Segmentation of Small Objects in Satellite Imagery Using Dense U-Net in
Massachusetts Buildings Dataset
Dublin Core
Title
Segmentation of Small Objects in Satellite Imagery Using Dense U-Net in
Massachusetts Buildings Dataset
Massachusetts Buildings Dataset
Subject
class imbalance, dataset, end-to-end, convolution, denseU-net
Description
Class imbalance is a serious problem that disrupts the process of semantic segmentation of satellite imagery in urban areas in
Earth remote sensing. Due to the large objects dominating the segmentation process, small object are consequently limited, so
solutions based on optimizing overall accuracy are often unsatisfactory. Due to the class imbalance of semantic segmentation
in Earth remote sensing images in urban areas, we developed the concept of Down-Sampling Block (DownBlock) to obtain
contextual information and Up-Sampling Block (UpBlock) to restore the original resolution. We proposed an end-to-end deep
convolutional neural network (DenseU-Net) architecture for pixel-wise urban remote sensing image segmentation. this method
to segmentation the small object in satellite imagery.The accuracy of the small object class in this study was further improved
using our proposed method. This study used data from the Massachusetts Buildings dataset using Dense U-Net method and
obtained an overall accuracy of 84.34%
Earth remote sensing. Due to the large objects dominating the segmentation process, small object are consequently limited, so
solutions based on optimizing overall accuracy are often unsatisfactory. Due to the class imbalance of semantic segmentation
in Earth remote sensing images in urban areas, we developed the concept of Down-Sampling Block (DownBlock) to obtain
contextual information and Up-Sampling Block (UpBlock) to restore the original resolution. We proposed an end-to-end deep
convolutional neural network (DenseU-Net) architecture for pixel-wise urban remote sensing image segmentation. this method
to segmentation the small object in satellite imagery.The accuracy of the small object class in this study was further improved
using our proposed method. This study used data from the Massachusetts Buildings dataset using Dense U-Net method and
obtained an overall accuracy of 84.34%
Creator
Muhammad Iqbal Izzul Haq1
, Aniati Murni Arymurthy2
, Irham Muhammad Fadhil3
, Aniati Murni Arymurthy2
, Irham Muhammad Fadhil3
Publisher
Universitas Indonesia
Date
30-06-2022
Contributor
Fajar Bagus W
Format
PDF
Language
Indonesia
Type
Text
Files
Collection
Citation
Muhammad Iqbal Izzul Haq1
, Aniati Murni Arymurthy2
, Irham Muhammad Fadhil3, “Segmentation of Small Objects in Satellite Imagery Using Dense U-Net in
Massachusetts Buildings Dataset,” Repository Horizon University Indonesia, accessed June 5, 2025, https://repository.horizon.ac.id/items/show/9175.
Massachusetts Buildings Dataset,” Repository Horizon University Indonesia, accessed June 5, 2025, https://repository.horizon.ac.id/items/show/9175.