Optimizing Multiple Kernel Learning for the Classification of UAV Data

Caroline Gevaert,Claudio Persello,George Vosselman

doi:10.3390/rs8121025

Caroline Gevaert, Claudio Persello + Show 1 more

Open Access

https://doi.org/10.3390/rs8121025

Copy DOI

Journal: Remote sensing	Publication Date: Dec 16, 2016
Citations: 23	License type: CC BY 4.0

Affiliation: University of Twente

Abstract

Unmanned Aerial Vehicles (UAVs) are capable of providing high-quality orthoimagery and 3D information in the form of point clouds at a relatively low cost. Their increasing popularity stresses the necessity of understanding which algorithms are especially suited for processing the data obtained from UAVs. The features that are extracted from the point cloud and imagery have different statistical characteristics and can be considered as heterogeneous, which motivates the use of Multiple Kernel Learning (MKL) for classification problems. In this paper, we illustrate the utility of applying MKL for the classification of heterogeneous features obtained from UAV data through a case study of an informal settlement in Kigali, Rwanda. Results indicate that MKL can achieve a classification accuracy of 90.6%, a 5.2% increase over a standard single-kernel Support Vector Machine (SVM). A comparison of seven MKL methods indicates that linearly-weighted kernel combinations based on simple heuristics are competitive with respect to computationally-complex, non-linear kernel combination methods. We further underline the importance of utilizing appropriate feature grouping strategies for MKL, which has not been directly addressed in the literature, and we propose a novel, automated feature grouping method that achieves a high classification accuracy for various MKL methods.

Highlights

Unmanned Aerial Vehicles (UAVs) are gaining enormous popularity due to their ability of providing high-quality spatial information in a very flexible manner and at a relatively low cost
We demonstrate the suitability of Multiple Kernel Learning (MKL) as a classification method for integrating heterogeneous features obtained from UAV data
Utilizing a novel feature grouping strategy and a simple heuristic for weighting the individual input kernels (CSMKSVM), we are able to obtain a classification accuracy of 90.6%, an increase of 5.2% over a standard Support Vector Machine (SVM) implementation and 4.1% over a random forest classification model

Summary

Introduction

Unmanned Aerial Vehicles (UAVs) are gaining enormous popularity due to their ability of providing high-quality spatial information in a very flexible manner and at a relatively low cost Another considerable advantage is the simultaneous acquisition of a photogrammetric point cloud (i.e., a 3D model consisting of a collection of points with X, Y, Z coordinates) and very high-resolution imagery. Key tie points are identified in multiple images, and a bundle-block adjustment is applied to simultaneously identify the camera parameters of each image, as well as the location of these tie points in 3D space Note that this step usually requires the inclusion of external ground control points for an accurate georeferencing. The optimization function is solved using the Lagrangian dual formulation as follows: max n ∑

Objectives

Methods

Results

Conclusion