• Home
  • Search
  • Efficient building segmentation with a lightweight U-Net in high-resolution aerial imagery
  • https://doi.org/10.1049/icp.2025.4069Copy DOI Icon

Efficient building segmentation with a lightweight U-Net in high-resolution aerial imagery

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

The precise and accurate semantic segmentation of complex scenes from remote sensing images has always been a challenging task. Thanks to advances in deep neural networks, segmentation models, especially U-Net and its variants, have shown promising segmentation results. However, the enhanced performance of the currently popular deep segmentation models comes at the cost of time and computational efficiency. Moreover, these models often struggle to deliver accurate segmentation results when computational resources are constrained, as is common in large-scale or operational remote sensing workflows. Therefore, this study presents a significantly small, fast, and computationally efficient version of a U-Net, called TinyEffUnet. To verify the effectiveness of the proposed lightweight model, we conduct extensive experiments on a building extraction dataset – INRIA aerial scene segmentation dataset. Compared to a canonical U-Net, TinyEffUnet achieves superior intersection over union (IoU) performance in extracting building structures from aerial imagery with only 1.8M parameters and 5.08B floating point operations (FLOPs), demonstrating its efficiency and suitability for large-scale remote sensing applications. This efficiency also makes it well-suited for deployment on satellite payloads with computational constraints.

Similar Papers
  • Research Article

Automatic instream large wood detection and wood load estimation using machine learning from high-resolution aerial imagery

  • Oct 09, 2025
  • Geomorphica
  • Janbert Aarnink +6
  • Research Article
  • Citations23

Forest fuel treatment detection using multi-temporal airborne lidar data and high-resolution aerial imagery: a case study in the Sierra Nevada Mountains, California

  • Jun 28, 2016
  • International Journal of Remote Sensing
  • Yanjun Su +5
  • PDF
  • Research Article
  • Citations3

Evapotranspiration estimation using high-resolution aerial imagery and pySEBAL for processing tomatoes

  • Jun 04, 2024
  • Irrigation Science
  • Srinivasa Rao Peddinti +3
  • Research Article

Developing a Machine Learning-Based Framework for Roadway Vulnerability and Impact Assessment Using Aerial Imagery

  • Apr 01, 2026
  • International Journal of Disaster Risk Science
  • Samuel Takyi +3
  • PDF
  • Research Article
  • Citations32

High-Resolution Aerial Imagery Semantic Labeling with Dense Pyramid Network.

  • Nov 05, 2018
  • Sensors
  • Xuran Pan +4
  • PDF
  • Research Article
  • Citations5

SEGMENT-AND-COUNT: VEHICLE COUNTING IN AERIAL IMAGERY USING ATROUS CONVOLUTIONAL NEURAL NETWORKS

  • Sep 26, 2018
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • S Azimi +3
  • Research Article
  • Citations17

Channel morphological change monitoring using high-resolution LiDAR-derived DEM and multi-temporal imageries

  • Feb 22, 2024
  • Science of The Total Environment
  • Tesfa Gebrie Andualem +5
  • Research Article
  • Citations6

Developing a forest description from remote sensing: Insights from New Zealand

  • Jun 01, 2025
  • Science of Remote Sensing
  • Grant D Pearse +7
  • PDF
  • Research Article

Investigating the efficiency and capabilities of UAVs and Convolutional Neural Networks in the field of remote sensing as a land classification tool

  • Aug 07, 2023
  • South African Journal of Geomatics
  • Cameron Wesson +2
  • Research Article

Comparative Study of Pretrained Models for Remote Sensing Image Classification

  • Jul 24, 2025
  • International Research Journal on Advanced Engineering Hub (IRJAEH)
  • Minakshi N Vharkate +2
  • Preprint Article

Timing and Extent of Late Quaternary Glaciation in the Ahuriri River Valley, Southern Alps, New Zealand

  • Mar 03, 2021
  • Levan Tielidze +3
  • Research Article

Correction: AM-UNet: Road Network Extraction from high-resolution Aerial Imagery Using Attention-Based Convolutional Neural Network

  • Feb 20, 2025
  • Journal of the Indian Society of Remote Sensing
  • Yashwant Soni +3
  • Research Article
  • Citations20

Linaria dalmatica invades south-facing slopes and less grazed areas in grazing-tolerant mixed-grass prairie

  • Aug 11, 2011
  • Biological Invasions
  • Dana M Blumenthal +7
  • Conference Article

Improving the Performance of Seabirds Detection Combining Multiple Semantic Segmentation Models

  • Sep 26, 2020
  • Chunxiu Liu +2
  • Preprint Article

Leaf-it to AI

  • May 21, 2025
  • Theo Hermann +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.