Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest

Yokoya, Naoto; Ghamisi, Pedram; Xia, Junshi; Sukhanov, Sergey; Heremans, Roel; Tankoyeu, Ivan; Bechtel, Benjamin; Saux, Bertrand Le; Moser, Gabriele; Tuia, Devis

doi:10.1109/jstars.2018.2799698

Cited by 123 publications

(95 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our challenge, on the other hand, uses images captured at one timestamp as the input, thus more flexible in real applications. Other previous land cover / land use semantic segmentation challenges as the ISPRS [3] or the IEEE GRSS data fusion contests [22,57] also used single shot ground truths and reported overall and average accuracy scores as evaluation metrics.…”

Section: Land Cover Classificationmentioning

confidence: 99%

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

Demir

Koperski

Lindenbaum

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

789

428

View full text Add to dashboard Cite

Figure 1: DeepGlobe Challenges: Example road extraction, building detection, and land cover classification training images superimposed on corresponding satellite images. AbstractWe present the DeepGlobe 2018 Satellite Image Understanding Challenge, which includes three public competitions for segmentation, detection, and classification tasks on satellite images ( Figure 1). Similar to other challenges in computer vision domain such as DAVIS[21] and COCO[33], DeepGlobe proposes three datasets and corresponding evaluation methodologies, coherently bundled in three competitions with a dedicated workshop co-located with CVPR 2018.We observed that satellite imagery is a rich and structured source of information, yet it is less investigated than everyday images by computer vision researchers. However, bridging modern computer vision with remote sensing data analysis could have critical impact to the way we understand our environment and lead to major breakthroughs in global urban planning or climate change research. Keeping such bridging objective in mind, DeepGlobe aims to bring together researchers from different domains to raise awareness of remote sensing in the computer vision community and vice-versa. We aim to improve and evaluate state-of-the-art satellite image understanding approaches, which can hopefully serve as reference benchmarks for future research in the same topic. In this paper, we analyze characteristics of each dataset, define the evaluation criteria of the competitions, and provide baselines for each task.

show abstract

Section: Land Cover Classificationmentioning

confidence: 99%

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

Demir

Koperski

Lindenbaum

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

789

428

View full text Add to dashboard Cite

show abstract

“…Following the introduction of LCZs, the World Urban Database and Portal (WUDAPT, http://www.wudapt.org) was initiated [3,4]. WUDAPT has been mainly developed by researchers to obtain high-quality land-cover/land-use information globally, usually via crowdsourcing [5,6], games [7], or other challenges [8]. The WUDAPT project presents a suggested workflow to produce the LCZ map by taking advantage of remote sensing techniques.…”

Section: Introductionmentioning

confidence: 99%

“…To cope with the aforementioned challenge of generalization, the 2017 Geoscience and Remote Sensing Society (GRSS) data fusion contest of the year 2017 proposed training the classifier on five cities (Berlin, Hong Kong, Paris, Rome, and Sao Paulo) and testing the results on four other cities (Amsterdam, Chicago, Madrid, and Xi'an). Although deep learning-based classification methods have proven to be strong in terms of classification accuracy a generalization capability in the remote sensing community [21][22][23][24], the ensemble-based canonical correlation forest (CCF) classification strategy achieved the best performance in the contest, among more than 800 submissions [8,25]. Therefore, this work uses the CCF classifier to pursue a solution for our task.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction and Selection of Sentinel-1 Dual-Pol Data for Global-Scale Local Climate Zone Classification

Ghamisi

Zhu

2018

IJGI

Self Cite

View full text Add to dashboard Cite

The concept of the local climate zone (LCZ) has been recently proposed as a generic land-cover/land-use classification scheme. It divides urban regions into 17 categories based on compositions of man-made structures and natural landscapes. Although it was originally designed for temperature study, the morphological structure concealed in LCZs also reflects economic status and population distribution. To this end, global LCZ classification is of great value for worldwide studies on economy and population. Conventional classification approaches are usually successful for an individual city using optical remote sensing data. This paper, however, attempts for the first time to produce global LCZ classification maps using polarimetric synthetic aperture radar (PolSAR) data. Specifically, we first produce polarimetric features, local statistical features, texture features, and morphological features and compare them, with respect to their classification performance. Here, an ensemble classifier is investigated, which is trained and tested on already separated transcontinental cities. Considering the challenging global scope this work handles, we conclude the classification accuracy is not yet satisfactory. However, Sentinel-1 dual-Pol SAR data could contribute the classification for several LCZ classes. According to our feature studies, the combination of local statistical features and morphological features yields the best classification results with 61.8% overall accuracy (OA), which is 3% higher than the OA produced by the second best features combination. The 3% is considerably large for a global scale. Based on our feature importance analysis, features related to VH polarized data contributed the most to the eventual classification result.

show abstract

“…First, the OA and kappa of the proposed framework were 76.15% and 0.72, which outperformed the baseline accuracy by 6.01% and 7%, respectively. Furthermore, the OA and kappa of the proposed framework still outperformed the winner of the 2017 IEEE GRSS Data Fusion Contest [17], [31], [37] by 1.21% and 1%, respectively, although fewer classifiers were used in this paper.…”

Section: A Baseline Framework and Feature Importancementioning

confidence: 85%

“…A CCF is an advanced forest classifier that naturally incorporates both the labels and the correlation between the input features in the choice of projection for computing decision boundaries in the projected feature space. Results demonstrate that the CCF has much better performance than other forest classifiers, such as the RF [23] and rotation forest (RoF) [36], when the training and test samples are not from the same domain [37]. Besides CCFs, three more works have managed to approach the intercity transferability problem by developing a co-training process [32], ensembling various classifiers [33], and conducting object-based classification [34] approaches.…”

Section: Global Mappingmentioning

confidence: 99%

Fusion of Heterogeneous Earth Observation Data for the Classification of Local Climate Zones

Ghamisi

Zhu

2019

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

This is a preprint. To read the final version please visit IEEE XPlore.This paper proposes a novel framework for fusing multitemporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly-used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM data, which becomes its main drawback. The proposed framework processes two data sources separately and then combines them at the model level through two fusion models (the landuse fusion model and building fusion model), which aim to fuse optical images with landuse and buildings layers of OSM data, respectively. In addition, a new approach to detecting building incompleteness of OSM data is proposed. The proposed framework was trained and tested using data from the 2017 IEEE GRSS Data Fusion Contest, and further validated on one additional test set containing test samples which are manually labeled in Munich and New York. Experimental results have indicated that compared to the feature stacking-based baseline framework the proposed framework is effective in fusing optical images with OSM data for the classification of LCZs with high generalization capability on a large scale. The classification accuracy of the proposed framework outperforms the baseline framework by more than 6% and 2%, while testing on the test set of 2017 IEEE GRSS Data Fusion Contest and the additional test set, respectively. In addition, the proposed framework is less sensitive to spectral diversities of optical satellite images and thus achieves more stable classification performance than state-of-theart frameworks.

show abstract

Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest

Cited by 123 publications

References 57 publications

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

Feature Extraction and Selection of Sentinel-1 Dual-Pol Data for Global-Scale Local Climate Zone Classification

Fusion of Heterogeneous Earth Observation Data for the Classification of Local Climate Zones

Contact Info

Product

Resources

About