Skip to Main content Skip to Navigation
Theses

Traitement d'images à haute résolution grâce à des techniques d'apprentissage en profondeur

Abstract : In this thesis, we discuss four different application scenarios that can be broadly grouped under the larger umbrella of Analyzing and Processing high-resolution images using deep learning techniques. The first three chapters encompass processing remote-sensing (RS) images which are captured either from airplanes or satellites from hundreds of kilometers away from the Earth. We start by addressing a challenging problem related to improving the classification of complex aerial scenes through a deep weakly supervised learning paradigm. We showcase as to how by only using the image level labels we can effectively localize the most distinctive regions in complex scenes and thus remove ambiguities leading to enhanced classification performance in highly complex aerial scenes. In the second chapter, we deal with refining segmentation labels of Building footprints in aerial images. This we effectively perform by first detecting errors in the initial segmentation masks and correcting only those segmentation pixels where we find a high probability of errors. The next two chapters of the thesis are related to the application of Generative Adversarial Networks. In the first one, we build an effective Cloud-GAN model to remove thin films of clouds in Sentinel-2 imagery by adopting a cyclic consistency loss. This utilizes an adversarial lossfunction to map cloudy-images to non-cloudy images in a fully unsupervised fashion, where the cyclic-loss helps in constraining the network to output a cloud-free image corresponding to the input cloudy image and not any random image in the target domain. Finally, the last chapter addresses a different set of high-resolution images, not coming from the RS domain but instead from High Dynamic Range Imaging (HDRI) application. These are 32-bit imageswhich capture the full extent of luminance present in the scene. Our goal is to quantize them to 8-bit Low Dynamic Range (LDR) images so that they can be projected effectively on our normal display screens while keeping the overall contrast and perception quality similar to that found in HDR images. We adopt a Multi-scale GAN model that focuses on both coarser as well as finer-level information necessary for high-resolution images. The final tone-mapped outputs have a high subjective quality without any perceived artifacts.
Document type :
Theses
Complete list of metadatas

Cited literature [192 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-02915582
Contributor : Abes Star :  Contact
Submitted on : Friday, August 14, 2020 - 5:47:08 PM
Last modification on : Wednesday, October 14, 2020 - 3:53:23 AM

File

2018PESC1172.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02915582, version 1

Collections

Citation

Praveer Singh. Traitement d'images à haute résolution grâce à des techniques d'apprentissage en profondeur. Apprentissage [cs.LG]. Université Paris-Est, 2018. Français. ⟨NNT : 2018PESC1172⟩. ⟨tel-02915582⟩

Share

Metrics

Record views

161

Files downloads

36