• Home
  • Search
  • Geometry-Aware Segmentation of Remote Sensing Images via Joint Height Estimation
  • Cite Icon16
  • https://doi.org/10.1109/lgrs.2021.3058168Copy DOI Icon

Geometry-Aware Segmentation of Remote Sensing Images via Joint Height Estimation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recent studies have shown the benefits of using additional elevation data [e.g., digital surface model (DSM) or normalized DSM (nDSM)] for enhancing the performance of the semantic labeling of aerial images. However, previous methods mostly adopt 3-D elevation information as additional inputs, while, in many real-world applications, one does not have the corresponding DSM images at hand, and the spatial resolution of acquired DSM images usually does not match the aerial images. To alleviate this data constraint and also take advantage of 3-D elevation information, in this letter, a geometry-aware segmentation model is introduced to achieve accurate semantic labeling of aerial images via joint height estimation. Instead of using a single-stream encoder–decoder network for semantic labeling, we design a separate decoder branch to predict the height map and use the DSM images as side supervision to train this newly designed decoder branch. With the newly designed decoder branch, our model can distill the 3-D geometric features from 2-D appearance features under the supervision of ground-truth DSM images. Moreover, we develop a new geometry-aware convolution module that fuses the 3-D geometric features from the height decoder branch and the 2-D contextual features from the semantic segmentation branch. The fused feature embeddings can produce geometry-aware segmentation maps with enhanced performance. Our model is trained with DSM images as side supervision, while, in the inference stage, it does not require DSM data and directly predicts the semantic labels. Experiments on International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam data sets demonstrate the effectiveness of the proposed method for the semantic segmentation of aerial images.

Similar Papers
  • PDF
  • Research Article
  • Citations240

Unsupervised Domain Adaptation Using Generative Adversarial Networks for Semantic Segmentation of Aerial Images

  • Jun 07, 2019
  • Remote Sensing
  • Bilel Benjdira +3
  • Research Article
  • Citations20

Calibrated Focal Loss for Semantic Labeling of High-Resolution Remote Sensing Images

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Haiwei Bai +4
  • Research Article
  • Citations2

ISPRS and internet: history, presence and future

  • Dec 01, 2002
  • Tuan-Chih Chen
  • PDF
  • Research Article
  • Citations24

Land Cover Classification Using SegNet with Slope, Aspect, and Multidirectional Shaded Relief Images Derived from Digital Surface Model

  • Sep 12, 2020
  • Journal of Sensors
  • Dae Geon Lee +2
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations51

CCANet: Class-Constraint Coarse-to-Fine Attentional Deep Network for Subdecimeter Aerial Image Semantic Segmentation

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Guohui Deng +4
  • Research Article
  • Citations16

MFALNet: A Multiscale Feature Aggregation Lightweight Network for Semantic Segmentation of High-Resolution Remote Sensing Images

  • Aug 06, 2020
  • IEEE Geoscience and Remote Sensing Letters
  • Liang Lv +5
  • Research Article
  • Citations19

A novel convolutional neural network architecture of multispectral remote sensing images for automatic material classification

  • May 25, 2021
  • Signal Processing: Image Communication
  • Chuen-Horng Lin +1
  • PDF
  • Research Article
  • Citations33

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

  • Nov 05, 2018
  • Sensors
  • Xuran Pan +4
  • PDF
  • Research Article
  • Citations62

Semantic Labeling of High Resolution Aerial Imagery and LiDAR Data with Fine Segmentation Network

  • May 11, 2018
  • Remote Sensing
  • Xuran Pan +5
  • Research Article
  • Citations43

DTM extraction under forest canopy using LiDAR data and a modified invasive weed optimization algorithm

  • Jul 11, 2018
  • Remote Sensing of Environment
  • Behnaz Bigdeli +2
  • Research Article
  • Citations7

MSINet: Mining scale information from digital surface models for semantic segmentation of aerial images

  • Jun 29, 2023
  • Pattern Recognition
  • Chengli Peng +4
  • Conference Article
  • Citations10

Fast semantic segmentation of aerial images based on color and texture

  • Sep 01, 2013
  • Mohaddeseh Ghiasi +1
  • Research Article

Automated building outline extraction from digital surface models and orthophoto: a novel contour-based approach

  • Sep 15, 2025
  • International Journal of Geographical Information Science
  • Fangyuqing Jin +9
  • PDF
  • Research Article
  • Citations13

True Orthoimage Generation Using Airborne LiDAR Data with Generative Adversarial Network‐Based Deep Learning Model

  • Jan 01, 2021
  • Journal of Sensors
  • Young Ha Shin +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.