Leveraging Self-Supervised Features for Efficient Flooded Region Identification in UAV Aerial Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deb, Dibyabha, Verma, Ujjwal
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908437735014400
author Deb, Dibyabha
Verma, Ujjwal
author_facet Deb, Dibyabha
Verma, Ujjwal
contents Identifying regions affected by disasters is a vital step in effectively managing and planning relief and rescue efforts. Unlike the traditional approaches of manually assessing post-disaster damage, analyzing images of Unmanned Aerial Vehicles (UAVs) offers an objective and reliable way to assess the damage. In the past, segmentation techniques have been adopted to identify post-flood damage in UAV aerial images. However, most of these supervised learning approaches rely on manually annotated datasets. Indeed, annotating images is a time-consuming and error-prone task that requires domain expertise. This work focuses on leveraging self-supervised features to accurately identify flooded regions in UAV aerial images. This work proposes two encoder-decoder-based segmentation approaches, which integrate the visual features learned from DINOv2 with the traditional encoder backbone. This study investigates the generalization of self-supervised features for UAV aerial images. Specifically, we evaluate the effectiveness of features from the DINOv2 model, trained on non-aerial images, for segmenting aerial images, noting the distinct perspectives between the two image types. Our results demonstrate that DINOv2's self-supervised pretraining on natural images generates transferable, general-purpose visual features that streamline the development of aerial segmentation workflows. By leveraging these features as a foundation, we significantly reduce reliance on labor-intensive manual annotation processes, enabling high-accuracy segmentation with limited labeled aerial data.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Self-Supervised Features for Efficient Flooded Region Identification in UAV Aerial Images
Deb, Dibyabha
Verma, Ujjwal
Computer Vision and Pattern Recognition
Identifying regions affected by disasters is a vital step in effectively managing and planning relief and rescue efforts. Unlike the traditional approaches of manually assessing post-disaster damage, analyzing images of Unmanned Aerial Vehicles (UAVs) offers an objective and reliable way to assess the damage. In the past, segmentation techniques have been adopted to identify post-flood damage in UAV aerial images. However, most of these supervised learning approaches rely on manually annotated datasets. Indeed, annotating images is a time-consuming and error-prone task that requires domain expertise. This work focuses on leveraging self-supervised features to accurately identify flooded regions in UAV aerial images. This work proposes two encoder-decoder-based segmentation approaches, which integrate the visual features learned from DINOv2 with the traditional encoder backbone. This study investigates the generalization of self-supervised features for UAV aerial images. Specifically, we evaluate the effectiveness of features from the DINOv2 model, trained on non-aerial images, for segmenting aerial images, noting the distinct perspectives between the two image types. Our results demonstrate that DINOv2's self-supervised pretraining on natural images generates transferable, general-purpose visual features that streamline the development of aerial segmentation workflows. By leveraging these features as a foundation, we significantly reduce reliance on labor-intensive manual annotation processes, enabling high-accuracy segmentation with limited labeled aerial data.
title Leveraging Self-Supervised Features for Efficient Flooded Region Identification in UAV Aerial Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.04915