Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep learning-based region merging with adaptive threshold optimization for building segmentation in remote sensing

Asim Shoaib¹, Muhammad Waqas Nadeem¹, Nohaidda Sariff²

¹Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Kampar, Perak, Malaysia.

|May 15, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

RUL-DBRS: A Novel Energy Efficient and Robust Protocol for Enhanced Communication in Underwater Wireless Sensor Networks.

Scientific reports·2026

Same author

Automated bone marrow cell classification using ensemble learning: performance, generalization, and clinical interpretability.

Frontiers in medicine·2026

Same author

Multimodal Fusion of Endoscopic and Histopathological Images for Lesion Detection Using Hybrid Deep Learning.

Current medical imaging·2026

Same author

RETRACTED: Srivastava et al. Match-Level Fusion of Finger-Knuckle Print and Iris for Human Identity Validation Using Neuro-Fuzzy Classifier. <i>Sensors</i> 2022, <i>22</i>, 3620.

Sensors (Basel, Switzerland)·2026

Same author

Computational approaches for drug-drug interaction prediction: a systematic review of data sources, modeling strategies, and evaluation frameworks.

Frontiers in pharmacology·2026

Same author

Development of an energy consumption map for turning inconel 718 through coupled chip-morphology and material-deformation analysis.

Scientific reports·2026

This summary is machine-generated.

This study introduces a new method for accurately extracting buildings from remote sensing images using an adaptive thresholding technique and a deep learning model. The approach improves building segmentation accuracy, outperforming traditional methods.

Area of Science:

Geosciences
Computer Science
Remote Sensing

Background:

Precise building extraction from remote sensing (RS) images is crucial for urban analysis and land management.
Challenges include spectral similarity with other objects, limited boundary information, and small building detection.
Traditional segmentation methods struggle with fixed thresholds and over-segmentation, leading to inaccurate results.

Purpose of the Study:

To develop a novel segmentation approach for accurate building extraction from high-resolution RS images.
To overcome limitations of traditional methods by incorporating adaptive thresholding and deep feature-based merging.
To enhance building boundary delineation and classification accuracy.

Main Methods:

Initial segmentation using Simple Linear Iterative Clustering (SLIC).

Related Experiment Videos

Last Updated: May 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Application of a Convolutional Neural Network (CNN)-based AttentionU-Net for deep feature extraction.

Integration of adaptive thresholding optimization and a merging criterion (MC) based on deep features.

Main Results:

The proposed approach combines low and high-level features, reducing misalignment during merging.
Achieved superior segmentation accuracy on the WHU buildings RS images dataset.
Outperformed the multiresolution segmentation (MRS) algorithm with an F-measure of 0.91 and Gs of 0.92.

Conclusions:

The novel approach effectively enhances traditional region merging strategies for building segmentation.
Eliminates the need for rigid thresholds, offering greater flexibility and accuracy.
Demonstrates significant improvements in building delineation accuracy compared to existing methods.