Differentiation of River Sediments Fractions in UAV Aerial Images by Convolution Neural Network

Hitoshi Takechi,Mitsuteru Irie,Shunsuke Aragaki

doi:10.3390/rs13163188

Abstract

Riverbed material has multiple functions in river ecosystems, such as habitats, feeding grounds, spawning grounds, and shelters for aquatic organisms, and particle size of riverbed material reflects the tractive force of the channel flow. Therefore, regular surveys of riverbed material are conducted for environmental protection and river flood control projects. The field method is the most conventional riverbed material survey. However, conventional surveys of particle size of riverbed material require much labor, time, and cost to collect material on site. Furthermore, its spatial representativeness is also a problem because of the limited survey area against a wide riverbank. As a further solution to these problems, in this study, we tried an automatic classification of riverbed conditions using aerial photography with an unmanned aerial vehicle (UAV) and image recognition with artificial intelligence (AI) to improve survey efficiency. Due to using AI for image processing, a large number of images can be handled regardless of whether they are of fine or coarse particles. We tried a classification of aerial riverbed images that have the difference of particle size characteristics with a convolutional neural network (CNN). GoogLeNet, Alexnet, VGG-16 and ResNet, the common pre-trained networks, were retrained to perform the new task with the 70 riverbed images using transfer learning. Among the networks tested, GoogleNet showed the best performance for this study. The overall accuracy of the image classification reached 95.4%. On the other hand, it was supposed that shadows of the gravels caused the error of the classification. The network retrained with the images taken in the uniform temporal period gives higher accuracy for classifying the images taken in the same period as the training data. The results suggest the potential of evaluating riverbed materials using aerial photography with UAV and image recognition with CNN.

Highlights

The sand, gravel, and rock that make up riverbed material have multiple functions as habitats, feeding grounds, spawning grounds, and shelters for aquatic creatures [1,2].Besides, the particle size of the riverbed material reflects the tractive force of the channel flow
The purpose of the present paper is to develop an evaluation method for the spatial distribution of riverbed materials in a wide area that requires a lot of classification processes of images with a shorter time
The method that we propose can be structured according to the following steps: aerial photography using unmanned aerial vehicle (UAV), sieving, image preprocessing, BASEGRAIN analysis, and image classification by convolutional neural network (CNN)

Summary

Introduction

The sand, gravel, and rock that make up riverbed material have multiple functions as habitats, feeding grounds, spawning grounds, and shelters for aquatic creatures [1,2]. The particle size of the riverbed material reflects the tractive force of the channel flow. We can better understand the spatial distribution of flow velocity [3,4]. The spatial distribution of particle size of riverbed material is very important information for flood control and environmental protection in river management. Accurate information on the topography of the riverbed and its material as well as rainfall and discharge, is necessary. The most general conventional sampling of surveying riverbed material is by field methods, such as grid-by-number or volumetric methods [5,6]. Field methods require huge labor, time, and cost because samples are collected on-site and measured or sieved

Objectives

Methods

Results

Discussion

Conclusion