Deep learning approaches for delineating wetlands on historical topographic maps

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13520%2F24%3A43898937" target="_blank" >RIV/44555601:13520/24:43898937 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21110/24:00376357

Výsledek na webu

<a href="https://onlinelibrary.wiley.com/doi/10.1111/tgis.13193?af=R" target="_blank" >https://onlinelibrary.wiley.com/doi/10.1111/tgis.13193?af=R</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1111/tgis.13193" target="_blank" >10.1111/tgis.13193</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep learning approaches for delineating wetlands on historical topographic maps

Popis výsledku v původním jazyce

Historical topographic maps are an important source of a visual record of the landscape, showing geographical elements such as terrain, elevation, rivers and water bodies, roads, buildings, and land use and land cover (LULC). Historical maps are scanned to their digital representation, a raster image. To quantify different classes of LULC, it is necessary to transform scanned maps to their vector equivalent. Traditionally, this has been done either manually, or by using (semi)automatic methods of clustering/segmentation. With the advent of deep neural networks, new horizons opened for more effective and accurate processing. This article attempts to use different deep-learning approaches to detect and segment wetlands on historical Topographic Maps 1: 10000 (TM10), created during the 50s and 60s. Due to the specific symbology of wetlands, their processing can be challenging. It deals with two distinct approaches in the deep learning world, semantic segmentation and object detection, represented by the U-Net and Single-Shot Detector (SSD) neural networks, respectively. The suitability, speed, and accuracy of the two approaches in neural networks are analyzed. The results aresatisfactory, with the U-Net F1 score reaching 75.7% and the SSD object detection approach presenting an unconventional alternative

Název v anglickém jazyce

Deep learning approaches for delineating wetlands on historical topographic maps

Popis výsledku anglicky

Historical topographic maps are an important source of a visual record of the landscape, showing geographical elements such as terrain, elevation, rivers and water bodies, roads, buildings, and land use and land cover (LULC). Historical maps are scanned to their digital representation, a raster image. To quantify different classes of LULC, it is necessary to transform scanned maps to their vector equivalent. Traditionally, this has been done either manually, or by using (semi)automatic methods of clustering/segmentation. With the advent of deep neural networks, new horizons opened for more effective and accurate processing. This article attempts to use different deep-learning approaches to detect and segment wetlands on historical Topographic Maps 1: 10000 (TM10), created during the 50s and 60s. Due to the specific symbology of wetlands, their processing can be challenging. It deals with two distinct approaches in the deep learning world, semantic segmentation and object detection, represented by the U-Net and Single-Shot Detector (SSD) neural networks, respectively. The suitability, speed, and accuracy of the two approaches in neural networks are analyzed. The results aresatisfactory, with the U-Net F1 score reaching 75.7% and the SSD object detection approach presenting an unconventional alternative

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20705 - Remote sensing

Projekt

<a href="/cs/project/SS05010090" target="_blank" >SS05010090: Voda v krajině Českého Švýcarska</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Transaction in GIS

ISSN

1361-1682

e-ISSN

1467-9671

Svazek periodika

2024

Číslo periodika v rámci svazku

28

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

1400-1411

Kód UT WoS článku

001240738200001

EID výsledku v databázi Scopus

2-s2.0-85195455583