Bayesian approach to single-tree detection in airborne laser scanning – use of training data for prior and likelihood modeling

Teemu Luostari,Timo Lähivaara,Petteri Packalen,Aku Seppänen

doi:10.1088/1742-6596/1047/1/012008

Teemu Luostari, Timo Lähivaara + Show 2 more

Open Access

https://doi.org/10.1088/1742-6596/1047/1/012008

Copy DOI

Abstract

This paper introduces a novel computational approach to handling remote sensing data from forests. More specifically, we consider the problem of detecting an unknown number of trees based on airborne laser scanning (ALS) data. In addition to detecting the locations of individual trees, their heights and crown shapes are estimated. This detection-estimation problem is treated in the Bayesian inversion framework. We use simplified, rotationally symmetric models for the tree canopies to model the echoes of laser pulses from the canopies. To account for the associated modeling errors, we use training data consisting of ALS data and field measurements to build a likelihood function which models statistically the propagation of a laser beam in the presence of a canopy. The training data is utilized also for constructing empirical prior models for the crown height/shape parameters. As a Bayesian point estimate, we consider the maximum a posteriori estimate. The proposed approach is tested with ALS measurement data from boreal forest, and validated with field measurements.

Highlights

Airborne laser scanning (ALS) is a widely used tool for remote sensing of forest [7, 9, 11]
ALS is based on light detection and ranging (LiDAR) technology, where laser beams are directed towards ground within a device-specific scan angle; these beams reflect from surfaces of objects they encounter, such as tree crowns and ground
In this paper, we studied the problem of single tree detection using ALS data

Summary

Introduction

Airborne laser scanning (ALS) is a widely used tool for remote sensing of forest [7, 9, 11]. ALS is based on light detection and ranging (LiDAR) technology, where laser beams are directed towards ground within a device-specific scan angle; these beams reflect from surfaces of objects they encounter, such as tree crowns and ground (see Figure 1). The times of the pulses reflected back from the tree crowns/ground are recorded and transformed into distance information, which together with constantly determined position and orientation of the ALS device allow for calculating coordinates on the Earth’s surface. The ALS point clouds include accurate (yet discrete) information of the ground level, and simultaneously versatile information on the structure of the forest

Objectives

Methods

Results

Conclusion