A Novel Deep Learning Method to Identify Single Tree Species in UAV-Based Hyperspectral Images

Gabriela Takahashi Miyoshi,Mauro Dos Santos Arruda,Nilton Nobuhiro Imai,Antonio Maria Garcia Tommaselli,Lucas Prado Osco,Diogo Nunes Gonçalves,Eija Honkavaara,José Marcato Junior,Wesley Nunes Gonçalves

doi:10.3390/rs12081294

Abstract

Deep neural networks are currently the focus of many remote sensing approaches related to forest management. Although they return satisfactory results in most tasks, some challenges related to hyperspectral data remain, like the curse of data dimensionality. In forested areas, another common problem is the highly-dense distribution of trees. In this paper, we propose a novel deep learning approach for hyperspectral imagery to identify single-tree species in highly-dense areas. We evaluated images with 25 spectral bands ranging from 506 to 820 nm taken over a semideciduous forest of the Brazilian Atlantic biome. We included in our network’s architecture a band combination selection phase. This phase learns from multiple combinations between bands which contributed the most for the tree identification task. This is followed by a feature map extraction and a multi-stage model refinement of the confidence map to produce accurate results of a highly-dense target. Our method returned an f-measure, precision and recall values of 0.959, 0.973, and 0.945, respectively. The results were superior when compared with a principal component analysis (PCA) approach. Compared to other learning methods, ours estimate a combination of hyperspectral bands that most contribute to the mentioned task within the network’s architecture. With this, the proposed method achieved state-of-the-art performance for detecting and geolocating individual tree-species in UAV-based hyperspectral images in a complex forest.

Highlights

The rapid development of lightweight sensors, associated with the market availability of unmanned aerial vehicles (UAV), has contributed to the development of techniques for fast and accurate acquisition of surface information [1]
In a previous study, we developed a convolutional neural networks (CNN) based method to deal with highly-dense vegetation [50]
In this paper we presented a novel deep learning method, based upon a CNN architecture, to deal with high dimensionality data of hyperspectral UAV-based images to detect single-tree species

Summary

Introduction

The rapid development of lightweight sensors, associated with the market availability of unmanned aerial vehicles (UAV), has contributed to the development of techniques for fast and accurate acquisition of surface information [1]. Feature extraction in hyperspectral data was performed with conventional and machine learning algorithms like the random forest (RF), decision trees (DT), support vector machine (SVM), artificial neural networks (ANN), k-nearest neighbor (kNN), among others [10,11,12,13]. The performance of these techniques has been evaluated in several studies and, for vegetation analysis, some achieved interesting results with a combination between them and remote sensing data [14,15,16]. These researches demonstrate the potential of artificial intelligence for dealing with this type of remote sensing data

Objectives

Methods

Findings

Conclusion