Spatio-Temporal Vegetation Pixel Classification by Using Convolutional Networks

Nogueira, Keiller; Santos, Jefersson A. dos; Menini, Nathalia; Silva, Thiago Sanna Freire; Morellato, Leonor Patrícia Cerdeira; Torres, Ricardo da S.

doi:10.1109/lgrs.2019.2903194

Cited by 14 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this PhD thesis, we proposed solutions that address important challenges related to the exploitation of deep learning into the remote sensing domain, including data availability, context exploitation, and so on. It was completed in approximately four years (from March 2015 to May 2019) and has resulted in four international journal papers [5], [8], [23], [25], and eleven international conference papers [3], [6], [7], [22], [24], [27]- [32].…”

Section: Discussionmentioning

confidence: 99%

“…Based on this argument, new technologies have been proposed toward acquiring aerial images with improved quality, resulting in more advanced satellites launched to observe the Earth, as well as, more recently, in drones and unmanned aerial vehicles. These top-notch Remote Sensing Images (RSIs) may provide useful information that could be employed in several Earth Observation applications, including urban planning [1], crop and forest management [2], [3], disaster relief [4], [5], phenological studies [6]- [8], etc.…”

Section: Introductionmentioning

confidence: 99%

“…With such concept, new morphological layers and networks were created and optimized for RSI classification. Besides those contributions, many others related to this PhD work were published in [3], [5]- [8], [27]- [30], [32]. The following sections detail each of the contributions obtained from the developed research.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Going Deep into Remote Sensing Spatial Feature Learning

Nogueira¹

2020

Anais Estendidos Da Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2020)

Self Cite

View full text Add to dashboard Cite

A lot of information may be extracted from the Earth’s surface through aerial images. This information may assist in myriad applications, such as urban planning, crop and forest management, disaster relief, etc. However, the process of distilling this information is strongly based on efficiently encoding the spatial features, a challenging task. Facing this, Deep Learning is able to learn specific data-driven features. This PhD thesis1 introduces deep learning into the remote sensing domain. Specifically, we tackled two main tasks, scene and pixel classification, using Deep Learning to encode spatial features over high-resolution remote sensing images. First, we proposed an architecture and analyze different strategies to exploit Convolutional Networks for image classification. Second, we introduced a network and proposed a new strategy to better exploit multi-context information in order to improve pixelwise classification. Finally, we proposed a new network based on morphological operations towards better learning of some relevant visual features.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Going Deep into Remote Sensing Spatial Feature Learning

Nogueira¹

2020

Anais Estendidos Da Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2020)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Mauro et al [30] used a multi-layer perceptron (MLP) and a CNN to classify land cover from multi-temporal Landsat images. Nogueira et al [31] implemented a multi-branch CNN for vegetation mapping and confirmed its superiority to a traditional CNN operating on a temporal stack of images. Pelletier et al [28] proposed a temporal CNN for crop classification where convolutions are applied in the temporal domain.…”

Section: Introductionmentioning

confidence: 92%

Towards a Multi-Temporal Deep Learning Approach for Mapping Urban Fabric Using Sentinel 2 Images

Mendili¹,

Puissant

Chougrad³

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The major part of the population lives in urban areas, and this is expected to increase in the future. The main challenges faced by cities currently and towards the future are the rapid urbanization, the increase in urban temperature and the urban heat island. Mapping and monitoring urban fabric (UF) to analyze the environmental impact of these phenomena is more necessary than ever. This coupled with the increased availability of Earth observation data and their growing temporal capabilities leads us to consider using temporal features for improving land use classification, especially in urban environments where the spectral overlap between classes makes it challenging. Urban land use classification thus remains a central question in remote sensing. Although some research studies have successfully used multi-temporal images such as Landsat-8 or Sentinel-2 to improve land cover classification, urban land use mapping is rarely carried using the temporal dimension. This paper explores the use of Sentinel-2 data in a deep learning framework, by firstly assessing the temporal robustness of four popular fully convolutional neural networks (FCNs) trained over single-date images for the classification of the urban footprint, and secondly, by proposing a multi-temporal FCN. A performance comparison between the proposed framework and a regular FCN is also conducted. In this study, we consider four UF classes typical of many European Western cities. Results show that training the proposed multi-date model on Sentinel 2 multi-temporal data achieved the best results with a Kappa coefficient increase of 2.72% and 6.40%, respectively for continuous UF and industrial facilities. Although a more definitive conclusion requires further testing, first results are promising because they confirm that integrating the temporal dimension with a high spatial resolution into urban land use classification may be a valuable strategy to discriminate among several urban categories.

show abstract

“…This section aims to explain all deep learning methods that were evaluated in this work for erosion identification. Such semantic segmentation approaches were selected based on their popularity and performance for different applications and images, including computer vision [8][9][10][11][12][13], remote sensing [5,7,[26][27][28][29][30], medical [31][32][33][34][35], and so on. However, although their success in different domains, as aforementioned, those methods were never evaluated in the erosion identification task.…”

Section: Introductionmentioning

confidence: 99%

Facing Erosion Identification in Railway Lines Using Pixel-Wise Deep-Based Approaches

et al. 2020

Self Cite

View full text Add to dashboard Cite

Soil erosion is considered one of the most expensive natural hazards with a high impact on several infrastructure assets. Among them, railway lines are one of the most likely constructions for the appearance of erosion and, consequently, one of the most troublesome due to the maintenance costs, risks of derailments, and so on. Therefore, it is fundamental to identify and monitor erosion in railway lines to prevent major consequences. Currently, erosion identification is manually performed by humans using huge image sets, a time-consuming and slow task. Hence, automatic machine learning methods appear as an appealing alternative. A crucial step for automatic erosion identification is to create a good feature representation. Towards such objective, deep learning can learn data-driven features and classifiers. In this paper, we propose a novel deep learning-based framework capable of performing erosion identification in railway lines. Six techniques were evaluated and the best one, Dynamic Dilated ConvNet, was integrated into this framework that was then encapsulated into a new ArcGIS plugin to facilitate its use by non-programmer users. To analyze such techniques, we also propose a new dataset, composed of almost 2000 high-resolution images.

show abstract

Spatio-Temporal Vegetation Pixel Classification by Using Convolutional Networks

Cited by 14 publications

References 13 publications

Going Deep into Remote Sensing Spatial Feature Learning

Going Deep into Remote Sensing Spatial Feature Learning

Towards a Multi-Temporal Deep Learning Approach for Mapping Urban Fabric Using Sentinel 2 Images

Facing Erosion Identification in Railway Lines Using Pixel-Wise Deep-Based Approaches

Contact Info

Product

Resources

About