Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing

Donghwa Shon; Byeongjoon Noh; Nahyang Byun

Home/Archive/arXiv

arXiv · 2201.01081

Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing

Donghwa Shon·Byeongjoon Noh·Nahyang Byun

View original source ↗Read source document ↗Export metadata ↓

Abstract

Despite the fact that architectural administration information in Korea has been providing high-quality information for a long period of time, the level of utility of the information is not high because it focuses on administrative information. While this is the case, a three-dimensional (3D) map with higher resolution has emerged along with the technological development. However, it cannot function better than visual transmission, as it includes only image information focusing on the exterior of the building. If information related to the exterior of the building can be extracted or identified from a 3D map, it is expected that the utility of the information will be more valuable as the national architectural administration information can then potentially be extended to include such information regarding the building exteriors to the level of BIM(Building Information Modeling). This study aims to present and assess a basic method of extracting information related to the appearance of the exterior of a building for the purpose of 3D mapping using deep learning and digital image processing. After extracting and preprocessing images from the map, information was identified using the Fast R-CNN(Regions with Convolutional Neuron Networks) model. The information was identified using the Faster R-CNN model after extracting and preprocessing images from the map. As a result, it showed approximately 93% and 91% accuracy in terms of detecting the elevation and window parts of the building, respectively, as well as excellent performance in an experiment aimed at extracting the elevation information of the building. Nonetheless, it is expected that improved results will be obtained by supplementing the probability of mixing the false detection rate or noise data caused by the misunderstanding of experimenters in relation to the unclear boundaries of windows.

Explore related subjects

cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Donghwa Shon, Byeongjoon Noh, Nahyang Byun. 2022-01-04. Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing. https://arxiv.org/abs/2201.01081

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing access to the trained models, have emerged as a formidable privacy threat. Given a trained network, these attacks enable adversaries to reconstruct high-fidelity data that closely aligns with the private training samples, posing significant privacy concerns. Despite the rapid advances in the field, we lack a comprehensive and systematic overview of existing MI attacks and defenses. To fill this gap, this paper thoroughly investigates this realm and presents a holistic survey. Firstly, our work briefly reviews early MI studies on traditional machine learning scenarios. We then elaborately analyze and compare numerous recent attacks and defenses on Deep Neural Networks (DNNs) across multiple modalities and learning tasks. By meticulously analyzing their distinctive features, we summarize and classify these methods into different categories and provide a novel taxonomy. Finally, this paper discusses promising research directions and presents potential solutions to open issues. To facilitate further study on MI attacks and defenses, we have implemented an open-source model inversion toolbox on GitHub (https://github.com/ffhibnese/Model-Inversion-Attack-ToolBox).

cs.CV↗

arXiv2026

ALINA: Advanced Line Identification and Notation Algorithm

Labels are the cornerstone of supervised machine learning algorithms. Most visual recognition methods are fully supervised, using bounding boxes or pixel-wise segmentations for object localization. Traditional labeling methods, such as crowd-sourcing, are prohibitive due to cost, data privacy, amount of time, and potential errors on large datasets. To address these issues, we propose a novel annotation framework, Advanced Line Identification and Notation Algorithm (ALINA), which can be used for labeling taxiway datasets that consist of different camera perspectives and variable weather attributes (sunny and cloudy). Additionally, the CIRCular threshoLd pixEl Discovery And Traversal (CIRCLEDAT) algorithm has been proposed, which is an integral step in determining the pixels corresponding to taxiway line markings. Once the pixels are identified, ALINA generates corresponding pixel coordinate annotations on the frame. Using this approach, 60,249 frames from the taxiway dataset, AssistTaxi have been labeled. To evaluate the performance, a context-based edge map (CBEM) set was generated manually based on edge features and connectivity. The detection rate after testing the annotated labels with the CBEM set was recorded as 98.45%, attesting its dependability and effectiveness.

cs.CV↗

arXiv2026

DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response

Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-centric assessment. To study this building-centric gap, we introduce \method{}, a diagnostic benchmark built on xBD, a pre/post-disaster satellite dataset with building-level damage labels. \method{} enriches building instances with OpenStreetMap-derived functional labels and contains 134{,}108 task-specific instruction records across 15 task types, spanning instance-level assessment, scene-level counting, multi-instance reasoning, and structured report generation. The benchmark supports RGB pre/post-disaster imagery, single- and multi-view instance formulations, and scene-level RGB/SAR diagnostic inputs. Experiments with general-domain and remote-sensing VLMs show that models perform better on visible damage cues than on building-function understanding, multi-instance reasoning, counting, and grounded reporting. Instruction tuning improves performance on several tasks but does not close this building-centric gap.

cs.CV↗