Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Pascoal, R. (2026). Multi-Sensor Augmented Reality for Reliable Outdoor Measurement in Urban and Landscape Design: From Data to Architectonic and Territorial Analysis. International Conference on Design Principles & Practices.
Exportar Referência (IEEE) 
R. M. Pascoal,  "Multi-Sensor Augmented Reality for Reliable Outdoor Measurement in Urban and Landscape Design: From Data to Architectonic and Territorial Analysis", in Int. Conf. on Design Principles & Practices, Rome, 2026
Exportar BibTeX 
@misc{pascoal2026_1773315120627,
	author = "Pascoal, R.",
	title = "Multi-Sensor Augmented Reality for Reliable Outdoor Measurement in Urban and Landscape Design: From Data to Architectonic and Territorial Analysis",
	year = "2026",
	url = "https://designprinciplesandpractices.com/"
}
Exportar RIS 
TY  - CPAPER
TI  - Multi-Sensor Augmented Reality for Reliable Outdoor Measurement in Urban and Landscape Design: From Data to Architectonic and Territorial Analysis
T2  - International Conference on Design Principles & Practices
AU  - Pascoal, R.
PY  - 2026
CY  - Rome
UR  - https://designprinciplesandpractices.com/
AB  - Accurate outdoor spatial measurement is fundamental for architectonic, urban, and environmental design processes, yet current mobile Augmented Reality (AR) tools still face significant limitations caused by calibration drift, sensor noise, and dynamic environmental conditions. This paper presents EfMAR (Effective Framework Measurement with Augmented Reality), a modular and scalable architecture that delivers high-precision outdoor distance and spatial measurements through adaptive multi-sensor fusion, advancing AR as a reliable instrument for spatial analysis and territorial planning. Beyond its technical/ practical implementation, EfMAR introduces a theoretical framework for adaptive sensor fusion in mobile AR, offering a reusable and device-agnostic model applicable across diverse urban contexts. The system integrates, e.g., SLAM (RGB), LiDAR, ToF, GPS, and IMU inputs within an adaptive fusion mechanism that continuously optimizes accuracy in response to lighting, surfaces, occlusions, and environmental variability. Unlike existing single-sensor pipelines, EfMAR formalizes a layered, generalizable architecture suitable for professional-grade design workflows. EfMAR was validated using a publicly available dataset of 584 measurements collected across varied urban morphologies, including plazas, narrow corridors, shaded parks, and construction areas, and benchmarked against reference instruments and commercial AR applications. For design practice, these results position EfMAR as a robust spatial tool that enhances site analysis, urban morphology assessment, environmental layout studies, and early-stage architectural decision-making. By strengthening measurement reliability in real-world conditions, EfMAR contributes to scalable, data-driven processes in architectonic, spatial, and environmental design.
ER  -