OpenStreetMap: Challenges and Opportunities in Machine Learning and Remote Sensing

Muñoz, John Ever; Srivastava, Shivangi; Tuia, Devis; Falcão, Alexandre X.

doi:10.1109/mgrs.2020.2994107

Cited by 94 publications

(47 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to humanitarian institutions, major commercial enterprises, such as Facebook, Kaart, Grab and Apple, have increasingly been taking a prominent role in OSM (see Anderson et al, 2019;Cinnamon, 2015;Morrison, 2020). In many cases on the initiative and with the support of institutional actors, new semi-automated mapping practices based on machine learning are also being introduced (Vargas Mun ˜oz et al, 2020).…”

Section: Discussion: Geographic Shifts and Socioinstitutional Changes In Osmmentioning

confidence: 99%

De/colonizing OpenStreetMap? Local mappers, humanitarian and commercial actors and the changing modes of collaborative mapping

et al. 2021

View full text Add to dashboard Cite

In its early days, the geodata and mapping project OpenStreetMap (OSM) was widely celebrated for opening up and “democratizing” the production of geographic knowledge. However, critical research highlights that the new socio-technical practices of collaborative mapping often also produce or reproduce patterns of exclusion, not least in the area of relative data density between the Global South and North. These findings notwithstanding, we consider it important to acknowledge the increasing number of contributions of geodata from regions outside the old European core of OSM. This expansion of geodata production in OSM is related to a diversification of OSM actors and socio-technical practices. While OSM has often been described as a crowd-based project bringing together thousands of individual craft mappers, our analysis of OSM metadata indicates new institutional actors are gaining relevance. These developments have not only resulted in new collaborations but also conflicts between local mapping communities and institutional actors. We interpret these processes in two ways. First, the expansion of mapping activities can be viewed as a decolonizing process, whereby quantitative differences in data density between the Global North and South are partly reduced and new groups of local mappers are empowered to produce geographic knowledge. Second, these new developments can also be understood as colonizing processes. The engagement of large commercial actors in OSM raises concerns that the project (and its local mappers) could be used as a new means of data extraction and that in particular new and diverse voices in the OSM community are marginalized by a fixation on economically exploitable, modernistic and universalistic epistemologies. However, this supposedly clear distinction should not obscure the fact that colonizing and decolonizing processes intertwine in complex ways.

show abstract

Section: Discussion: Geographic Shifts and Socioinstitutional Changes In Osmmentioning

confidence: 99%

De/colonizing OpenStreetMap? Local mappers, humanitarian and commercial actors and the changing modes of collaborative mapping

et al. 2021

View full text Add to dashboard Cite

show abstract

“…OpenStreetMap (OSM) [49] is a crowdsourced spatial database that can provide a detailed representation of land use and land cover (LULC). Although its completeness and correctness may vary across regions, it has been used in studies for collecting reference data for land cover mapping [50,51]. Furthermore, the fine scale offered by OSM, representing objects up to mid-sized buildings in cities, has allowed for studies to use OSM information as reference data for mapping road networks [52], as well as urban open spaces [11,12,53,54].…”

Section: Ancillary Data and Preprocessingmentioning

confidence: 99%

A Cloud-Based Mapping Approach Using Deep Learning and Very-High Spatial Resolution Earth Observation Data to Facilitate the SDG 11.7.1 Indicator Computation

2022

View full text Add to dashboard Cite

As urbanized areas continue to expand rapidly across all continents, the United Nations adopted in 2015 the Sustainable Development Goal (SDG) 11, aimed at shaping a sustainable future for city dwellers. Earth Observation (EO) satellite data can provide at a fine scale, essential urban land use information for computing SDG 11 indicators in order to complement or even replace inaccurate or invalid existing spatial datasets. This study proposes an EO-based approach for extracting large scale information regarding urban open spaces (UOS) and land allocated to streets (LAS) at the city level, for calculating SDG indicator 11.7.1. The research workflow was developed over the Athens metropolitan area in Greece using deep learning classification models for processing PlanetScope and Sentinel-1 imagery, employing freely-available cloud environments offered by Google. The LAS model exhibited satisfactory results while the best experiment performance for mapping UOS, considering both PlanetScope and Sentinel-1 data, yielded high commission errors, however, the cross-validation analysis with the UOS area of OpenStreetMap exhibited a total overlap of 67.38%, suggesting that our workflow is suitable for creating a “potential” UOS layer. The methodology developed herein can serve as a roadmap for the calculation of indicator 11.7.1 through national statistical offices when spatial data are absent or unreliable.

show abstract

“…ML is playing an increasingly important role in the automatic capture of spatial data-particularly in the context of citizen science projects. For example, Varas-Munoz et al [48] demonstrate the benefit of using convoluted neural networks (CNN) to support what is currently a human centered approach to creating content for OpenStreetMap. They review CNN techniques that have been used to automatically extract roads from imagery, and to identify geometric and semantic errors in the data entry process.…”

Section: Object Extraction From Imagery Using Machine Learning (Ml)mentioning

confidence: 99%

Applying the FFP Approach to Wider Land Management Functions

Kelm

Antos

McLaren³

2021

Land

View full text Add to dashboard Cite

The initial focus of implementing the Fit-for-Purpose Land Administration (FFPLA) methodology was to address the significant, global security of tenure divide. We argue that this land tenure methodology is proving successful in scaling up the provision of security of tenure for developing countries. The increasing adoption of the FFPLA methodology has also opened opportunities and provided flexibility for the innovative use of emerging technologies to accelerate the global roll out of security of tenure, such as the use of autonomous drones and machine learning techniques applied to image analysis. Despite wider adoption of participatory approaches to the recording of land tenure, similar FFP solutions for the other components of land administration services (land value, land use and land development) and land management functions are still evolving. This article therefore explores how the FFP approach can be applied to this wider set of land administration services and land management functions. A case study methodology, using three case studies, is used to determine if the case study approaches meet the FFP criteria. The focus is on the urban environment, drawing mostly from experiences and case studies in the Urban, Disaster Risk Management, Resilience & Land Global Practice of the World Bank. These opportunities for the wider application of the FFP approach and associated principles are being triggered by the innovative use of emerging new data capture technology developments. The paper examines the innovative use of these emerging technologies to identify a common set of data capture techniques and geospatial data that can be shared across a range of urban land administration and management activities. Finally, the paper discusses how individual land projects could be integrated into a more holistic land administration and management program approach and deliver a significant set of socio-economic benefits more quickly. It is found that the FFP approach can be more widely adopted across land administration and land management and in many cases can share a common set of geospatial data. The authors argue that the wider adoption and integration of these new, innovative FFP urban management approaches will require a significant cultural, professional, and institutional change from all stakeholders. Future work will explore more deeply these institutional weaknesses, which will provide a basis for guidance to the World Bank and similar institutions.

show abstract

OpenStreetMap: Challenges and Opportunities in Machine Learning and Remote Sensing

Cited by 94 publications

References 95 publications

De/colonizing OpenStreetMap? Local mappers, humanitarian and commercial actors and the changing modes of collaborative mapping

De/colonizing OpenStreetMap? Local mappers, humanitarian and commercial actors and the changing modes of collaborative mapping

A Cloud-Based Mapping Approach Using Deep Learning and Very-High Spatial Resolution Earth Observation Data to Facilitate the SDG 11.7.1 Indicator Computation

Applying the FFP Approach to Wider Land Management Functions

Contact Info

Product

Resources

About