2D tree detection in large urban landscapes using aerial LiDAR data

Authors:
George Chen;Avideh Zakhor
Affiliations:
Video and Image Processing Lab, EECS Department, University of California, Berkeley;Video and Image Processing Lab, EECS Department, University of California, Berkeley
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 7
Cited 4

Random Forests

Machine Learning
Constructing 3D City Models by Merging Aerial and Ground Views

IEEE Computer Graphics and Applications
Supervised Parametric Classification of Aerial LiDAR Data

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 3 - Volume 03
Digital Image Processing (3rd Edition)

Digital Image Processing (3rd Edition)
Aerial Lidar Data Classification using AdaBoost

3DIM '07 Proceedings of the Sixth International Conference on 3-D Digital Imaging and Modeling
Automatic extraction of LIDAR data classification rules

ICIAP '07 Proceedings of the 14th International Conference on Image Analysis and Processing
Classifying urban landscape in aerial LiDAR using 3D shape analysis

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing

Tree detection from aerial imagery

Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
Classifying urban landscape in aerial LiDAR using 3D shape analysis

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Modeling residential urban areas from dense aerial LiDAR point clouds

CVM'12 Proceedings of the First international conference on Computational Visual Media
Complete residential urban area reconstruction from dense aerial LiDAR point clouds

Graphical Models

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a scalable approach to tree detection in large urban landscapes using aerial LiDAR data. Similar to our previous work in 2006, our current method consists of segmentation followed by classification. However, unlike our previous work, the current approach does not use color information or aerial imagery, and hence is more generally applicable. Also, our current approach has been successfully tested on two very large datasets, which are many orders of magnitude larger than the dataset used in 2006. Specifically, we use a North American dataset, containing 125 million LiDAR returns over 3 km2, and a European dataset, containing 200 million LiDAR returns over 7 km2. For both datasets, we report precision and recall rates of over 95%.