Benchmarking classification of earth-observation data: From learning explicit features to convolutional networks

Lagrange, Adrien; Saux, Bertrand Le; Beaupere, Anne; Boulch, Alexandre; Chan-Hon-Tong, Adrien; Herbin, Stéphane; Randrianarivo, Hicham; Ferecatu, Marin

doi:10.1109/igarss.2015.7326745

Cited by 77 publications

(68 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The filters learned by the first layer of the network will, therefore, depend on a stack of different sources. Studies considering this straightforward extension of neural networks are numerous and, in [126], authors compared networks trained on color RGB data (fine tuned from existing architectures) with networks, including a DSM channel on the 2015 Data Fusion Contest dataset over the city of Zeebruges [127] 2 . They use the CNN as a feature extractor and then use the features to train a SVM, predicting a single semantic class for the entire patch.…”

Section: Multimodal Data Fusionmentioning

confidence: 99%

Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

Zhu

Tuia

Mou

et al. 2017

IEEE Geosci. Remote Sens. Mag.

2,442

1,204

View full text Add to dashboard Cite

This is the pre-acceptance version, to read the final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE XPlore.Standing at the paradigm shift towards data-intensive science, machine learning techniques are becoming increasingly important. In particular, as a major breakthrough in the field, deep learning has proven as an extremely powerful tool in many fields. Shall we embrace deep learning as the key to all? Or, should we resist a "black-box" solution? There are controversial opinions in the remote sensing community. In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with. More importantly, we advocate remote sensing scientists to bring their expertise into deep learning, and use it as an implicit general model to tackle unprecedented large-scale influential challenges, such as climate change and urbanization. Following this wave of success and thanks to the increased availability of data and computational resources, the use of deep learning in remote sensing is finally taking off in remote sensing as well. Remote sensing data bring some new challenges for deep learning, since satellite image analysis raises some unique questions that translate into challenging new scientific questions:• Remote sensing data are often multi-modal, e.g. from optical (multi-and hyperspectral) and synthetic aperture radar (SAR) sensors, where both the imaging geometries and the content are completely different. Data and information fusion uses these complementary

show abstract

Section: Multimodal Data Fusionmentioning

confidence: 99%

Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

Zhu

Tuia

Mou

et al. 2017

IEEE Geosci. Remote Sens. Mag.

2,442

1,204

View full text Add to dashboard Cite

show abstract

“…Semantic labeling (also known as semantic segmentation in computer vision) consists in automatically building maps of geo-localized semantic classes (e.g., land use: buildings, roads, vegetation; or objects: vehicles) upon Earth Observation data [9]. In the following, we present our approach for multiscale classification using pre-trained convolutional neural networks (CNNs) based on AlexNet [13].…”

Section: Multiscale Semantic Classificationmentioning

confidence: 99%

“…In the following, we present our approach for multiscale classification using pre-trained convolutional neural networks (CNNs) based on AlexNet [13]. While easy to implement, it yields state-of-the-art performances on various datasets [9], [2] and thus works as an efficient baseline. a) Superpixel segmentation: We first segment orthophotos using the SLIC (Simple Linear Iterative Clustering [1]) method.…”

Section: Multiscale Semantic Classificationmentioning

confidence: 99%

“…Since the early applications to road detection back in 2010 [18], convolutional networks have been successfully used for classification and dense labeling of aerial imagery. They have defined new state-of-the-art performances and showed the re-use of cross-domain databases is possible to gain and transfer knowledge [20], [9]. New challenges will soon be addressed, such as image registration or 3D data analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for urban remote sensing

Audebert

Boulch

Randrianarivo

et al. 2017

2017 Joint Urban Remote Sensing Event (JURSE)

Self Cite

View full text Add to dashboard Cite

Abstract-This work shows how deep learning techniques can benefit to remote sensing. We focus on tasks which are recurrent in Earth Observation data analysis. For classification and semantic mapping of aerial images, we present various deep network architectures and show that context information and dense labeling allow to reach better performances. For estimation of normals in point clouds, combining Hough transform with convolutional networks also improves the accuracy of previous frameworks by detecting hard configurations like corners. It shows that deep learning allows to revisit remote sensing and offers promising paths for urban modeling and monitoring.

show abstract

“…This work has been later consolidated by [6] to better understand CNN-based classification of Earth Observation images. Lagrange, A. et al [14] used CNN-based superpixel classification to perform semantic segmentation and obtained competitive results on the IEEE GRSS Data Fusion Contest 2015.…”

Section: Related Workmentioning

confidence: 99%

Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images

2017

Self Cite

View full text Add to dashboard Cite

Like computer vision before, remote sensing has been radically changed by the introduction of deep learning and, more notably, Convolution Neural Networks. Land cover classification, object detection and scene understanding in aerial images rely more and more on deep networks to achieve new state-of-the-art results. Recent architectures such as Fully Convolutional Networks can even produce pixel level annotations for semantic mapping. In this work, we present a deep-learning based segment-before-detect method for segmentation and subsequent detection and classification of several varieties of wheeled vehicles in high resolution remote sensing images. This allows us to investigate object detection and classification on a complex dataset made up of visually similar classes, and to demonstrate the relevance of such a subclass modeling approach. Especially, we want to show that deep learning is also suitable for object-oriented analysis of Earth Observation data as effective object detection can be obtained as a byproduct of accurate semantic segmentation. First, we train a deep fully convolutional network on the ISPRS Potsdam and the NZAM/ONERA Christchurch datasets and show how the learnt semantic maps can be used to extract precise segmentation of vehicles. Then, we show that those maps are accurate enough to perform vehicle detection by simple connected component extraction. This allows us to study the repartition of vehicles in the city. Finally, we train a Convolutional Neural Network to perform vehicle classification on the VEDAI dataset, and transfer its knowledge to classify the individual vehicle instances that we detected.

show abstract

Benchmarking classification of earth-observation data: From learning explicit features to convolutional networks

Cited by 77 publications

References 5 publications

Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

Deep learning for urban remote sensing

Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images

Contact Info

Product

Resources

About