Convolutional neural networks for road surface classification on aerial imagery

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F24%3A00379823" target="_blank" >RIV/68407700:21110/24:00379823 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.7717/PEERJ-CS.2571" target="_blank" >https://doi.org/10.7717/PEERJ-CS.2571</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.7717/PEERJ-CS.2571" target="_blank" >10.7717/PEERJ-CS.2571</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Convolutional neural networks for road surface classification on aerial imagery

Popis výsledku v původním jazyce

Any place the human species inhabits is inevitably modified by them. One of the first features that appear everywhere, in urban areas as well as in the countryside or deep forests, are roads. Further, roads and streets in general reflect their omnipresent and significant role in our lives through the flow of goods, people, and even culture and information. However, their contribution to the public is highly influenced by their surface. Yet, research on automated road surface classification from remotely sensed data is peculiarly scarce. This work investigates the capacities of chosen convolutional neural networks (fully convolutional network (FCN), U-Net, SegNet, DeepLabv3+) on this task. We find that convolutional neural network (CNN) are capable of distinguishing between compact (asphalt, concrete) and modular (paving stones, tiles) surfaces for both roads and sidewalks on aerial data of spatial resolution of 10 cm. U-Net proved its position as the best-performing model among the tested ones, reaching an overall accuracy of nearly 92%. Furthermore, we explore the influence of adding a near-infrared band to the basic red green blue (RGB) scenes and stress where it should be used and where avoided. Overfitting strategies such as dropout and data augmentation undergo the same examination and clearly show their pros and cons. Convolutional neural networks are also compared to single-pixel based random forests and show indisputable advantage of the context awareness in convolutional neural networks, U-Net reaching almost 25% higher accuracy than random forests. We conclude that convolutional neural networks and U-Net in particular should be considered as suitable approaches for automated semantic segmentation of road surfaces on aerial imagery, while common overfitting strategies should only be used under particular conditions.

Název v anglickém jazyce

Convolutional neural networks for road surface classification on aerial imagery

Popis výsledku anglicky

Any place the human species inhabits is inevitably modified by them. One of the first features that appear everywhere, in urban areas as well as in the countryside or deep forests, are roads. Further, roads and streets in general reflect their omnipresent and significant role in our lives through the flow of goods, people, and even culture and information. However, their contribution to the public is highly influenced by their surface. Yet, research on automated road surface classification from remotely sensed data is peculiarly scarce. This work investigates the capacities of chosen convolutional neural networks (fully convolutional network (FCN), U-Net, SegNet, DeepLabv3+) on this task. We find that convolutional neural network (CNN) are capable of distinguishing between compact (asphalt, concrete) and modular (paving stones, tiles) surfaces for both roads and sidewalks on aerial data of spatial resolution of 10 cm. U-Net proved its position as the best-performing model among the tested ones, reaching an overall accuracy of nearly 92%. Furthermore, we explore the influence of adding a near-infrared band to the basic red green blue (RGB) scenes and stress where it should be used and where avoided. Overfitting strategies such as dropout and data augmentation undergo the same examination and clearly show their pros and cons. Convolutional neural networks are also compared to single-pixel based random forests and show indisputable advantage of the context awareness in convolutional neural networks, U-Net reaching almost 25% higher accuracy than random forests. We conclude that convolutional neural networks and U-Net in particular should be considered as suitable approaches for automated semantic segmentation of road surfaces on aerial imagery, while common overfitting strategies should only be used under particular conditions.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10500 - Earth and related environmental sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

PeerJ Computer Science

ISSN

2376-5992

e-ISSN

2376-5992

Svazek periodika

10

Číslo periodika v rámci svazku

12

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

26

Strana od-do

—

Kód UT WoS článku

001415620300005

EID výsledku v databázi Scopus

2-s2.0-85214492007