Maintaining accurate, current, rural road network data: An extraction and updating routine using RapidEye, participatory GIS and deep learning

Kearney, Sean P.; Coops, Nicholas C.; Sethi, Simran; Stenhouse, Gordon B.

doi:10.1016/j.jag.2019.102031

Cited by 32 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed technique yields a total F1-score of 0.704, a 1.1% improvement to 12.5%. Kearney et al [32] utilized RapidEye, participative GIS, and DL to extract and update the unpaved roads.…”

Section: Traffic and Route Planningmentioning

confidence: 99%

A Brief Review of Recent Developments in the Integration of Deep Learning with GIS

Mohan

M.V.S.S

2022

GaEE

View full text Add to dashboard Cite

The interaction of Deep Learning (DL) methods with Geographical Information System (GIS) provides the opportunity to obtain new insights into environmental processes through the spatial, temporal and spectral resolutions as well as data integration. The two technologies may be connected to form a dynamic system that is incredibly well adapted to the evaluation of environmental conditions through the interrelationships of texture, size, pattern, and process. This perspective has acquired popularity in multiple disciplines. GIS is significantly dependant on processors, particularly for 3D calculations, map rendering, and route calculation whereas DL can process huge amounts of data. DL has received a lot of attention recently as a technology with a plethora of promising results. Furthermore, the growing use of DL methods in a variety of disciplines, including GIS, is evident. This study tries to provide a brief overview of the use of DL methods in GIS. This paper introduces the essential DL concepts relevant to GIS, the majority of which have been published in recent years. This research explores remote sensing applications and technologies in areas such as mapping, hydrological modelling, disaster management, and transportation route planning. Finally, conclusions on contemporary framework methodologies and suggestions for further studies are provided.

show abstract

Section: Traffic and Route Planningmentioning

confidence: 99%

A Brief Review of Recent Developments in the Integration of Deep Learning with GIS

Mohan

M.V.S.S

2022

GaEE

View full text Add to dashboard Cite

show abstract

“…This may be one reason why the methods of road detection that are used in urban areas are not applied in rural areas, and vice versa, or for identification of non-paved roads. Together with the fact that most of the methods developed are used in urban areas, this results in a net deficit of methods than can be used to address the needs of rural areas [12]. In addition, despite the obvious impact of aforementioned challenges on the quality of the extracted roads, studies explicitly analyzing this aspect are scarce [3].…”

Section: Brief Review Of the State-of-artmentioning

confidence: 99%

“…Although these techniques are the most accurate and robust, they are also time-consuming and costly [14]. This group also includes participatory GIS; in a recent great study, a mobile application, RoadLab Pro, was used to automatically map the driving location of six different drivers [12]. The data were collected by taking advantage of the car/truck journeys by users working for organizations operating in the study area.…”

Section: Brief Review Of the State-of-artmentioning

confidence: 99%

“…In this particular case, the data collection was limited to areas transited by vehicles, and narrow roads or abandoned logging roads were excluded. Assuming no technical limitations for users travelling on foot, this is an easy method of collecting data, although less accurate than traditional methods and possibly more expensive than in the case reported [12]. Data collected using manual techniques are usually used to train semi-automatic and automatic methods and assess the accuracy of the detection.…”

Section: Brief Review Of the State-of-artmentioning

confidence: 99%

See 1 more Smart Citation

Forest Road Detection Using LiDAR Data and Hybrid Classification

et al. 2021

View full text Add to dashboard Cite

Knowledge about forest road networks is essential for sustainable forest management and fire management. The aim of this study was to assess the accuracy of a new hierarchical-hybrid classification tool (HyClass) for mapping paved and unpaved forest roads with LiDAR data. Bare-earth and low-lying vegetation were also identified. For this purpose, a rural landscape (area 70 ha) in northwestern Spain was selected for study, and a road network map was extracted from the cadastral maps as the ground truth data. The HyClass tool is based on a decision tree which integrates segmentation processes at local scale with decision rules. The proposed approach yielded an overall accuracy (OA) of 96.5%, with a confidence interval (CI) of 94.0–97.6%, representing an improvement over pixel-based classification (OA = 87.0%, CI = 83.7–89.8%) using Random Forest (RF). In addition, with the HyClass tool, the classification precision varied significantly after reducing the original point density from 8.7 to 1 point/m2. The proposed method can provide accurate road mapping to support forest management as an alternative to pixel-based RF classification when the LiDAR point density is higher than 1 point/m2.

show abstract

“…Remote sensing allows us to efficiently monitor the physical properties of the environment using multi‐temporal data acquisitions of large areas (Imran et al 2020). The use of relevant information derived from these observations has become a common approach across a wide range of disciplines, including agriculture (Luis Soca‐Munoz et al 2020) or feature extraction (Kearney et al 2020). At the interface between geography and ecology, remotely sensing ecosystem properties have great potential to contribute to land cover and biodiversity monitoring and research (O'Connor et al 2015, Pettorelli et al 2016, Vihervaara et al 2017, Jetz et al 2019).…”

Section: Introductionmentioning

confidence: 99%

RSDB: an easy to deploy open‐source web platform for remote sensing raster and point cloud data management, exploration and processing

et al. 2020

View full text Add to dashboard Cite

Monitoring biodiversity and its change over space and time is a key challenge for ecological research. Utilizing remote sensing data in ecological research has been shown to be a powerful complement to labor‐intensive field work to derive area‐wide biodiversity indices, which can also capture larger spatiotemporal areas. However, preprocessing different types of remote sensing data for specific studies often requires extensive computational skills as the algorithms for creating final data products are scattered across the literature. Our remote sensing database (RSDB, ) serves as an integrative storage, management and processing solution for several types of remote sensing data. Transparent data processing capabilities for more than 200 biodiversity‐related indices are included and can be used to calculate ready‐to‐use data products for a variety of ecological studies. These data products, for example, leaf area, vertical distribution of biomass and foliage height derived from light detection and ranging (LiDAR) point clouds, are individually calculated for user‐specified study areas and can serve as proxies for ecological variables, such as the availability of resources or habitat heterogeneity. The primary RSDB user interface is web browser based on management, exploration, visualization and product processing capabilities. The RSDB stores data in layers that are discoverable by textual metadata and mapping on overview maps. Individual data layers can be explored using interactive maps and 3‐D visualizations. We additionally provide a seamless connection of the RSDB's functionality with the R environment through our accompanying R package for scripting and advanced processing tasks. We designed the RSDB to be an easily accessible solution for on‐demand processing of comprehensive biodiversity indices. To date, the RSDB has been used and tested in several studies, and we are convinced that it will continue to facilitate biodiversity monitoring via its application to ecological research.

show abstract

Maintaining accurate, current, rural road network data: An extraction and updating routine using RapidEye, participatory GIS and deep learning

Cited by 32 publications

References 14 publications

A Brief Review of Recent Developments in the Integration of Deep Learning with GIS

A Brief Review of Recent Developments in the Integration of Deep Learning with GIS

Forest Road Detection Using LiDAR Data and Hybrid Classification

RSDB: an easy to deploy open‐source web platform for remote sensing raster and point cloud data management, exploration and processing

Contact Info

Product

Resources

About