InfraredTags: Embedding Invisible AR Markers and Barcodes Using Low-Cost, Infrared-Based 3D Printing and Imaging Tools

AR Navigation & Context Awareness3D Modeling & AnimationUI/UX DesignersMakers & DIY EnthusiastsHCI Researchers

Title of the Paper

InfraredTags: Embedding Invisible AR Markers and Barcodes Using Low-Cost, Infrared-Based 3D Printing and Imaging Tools

Paper Information

  • Subject Area: Human-Computer Interaction, Augmented Reality (AR), 3D Printing, and Computer Vision
  • Keywords: Invisible tags, marker recognition, 3D printing, personalized manufacturing, infrared imaging, augmented reality, computer vision, barcode technology

Research Background and Problem

  • Problems/Challenges Identified by the Authors:

    • Tags used for augmented reality (AR) and object tracking are often visually obtrusive and detract from the aesthetics of objects.
    • Traditional methods for embedding tags into 3D printing require expensive equipment or complex manufacturing processes.
    • Existing solutions (e.g., AirCode, InfraStructs, LayerCode) face issues such as inefficiency or high costs, including time-consuming scanning using projection devices or the need for custom hardware materials.
    • Tag detection can be limited by material transparency and lighting conditions.
  • Significance:

    • Concealable tag technology could significantly expand the potential of AR, packaging tracking, object recognition, and other fields.
    • Tags that eliminate visual interference can advance personalized manufacturing technologies and enhance user interaction experiences.
  • Research Motivation and Related Work:

    • The authors aim to achieve fully functional, low-cost, invisible encoded tags embedded in 3D-printed objects.
    • Previous related studies (e.g., AirCode and InfraStructs) partially address these issues but fall short in terms of cost and complexity.

Solution

  • Method or Solution:

    • Proposes a novel infrared-based method, "InfraredTags," to embed invisible tags into 3D-printed objects.
    • Uses infrared-transmissive materials (IR PLA) and air-gap designs to generate codes, making tags detectable only under infrared light.
    • Developed a user interface to facilitate the integration of common tags (e.g., QR codes, ArUco markers) into object geometries, supporting both single-material and multi-material printing.
    • Designed a low-cost infrared imaging module that can be integrated with mobile devices and uses a custom image processing pipeline to decode the tags.
  • Innovations:

    • Tags are invisible to the naked eye: embedded tags are completely concealed under normal lighting but detectable under infrared light.
    • Utilizes readily available low-cost equipment (e.g., FDM 3D printers and standard infrared cameras), avoiding the need for expensive or custom hardware.
    • Supports tag detection within seconds from a single frame, making it suitable for real-time applications.
  • Implementation Steps:

    • Print objects using infrared-transmissive materials (IR PLA) and embed tags based on geometric designs.
    • Construct an infrared imaging module with an infrared filter to block visible light interference and infrared LED lighting to enhance detection.
    • Provide an interactive interface for embedding tags, supporting position adjustments and printing options.
    • Use improved image processing techniques to enable real-time tag decoding via smartphone cameras.

Research Outcomes

  • Specific Results:

    • Successfully developed a low-cost, high-efficiency infrared tag embedding system capable of supporting various barcodes (e.g., QR codes and ArUco markers).
    • Achieved tag detection from a distance of 250 cm and effective operation under low-light conditions (e.g., 0.2 lux).
    • The tag technology expands the feasibility of AR interactions, information embedding, and object tracking.
  • Advantages:

    • Compared to existing technologies, this solution significantly reduces costs and simplifies the manufacturing process.
    • Multi-tag designs (supporting scanning from different angles or partially occluded tags) enhance detection flexibility.
    • Fast detection speeds enable real-time interaction and compatibility with standard smartphones.
  • Experimental or Evaluation Results:

    • Multi-material printed tags exhibited longer detection ranges than single-material printed tags, with a minimum tag size of 6mm width (ArUco markers).
    • Tags performed well under challenging lighting conditions (e.g., indoor lighting or complete darkness), especially when multi-material printing was combined with infrared LED lighting.
    • Different printing thickness strategies (e.g., shell thickness) optimized visibility and functionality.
  • Limitations and Future Directions:

    • Printing resolution limitations: FDM printers may struggle to achieve ultra-high precision for small tags. Future work could incorporate SLA printing technology and higher-resolution cameras to increase tag density.
    • Discoverability and concealment: Users may not know the location of embedded tags. Future research could explore more effective user guidance designs or expand tag detection ranges.
    • Material diversity: Currently, only black IR PLA was used. Future work could explore a wider range of colors and material types.
    • Performance on curved surfaces: For curved objects, improvements are needed in tag detection angles and distortion handling.

Conclusion

This study demonstrates a revolutionary method combining low-cost materials and infrared technology to create invisible tags for applications in augmented reality, object recognition, and interaction. By advancing the technology, hardware, and application scope, InfraredTags has the potential to become a mainstream object tagging technology, bridging the gap between physical objects and digital interaction.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/chi/68913/2022

AdRecommended

Learn AI Coding at CodeNow

open_in_newOpen DOI Link
DOI: https://dl.acm.org/doi/abs/10.1145/3491102.3501951
At a Glance

Paper Snapshot

fact_check
dataset
Source
CHI
calendar_month
Year
2022
emoji_events
Award
No award tagged
group
Authors
7 authors
sell
Subtopics
AR Navigation & Context Awareness, 3D Modeling & Animation
work
Professions
UI/UX Designers, Makers & DIY Enthusiasts, HCI Researchers
article
Content Status
Full text indexed
hub
Related Papers
0 related papers