Understanding urban landuse from the above and ground perspectives: A deep learning, multimodal solution

Srivastava, Shivangi; Muñoz, John Ever; Tuia, Devis

doi:10.1016/j.rse.2019.04.014

Cited by 128 publications

(99 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the use of several sources of data (multimodal approaches) have proven to be beneficial for solving several problems it has been only applied in relatively few works described in this manuscript, such as in [19]. We believe that the performance of supervised methods used to improve OSM data can be greatly improved with the use of several data sources, such as images, tracking data, and social media data.…”

Section: Applications With Multimodal Datamentioning

confidence: 98%

OpenStreetMap: Challenges and Opportunities in Machine Learning and Remote Sensing

Muñoz

Srivastava

Tuia

et al. 2021

IEEE Geosci. Remote Sens. Mag.

Self Cite

106

View full text Add to dashboard Cite

OpenStreetMap (OSM) is a community-based, freely available, editable map service that was created as an alternative to authoritative ones. Given that it is edited mainly by volunteers with different mapping skills, the completeness and quality of its annotations are heterogeneous across different geographical locations. Despite that, OSM has been widely used in several applications in Geosciences, Earth Observation and environmental sciences. In this work, we present a review of recent methods based on machine learning to improve and use OSM data. Such methods aim either 1) at improving the coverage and quality of OSM layers, typically using GIS and remote sensing technologies, or 2) at using the existing OSM layers to train models based on image data to serve applications like navigation or land use classification. We believe that OSM (as well as other sources of open land maps) can change the way we interpret remote sensing data and that the synergy with machine learning can scale participatory map making and its quality to the level needed to serve global and up-to-date land mapping. A preliminary version of this manuscript has been presented in the first authors dissertation [1].

show abstract

Section: Applications With Multimodal Datamentioning

confidence: 98%

OpenStreetMap: Challenges and Opportunities in Machine Learning and Remote Sensing

Muñoz

Srivastava

Tuia

et al. 2021

IEEE Geosci. Remote Sens. Mag.

Self Cite

106

View full text Add to dashboard Cite

show abstract

“…Relating to the Buildings [5] andÎle-de-France land use [4] datasets, both were designed for multi-view scene classification. The first dataset contains 56, 259 paired aerial/street-level images of 4 different types of buildings, covering Washington DC.…”

Section: Related Workmentioning

confidence: 99%

“…• House: a single-family residence. 4 www.openstreetmap.org/ 5 https://overpass-turbo.eu/ 6 https://developers.google.com/maps/documentation/maps-static/intro 7 https://developers.google.com/maps/documentation/streetview/intro Figure 4, whereas the class distribution is presented in Figure 3. Regarding the images, all of them are 500×500 RGB images.…”

Section: B Cv-brctmentioning

confidence: 99%

“…In multi-view scenarios, it would be crucial to combine the complementary information of aerial and ground images in order to efficiently tackle a problem. Such combination of multiple sources images can benefit many applications in different fields, like 3D human pose estimation [2], places geo-localization [3], and urban land use [4]. Motivated by these benefits, several approaches [5], [6], [7], [8], [9] have been proposed to exploit multi-view datasets to face distinct tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AiRound and CV-BrCT: Novel Multiview Datasets for Scene Classification

Machado

Ferreira

Nogueira

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

It is undeniable that aerial/satellite images can provide useful information for a large variety of tasks. But, since these images are always looking from above, some applications can benefit from complementary information provided by other perspective views of the scene, such as ground-level images. Despite a large number of public repositories for both georeferenced photographs and aerial images, there is a lack of benchmark datasets that allow the development of approaches that exploit the benefits and complementarity of aerial/ground imagery. In this paper, we present two new publicly available datasets named AiRound and CV-BrCT. The first one contains triplets of images from the same geographic coordinate with different perspectives of view extracted from various places around the world. Each triplet is composed of an aerial RGB image, a ground-level perspective image, and a Sentinel-2 sample. The second dataset contains pairs of aerial and street-level images extracted from southeast Brazil. We design an extensive set of experiments concerning multi-view scene classification, using early and late fusion. Such experiments were conducted to show that image classification can be enhanced using multi-view data.

show abstract

“…This is again a semantic segmentation task. Finding borders between landuse classes is not trivial, which explains why researchers often complement their discriminative workflow with ground-based images (Srivastava et al, 2019).…”

Section: Fostering Applicationsmentioning

confidence: 99%

Current Challenges in Operational Very High Resolution Land-Cover Mapping

Mallet

Bris

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Many land-cover products have been made available for a large range of end-users over the last ten years, even at global scales. In particular, remote sensing data analysis has proved to be the most feasible solution for automation purposes, at multiple spatial scales. However, current solutions are not sufficient for designing better products, adapted to real-case applications, operational constraints, and the generation of services, built upon these core layers. In this paper, we review the main requirements and the recent changes in remote sensing for the specific case of very high resolution land-cover mapping. We also comment current and evaluate challenges for the optimal exploitation of Earth Observation images with the aim of automatically generating maps tailored to specific end-users’ needs. We advocate for more challenging large-scale benchmarks and for human-in-the-loop solutions.

show abstract

Understanding urban landuse from the above and ground perspectives: A deep learning, multimodal solution

Cited by 128 publications

References 49 publications

OpenStreetMap: Challenges and Opportunities in Machine Learning and Remote Sensing

OpenStreetMap: Challenges and Opportunities in Machine Learning and Remote Sensing

AiRound and CV-BrCT: Novel Multiview Datasets for Scene Classification

Current Challenges in Operational Very High Resolution Land-Cover Mapping

Contact Info

Product

Resources

About