Data Fusion for Multi-Task Learning of Building Extraction and Height Estimation

Saad Ahmed Jamal, Arioluwa Aribisala
8/5/2023
cs.CVcs.AIcs.LG

No official code found. Best implementation: SaadAhmedJamal/IEEE_DFC2023 (5 stars, Apache-2.0, last commit 2023-10-18).

Abstract

In accordance with the urban reconstruction problem proposed by the DFC23 Track 2 Contest, this paper attempts a multitask-learning method of building extraction and height estimation using both optical and radar satellite imagery. Contrary to the initial goal of multitask learning which could potentially give a superior solution by reusing features and forming implicit constraints between multiple tasks, this paper reports the individual implementation of the building extraction and height estimation under constraints. The baseline results for the building extraction and the height estimation significantly increased after designed experiments.

View on arXivView PDF

Code Implementations(1)

SaadAhmedJamal/IEEE_DFC2023Community100%
Apache-2.0
50Python, Jupyter NotebookAug 5, 20233 years agoApache-2.0

Similar Papers

HGDNet: A Height-Hierarchy Guided Dual-Decoder Network for Single View Building Extraction and Height Estimation

84% match2023

LIGHT: Joint Individual Building Extraction and Height Estimation from Satellite Images through a Unified Multitask Learning Network

84% match2023

An Object-Based Deep Learning Approach for Building Height Estimation from Single SAR Images

83% match2025

Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery

82% match2025

BuildMamba: A Visual State-Space Based Model for Multi-Task Building Segmentation and Height Estimation from Satellite Images

82% match2026

Building Height Estimation Using Shadow Length in Satellite Imagery

81% match2024

Cite this paper

@article{jamal2023data,
  title  = {Data Fusion for Multi-Task Learning of Building Extraction and Height Estimation},
  author = {Saad Ahmed Jamal and Arioluwa Aribisala},
  year   = {2023},
  eprint = {2308.02960},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.02960v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.02960.svg)](https://codeofpaper.com/paper/2308.02960)

Discussion