Abstract
We describe a learning-based 3D object recognition pipeline developed under the DARPA URGENT program for analyzing a large LIDAR dataset collected by both airborne and ground platforms for an extended urban area. Our approach utilizes a novel strip-based cueing approach that incorporates the properties and context of urban objects. Strip-based cueing segments potential objects and assigns them to appropriate classification stages. Our learning-based recognition pipeline successfully recognized 17 3D object classes in LIDAR data collected in and over Ottawa, Canada with high efficiency and average accuracy of 70%.
© 2010 Optical Society of America
PDF ArticleMore Like This
Kunwar K. Singh, John B. Vogler, Qingmin Meng, and Ross K. Meentemeyer
OMC2 Optical Remote Sensing of the Environment (ORS) 2010
Riviere Nicolas, Dupouy Paul-Édouard, Moussous Ahmed, Schilling Anita, and Viala Erwan
LsM3C.3 Applications of Lasers for Sensing and Free Space Communications (LS&C) 2022
Nina Varney and Vijayan Asari
JTu2C.5 Imaging Systems and Applications (IS) 2014