Skip to content

Commit 985f5a9

Browse files
committed
Add theses
1 parent bc925ea commit 985f5a9

File tree

3 files changed

+37
-0
lines changed

3 files changed

+37
-0
lines changed
328 KB
Loading
Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
---
2+
title: Multispectral image translation from SAR data
3+
date: 2025-03-26
4+
show_date: false
5+
show_related: true
6+
profile: false
7+
tags: ['SAR', 'image translation', 'multispectral']
8+
---
9+
10+
The goal of this thesis is to investigate Deep Learning techniques for the translation of SAR data into multispectral imagery. In particular, the student will utilise a public dataset offering aligned image pairs of the Sentinel-1 (SAR) and Sentinel-2 (multispectral) satellites, such as SEN1-2 [1]. Several DL models can be explored, such as [2]-[4], and their performance will be assessed and compared.
11+
12+
**Prerequisites:** Strong Python skills, Machine Learning basic concepts, Deep Learning python framework (Pytorch, Tensorflow, etc)
13+
14+
**Supervisor:** Maria Sdraka
15+
16+
[1] https://mediatum.ub.tum.de/1436631 <br>
17+
[2] https://ieeexplore.ieee.org/abstract/document/8825802 <br>
18+
[3] https://www.sciencedirect.com/science/article/pii/S0031320321003897?casa_token=GOXb7dDI-EwAAAAA:pQPI0bBFRD5YLQ6gHkP7TiwH-RzGX9W3Xdbjz1EGG-Bp4fwQrKVVaH0l_T0uI_23Nvdq6pRi9dvA <br>
19+
[4] https://www.mdpi.com/2072-4292/11/17/2067
Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
---
2+
title: Crop segmentation from multispectral imagery
3+
date: 2025-03-26
4+
show_date: false
5+
show_related: true
6+
profile: false
7+
tags: ['wildfires', 'change detection', 'mapping']
8+
---
9+
10+
Orion Lab has assembled a novel benchmark dataset, namely Sen4AgriNet [1], for crop classification and segmentation via multi-temporal multispectral satellite imagery. The dataset comprises multi-temporal image acquisitions from the Sentinel-2 satellites over Catalonia and France, and the ground truth labels cover 168 classes.
11+
12+
The aim of this thesis is to experiment with different Deep Learning models for the segmentation of crops, and/or the detection of parcels.
13+
14+
**Prerequisites:** Strong Python skills, Machine Learning basic concepts, Deep Learning python framework (Pytorch, Tensorflow, etc)
15+
16+
**Supervisor:** Maria Sdraka
17+
18+
[1] https://ieeexplore.ieee.org/abstract/document/9749916

0 commit comments

Comments
 (0)