LULC Segmentation in Historical Images Under Domain Shift: An Empirical Study

Agricultural abandonment is a global trend leading to vegetation succession and Forests expansion. Manual annotations of 1946 and 2019 aerial surveys images from a peri-urban area in Massif Central shows Land Use and Land Cover (LULC) evolution in this period. We propose to use a convolutional neura...

Full description

Saved in:
Bibliographic Details
Main Authors: Briand, Swann, Weissgerber, Flora, Fournier, Pierre, Weissgerber, Magali
Format: Conference Proceeding
Language:English
Subjects:
aerial survey
Agricultural abandonment
CNN semantic segmentation
Data augmentation
domain adaptation
Image segmentation
Manuals
Semantics
Surveys
Training
Vegetation mapping
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Agricultural abandonment is a global trend leading to vegetation succession and Forests expansion. Manual annotations of 1946 and 2019 aerial surveys images from a peri-urban area in Massif Central shows Land Use and Land Cover (LULC) evolution in this period. We propose to use a convolutional neural network trained on labelled years images to predict LULC maps from 13 intermediate years unlabelled images. However, sensors variety used for acquisition during this time induce variability in ground sampling distances and colorimetry. We have shown using transfer between labelled years that sampling distances have to be the same in the training and testing set, and that coarse scaling offer sufficient performances for the considered LULC classes. Colorimetric data augmentations were individually used after sampling unification to make models more robust to sensors and illumination changes, but proved to be inconsistent in transfer on intermediate years.
ISSN:2153-7003
DOI:10.1109/IGARSS53475.2024.10642279