networks are able to identify the presence of 6 structural classes, including roads, walls, and buildings, in volumes as big as 8000 m3 in as little as 1.2 seconds on a commodity 4-core Intel CPU. The presented framework is neither dataset nor sensor-modality limited due to the registration process, and is capable of multi-sensor data-fusion.

Paper Details

Date Published: 1 May 2017
PDF: 7 pages
Proc. SPIE 10199, Geospatial Informatics, Fusion, and Motion Video Analytics VII, 101990D (1 May 2017); doi: 10.1117/12.2262872
Show Author Affiliations
Abhejit Rajagopal, Univ. of California, Santa Barbara (United States)
Toyon Research Corp. (United States)
Karthik Chellappan, Toyon Research Corp. (United States)
Shivkumar Chandrasekaran, Univ. of California, Santa Barbara (United States)
Andrew P. Brown, Toyon Research Corp. (United States)


Published in SPIE Proceedings Vol. 10199:
Geospatial Informatics, Fusion, and Motion Video Analytics VII
Kannappan Palaniappan; Peter J. Doucette; Gunasekaran Seetharaman; Anthony Stefanidis, Editor(s)

© SPIE. Terms of Use
Back to Top