Processing of Extremely High-Resolution LiDAR and RGB Data: Outcome of the 2015 IEEE GRSS Data Fusion Contest–Part A: 2-D Contest

Campos-Taberner, Manuel; Romero-Soriano, Adriana; Gatta, Carlo; Camps‐Valls, Gustau; Lagrange, Adrien; Saux, Bertrand Le; Beaupere, Anne; Boulch, Alexandre; Chan-Hon-Tong, Adrien; Herbin, Stéphane; Randrianarivo, Hicham; Ferecatu, Marin; Shimoni, Michal; Moser, Gabriele; Tuia, Devis

doi:10.1109/jstars.2016.2569162

Cited by 106 publications

(84 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

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.

Self Cite

2,346

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.

Self Cite

2,346

1,204

View full text Add to dashboard Cite

show abstract

“…The ISPRS scientific research agenda reported in Chen et al (2015) identified an ongoing need for benchmarking in photogrammetry (Commission II) and open geospatial science in spatial information science (Commission IV). Recent efforts toward this goal include work by Rottensteiner et al (2014), Nex et al (2015), Campos-Taberner et al (2016), Koch et al (2016), and Wang et al (2016). Most publicly available benchmark datasets for 3D urban scene modeling have consisted of high resolution airborne imagery and lidar suitable for 3D modeling on a relatively modest scale.…”

Section: Introductionmentioning

confidence: 99%

Metric Evaluation Pipeline for 3d Modeling of Urban Scenes

Bosch

Leichtman

Chilcott

et al. 2017

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

View full text Add to dashboard Cite

ABSTRACT:Publicly available benchmark data and metric evaluation approaches have been instrumental in enabling research to advance state of the art methods for remote sensing applications in urban 3D modeling. Most publicly available benchmark datasets have consisted of high resolution airborne imagery and lidar suitable for 3D modeling on a relatively modest scale. To enable research in larger scale 3D mapping, we have recently released a public benchmark dataset with multi-view commercial satellite imagery and metrics to compare 3D point clouds with lidar ground truth. We now define a more complete metric evaluation pipeline developed as publicly available open source software to assess semantically labeled 3D models of complex urban scenes derived from multi-view commercial satellite imagery. Evaluation metrics in our pipeline include horizontal and vertical accuracy and completeness, volumetric completeness and correctness, perceptual quality, and model simplicity. Sources of ground truth include airborne lidar and overhead imagery, and we demonstrate a semi-automated process for producing accurate ground truth shape files to characterize building footprints. We validate our current metric evaluation pipeline using 3D models produced using open source multi-view stereo methods. Data and software is made publicly available to enable further research and planned benchmarking activities.

show abstract

“…More recently, Bearman et al [46] exploited a point-wise annotation for semantic segmentation, which creatively makes a better trade-off between training annotation cost and accuracy. In the area of remote sensing, Camps-Valls and Romero et al [47,48] proposed the use of greedy layer-wise unsupervised pre-training that learns sparse features for remote sensing image classification. Tschannen et al [49] introduced a structured CNNs that employed Haar wavelet-based trees for identifying the semantic category of every pixel of remote sensing image.…”

Section: Related Workmentioning

confidence: 99%

Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images

Zhang

Zhao

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Semantic image segmentation has recently witnessed considerable progress by training deep convolutional neural networks (CNNs). The core issue of this technique is the limited capacity of CNNs to depict visual objects. Existing approaches tend to utilize approximate inference in a discrete domain or additional aides and do not have a global optimum guarantee. We propose the use of the multi-label manifold ranking (MR) method in solving the linear objective energy function in a continuous domain to delineate visual objects and solve these problems. We present a novel embedded single stream optimization method based on the MR model to avoid approximations without sacrificing expressive power. In addition, we propose a novel network, which we refer to as dual multi-scale manifold ranking (DMSMR) network, that combines the dilated, multi-scale strategies with the single stream MR optimization method in the deep learning architecture to further improve the performance. Experiments on high resolution images, including close-range and remote sensing datasets, demonstrate that the proposed approach can achieve competitive accuracy without additional aides in an end-to-end manner.

show abstract

Processing of Extremely High-Resolution LiDAR and RGB Data: Outcome of the 2015 IEEE GRSS Data Fusion Contest–Part A: 2-D Contest

Cited by 106 publications

References 57 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

Metric Evaluation Pipeline for 3d Modeling of Urban Scenes

Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images

Contact Info

Product

Resources

About