Fusing Multi-Seasonal Sentinel-2 Images with Residual Convolutional Neural Networks for Local Climate Zone-Derived Urban Land Cover Classification

Qiu, Chunping; Schmitt, Michael; Zhu, Xiao Xiang

doi:10.1109/igarss.2019.8898223

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from the dataset to train the network, in the prediction phase, multisource multitemporal data fusion is also a straightforward and effective approach to further improve the obtained benchmark LCZ classification results. The effectiveness of data fusion has been shown in [18], [65], and [21]. Specifically, a final robust result can be achieved via a decision-level fusion of multiple predictions that are obtained from multisource data, such as SAR and hyperspectral image, with same or different classifiers [66]- [70].…”

Section: Discussionmentioning

confidence: 99%

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Qiu

Tong

Schmitt

et al. 2020

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

Self Cite

View full text Add to dashboard Cite

As a unique classification scheme for urban forms and functions, the local climate zone (LCZ) system provides essential general information for any studies related to urban environments, especially on a large scale. Remote sensing data-based classification approaches are the key to large-scale mapping and monitoring of LCZs. The potential of deep learning-based approaches is not yet fully explored, even though advanced convolutional neural networks (CNNs) continue to push the frontiers for various computer vision tasks. One reason is that published studies are based on different datasets, usually at a regional scale, which makes it impossible to fairly and consistently compare the potential of different CNNs for real-world scenarios. This article is based on the big So2Sat LCZ42 benchmark dataset dedicated to LCZ classification. Using this dataset, we studied a range of CNNs of varying sizes. In addition, we proposed a CNN to classify LCZs from Sentinel-2 images, Sen2LCZ-Net. Using this base network, we propose fusing multilevel features using the extended Sen2LCZ-Net-MF. With this proposed simple network architecture, and the highly competitive benchmark dataset, we obtain results that are better than those obtained by the state-of-the-art CNNs, while requiring less computation with fewer layers and parameters. Large-scale LCZ classification examples of completely unseen areas are presented, demonstrating the potential of our proposed Sen2LCZ-Net-MF

show abstract

Section: Discussionmentioning

confidence: 99%

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Qiu

Tong

Schmitt

et al. 2020

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Apart from the dataset to train the network, in the prediction phase, multi-source multi-temporal data fusion is also a straightforward and effective approach to further improve the obtained benchmark LCZ classification results. The effectiveness of data fusion has been shown in [18], [65], and [21]. Specifically, a final robust result can be achieved via a decision-level fusion of multiple predictions that are obtained from multi-source data, such as SAR and hyperspectral image, with same or different classifiers [66], [67], [68], [69], [70].…”

Section: Discussionmentioning

confidence: 99%

“…The key to efficient large-scale LCZ classification is developing advanced machine learning models with high generalization ability [14], [15]. In this regard, tailoring deep learningbased approaches to the peculiarities of remote sensing data is one important strategy that has gained much attention recently [16], [17], [18], [19], [20], [21], [22]. A review of these published studies tells us that deep learning, specifically in the form of convolutional neural networks (CNNs), is indeed able to enhance LCZ classification accuracy given a proper dataset due to its powerful feature representation capacity, when compared to random forest approaches [23].…”

Section: Introductionmentioning

confidence: 99%

Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Qiu¹,

Tong²,

Schmitt³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This article was accepted by IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. As a unique classification scheme for urban forms and functions, the local climate zone (LCZ) system provides essential general information for any studies related to urban environments, especially on a large scale. Remote sensing databased classification approaches are the key to large-scale mapping and monitoring of LCZs. The potential of deep learning-based approaches is not yet fully explored, even though advanced convolutional neural networks (CNNs) continue to push the frontiers for various computer vision tasks. One reason is that published studies are based on different datasets, usually at a regional scale, which makes it impossible to fairly and consistently compare the potential of different CNNs for realworld scenarios. This study is based on the big So2Sat LCZ42 benchmark dataset dedicated to LCZ classification. Using this dataset, we studied a range of CNNs of varying sizes. In addition, we proposed a CNN to classify LCZs from Sentinel-2 images, Sen2LCZ-Net. Using this base network, we propose fusing multi-level features using the extended Sen2LCZ-Net-MF. With this proposed simple network architecture, and the highly competitive benchmark dataset, we obtain results that are better than those obtained by the state-of-the-art CNNs, while requiring less computation with fewer layers and parameters. Large-scale LCZ classification examples of completely unseen areas are presented, demonstrating the potential of our proposed Sen2LCZ-Net-MF as well as the So2Sat LCZ42 dataset. We also intensively investigated the influence of network depth and width, and the effectiveness of the design choices made for Sen2LCZ-Net-MF. Our work will provide important baselines for future CNN-based algorithm developments for both LCZ classification and other urban land cover land use classification. Code and pretrained models are available at https://github.com/ChunpingQiu/ benchmark-on-So2SatLCZ42-dataset-a-simple-tour.

show abstract

“…For the city of Cologne, these data are derived from satellite data (Sentinel 2-Data). Detailed information on the used framework to identify the LCZs can be found in Qui et al [39]. The LCZ-land use classes, originally introduced by Stewart and Oke [13] to analyze the impact of the built-up morphology on the climate of urban areas, describe the degree of built-up areas in a defined area.…”

Section: Datamentioning

confidence: 99%

A Method for Modeling Urban Water Infrastructures Combining Geo-Referenced Data

Lorenz

Friesen

Pouls

et al. 2021

Water

View full text Add to dashboard Cite

Water distribution networks are the backbone of any municipal water supply. Their task is to supply the population regardless of the respective demand. High resilience of these infrastructures is of great importance and has brought these infrastructures into the focus of science and politics. At the same time, the data collected is highly sensitive and often openly unavailable. Therefore, researchers have to rely on models that represent the topology of these infrastructures. In this work, a model is developed that allows the topology of an urban water infrastructure to be mapped using the example of Cologne, Germany by combining freely available data. On the one hand, spatial data on land use (local climate zones) are used to disaggregate the water demand within the city under consideration. On the other hand, the parallelism of water and urban transportation infrastructures is used to identify the topology of a network by applying optimization methods. These networks can be analyzed to identify vulnerable areas within urban structures.

show abstract

Fusing Multi-Seasonal Sentinel-2 Images with Residual Convolutional Neural Networks for Local Climate Zone-Derived Urban Land Cover Classification

Cited by 6 publications

References 11 publications

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

A Method for Modeling Urban Water Infrastructures Combining Geo-Referenced Data

Contact Info

Product

Resources

About