PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
January 6, 2026Remote SensingOpen Access

High-Rise Building Area Extraction Based on Prior-Embedded Dual-Branch Neural Network

View Full Paper
Ask AI
Bookmark
Share

Authors

QSQiliang SiLLLiwei LiGCGang Cheng

Discussion

Loading...

Member takes

Overview

This approach improves urban planning and resource management by effectively extracting high-rise building features from remote sensing images.

Key Points

  • To develop a robust method for extracting high-rise building areas using advanced neural networks.
  • Utilized a Prior-Embedded Dual-Branch Neural Network (PEDNet) for feature extraction.
  • Incorporated a window attention mechanism to integrate diverse prior information.
  • Conducted experiments with Sentinel-2 data from multiple cities.
  • Outperformed traditional models like FCN and U-Net.
  • Surpassed recent high-performance models including DeepLabV3+ and BuildFormer.
  • Successfully adapted to various complex conditions for urban monitoring.

Cite This Study

Si et al. (2026) studied this question.

synapsesocial.com/papers/695d855e3483e917927a4beehttps://doi.org/10.3390/rs18010167
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Building Detection: Testing a New Object-Based Approach Against Neural Networks2024
  2. 2Individual High-Rise Building Extraction from Single High-Resolution SAR Image Based on Part Model2024 · 1 citations
  3. 3GA-HRNet: High-Precision Building Extraction for Individualization of Oblique Photogrammetry 3D Models2026
  4. 4Building Instance Extraction via Multi-Scale Hybrid Dual-Attention Network2025
  5. 5Building extraction from remote sensing imagery: advanced squeeze-and-excitation residual network based methodology2024