KIT | KIT-Bibliothek | Impressum | Datenschutz

A Novel Building Temperature Simulation Approach Driven by Expanding Semantic Segmentation Training Datasets with Synthetic Aerial Thermal Images

Hou, Yu; Volk, Rebekka ORCID iD icon; Soibelman, Lucio

Multi-sensor imagery data has been used by researchers for the image semantic segmentation of buildings and outdoor scenes. Due to multi-sensor data hunger, researchers have implemented many simulation approaches to create synthetic datasets, and they have also synthesized thermal images because such thermal information can potentially improve segmentation accuracy. However, current approaches are mostly based on the laws of physics and are limited to geometric models’ level of detail (LOD), which describes the overall planning or modeling state. Another issue in current physics-based approaches is that thermal images cannot be aligned to RGB images because the configurations of a virtual camera used for rendering thermal images are difficult to synchronize with the configurations of a real camera used for capturing RGB images, which is important for segmentation. In this study, we propose an image translation approach to directly convert RGB images to simulated thermal images for expanding segmentation datasets. We aim to investigate the benefits of using an image translation approach for generating synthetic aerial thermal images and compare those approaches with physics-based approaches. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000128283
Veröffentlicht am 18.01.2021
DOI: 10.3390/en14020353
Zitationen: 3
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Industriebetriebslehre und Industrielle Produktion (IIP)
Publikationstyp Zeitschriftenaufsatz
Publikationsdatum 11.01.2021
Sprache Englisch
Identifikator ISSN: 1996-1073
KITopen-ID: 1000128283
Erschienen in Energies
Verlag MDPI
Band 14
Heft 2
Seiten Art.-Nr.: 353
Bemerkung zur Veröffentlichung This article belongs to the Special Issue Building Thermal Envelope - New Trends and Applications
Schlagwörter building envelopes; thermal image simulation; segmentation datasets; data hunger
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page