Search
Feedback
About UniCat 
Help
News
| Listing 1 - 2 of 2 |
Sort by
|
Dissertation
Year: 2021 Publisher: Liège Université de Liège (ULiège)
Abstract | Keywords | Export | Availability | Bookmark
Loading...Choose an application
- Reference Manager
- EndNote
- RefWorks (Direct export to RefWorks)
Land cover change detection is a crucial task to automate for many applications ranging from efficient natural disaster monitoring or military surveillance to property insurance optimization. Space missions, notably Sentinel-2 from the European Space Agency have opened the path to a much wider use of multispectral geospatial imaging with high temporal resolution which proves ideal for the task of bitemporal change detection. In that context, the company Aerospacelab has implemented a neural network trained on a synthetic dataset in order to cope for the lack of labeled data. This thesis has two aims: evaluating the potential of multispectral channels in contrast to the three typical visual spectral channels Red-Green-Blue for the task of general change detection and establishing whether or not unsupervised or semi-supervised methods can better cope with the common lack of available labeled data. To provide these insights, an unsupervised approach initially proposed by Gong et al. called Generative Discriminatory Classified Network (GDCN) is exploited, derived, implemented and tested. It consists in a generator to produce bitemporal multispectral satellite images and a discriminator which simultaneously discriminates between real and fake pairs of images as well as classify each of its pixels as change or non-change. To determine the impact of each of the approach's components on the performances for the task of change detection, three models are implemented: GDCN itself, ConvGDCN which is a scalable derivation of the model inspired from the Deep Convolutional GAN framework proposed by Radford et al. and finally, ConvCN which is a copy of ConvGDCN from which were removed the parts dedicated to the generation task in order to evaluate just how useful it is. Each model is trained in the unsupervised manner proposed by Gong et al. relying on pseudo labeled samples provided by another notable unsupervised method: Compressed Change Vector Analysis by Bovolo et al. The unsupervised models are tuned on a validation set and the best of each model trained on both RGB and multispectral images are fine-tuned with a small amount of hand-labeled samples. All unsupervised and tuned models with both RGB and multispectral images are tested on a test dataset and the results provide insights to the company's questions. Specifically, this work shows that RGB images carry most of the information relevant to the task of general change detection and that most significant improvements can be obtained by better exploiting these RGB bands. Additional multispectral bands can still be used in specific contexts, for instance in the form of known spectral indices but otherwise complicate the learning task by adding more noise than useful information which creates a need for more complex models and larger datasets. As to the unsupervised and semi-supervised methods, this work shows that they can compare to the synthetic dataset-trained approach while not outperforming it. Nevertheless, our appproach can provide good pretrained weights to be tuned for a more specific task of change detection.
Multispectral Imagery --- Change Detection --- Unsupervised Learning --- Semi-Supervised Learning --- Generative Adversarial Networks --- Deep Learning --- Machine Learning --- Deep Convolutional Generative Adversarial Networks --- High Resolution Satellite Imagery --- Sentinel-2 --- Ingénierie, informatique & technologie > Sciences informatiques
Book
ISBN: 3039217577 3039217569 Year: 2019 Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Abstract | Keywords | Export | Availability | Bookmark
Loading...Choose an application
- Reference Manager
- EndNote
- RefWorks (Direct export to RefWorks)
Recently, growing interest in the use of remote sensing imagery has appeared to provide synoptic maps of water quality parameters in coastal and inner water ecosystems;, monitoring of complex land ecosystems for biodiversity conservation; precision agriculture for the management of soils, crops, and pests; urban planning; disaster monitoring, etc. However, for these maps to achieve their full potential, it is important to engage in periodic monitoring and analysis of multi-temporal changes. In this context, very high resolution (VHR) satellite-based optical, infrared, and radar imaging instruments provide reliable information to implement spatially-based conservation actions. Moreover, they enable observations of parameters of our environment at greater broader spatial and finer temporal scales than those allowed through field observation alone. In this sense, recent very high resolution satellite technologies and image processing algorithms present the opportunity to develop quantitative techniques that have the potential to improve upon traditional techniques in terms of cost, mapping fidelity, and objectivity. Typical applications include multi-temporal classification, recognition and tracking of specific patterns, multisensor data fusion, analysis of land/marine ecosystem processes and environment monitoring, etc. This book aims to collect new developments, methodologies, and applications of very high resolution satellite data for remote sensing. The works selected provide to the research community the most recent advances on all aspects of VHR satellite remote sensing.
very high-resolution Pléiades imagery --- surface convergence --- data augmentation --- acquisition geometry --- SVM classification --- urban water mapping --- beaver dam analogue --- agriculture parcel segmentation --- morphological building index --- airborne hypespectral imagery --- sunglint correction --- water index --- over-segmentation index (OSI) --- High-resolution satellite imagery --- multi-resolution segmentation (MRS) --- GaoFen-2 (GF-2) --- benthic mapping --- scene classification --- greenhouse extraction --- edge constraint --- Deformable CNN --- built-up areas extraction --- ultra-dense connection --- seagrass --- beaver mimicry --- forested mountain --- natural hazards --- remote sensing --- dimensionality reduction techniques --- road extraction --- landslide monitoring --- Slumgullion landslide --- synthetic aperture radar --- building detection --- Worldview-2 --- saliency index --- under-segmentation index (USI) --- texture analysis --- fast marching method --- video satellite --- CNN --- capsule --- super-resolution --- feature distillation --- shadow detection --- PrimaryCaps --- semiautomatic --- compensation unit --- superpixels --- riparian --- QuickBird --- submesoscale --- linear unmixing --- accuracy assessment --- composite error index (CEI) --- cyanobacteria --- local feature points --- Faster R-CNN --- occluded object detection --- error index of total area (ETA) --- large displacements --- threshold stability --- remote sensing imagery --- water column correction --- canopy height model --- spiral eddy --- sub-pixel offset tracking --- consensus --- stream restoration --- western Baltic Sea --- Worldview --- very high-resolution image --- CapsNet --- atmospheric correction
| Listing 1 - 2 of 2 |
Sort by
|