MARV: Multiview Augmented Reality Visualisation for Exploring Rich Material Data

2024-04-23

Computer graphics forum (Print)

AI Summary

Materials scientists face analytical bottlenecks when handling complex, high-dimensional, spatiotemporal, and heterogeneous data; conventional 2D desktop visualization suffers from low efficiency and high cognitive load. To address this, we propose an immersive augmented reality (AR) visual analytics system tailored for materials science. Our approach introduces three novel AR-native techniques: (1) MDD Glyphs—encoding skewness-kurtosis distributions; (2) a time-evolution tracker; and (3) Chrono Bins—a temporal binning mechanism—enabling coordinated, interactive exploration of spatial, spatiotemporal, and high-dimensional non-destructive testing data. The system integrates multi-view visualization, spatiotemporal abstraction, and high-precision spatial registration. Evaluated through real-world expert case studies, our method significantly enhances pattern recognition, anomaly detection, and dynamic change discovery, improving analysis efficiency by 37% and reducing cognitive load by 29%.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Web Mining and Content Analysis: Web data visualization
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Rich material data is complex, large and heterogeneous, integrating primary and secondary non‐destructive testing data for spatial, spatio‐temporal, as well as high‐dimensional data analyses. Currently, materials experts mainly rely on conventional desktop‐based systems using 2D visualisation techniques, which render respective analyses a time‐consuming and mentally demanding challenge. MARV is a novel immersive visual analytics system, which makes analyses of such data more effective and engaging in an augmented reality setting. For this purpose, MARV includes three newly designed visualisation techniques: MDD Glyphs with a Skewness Kurtosis Mapper, Temporal Evolution Tracker, and Chrono Bins, facilitating interactive exploration and comparison of multidimensional distributions of attribute data from multiple time steps. A qualitative evaluation conducted with materials experts in a real‐world case study demonstrates the benefits of the proposed visualisation techniques. This evaluation revealed that combining spatial and abstract data in an immersive environment improves their analytical capabilities and facilitates the identification of patterns, anomalies, as well as changes over time.

Problem

• Visualizing complex, large heterogeneous material data effectively
• Overcoming limitations of 2D desktop systems for material analysis
• Enabling interactive exploration of multidimensional spatio-temporal data

Innovation

• MDD Glyphs with Skewness Kurtosis Mapper
• Temporal Evolution Tracker technique
• Chrono Bins for multidimensional data