Related Experiment Video
Updated: Jun 15, 2026
10:25
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
Published on: September 2, 2025
Real-time detection and tracking for augmented reality on mobile phones.
Daniel Wagner1, Gerhard Reitmayr, Alessandro Mulloni
1Graz University of Technology, Graz, Austria. wagner@icg.tugraz.at
IEEE Transactions on Visualization and Computer Graphics
|March 13, 2010
Summary
This paper introduces three real-time 6DOF natural feature tracking techniques for mobile phones. Optimized SIFT and Ferns descriptors with template tracking achieve 30 Hz for augmented reality applications.
Area of Science:
- Computer Vision
- Mobile Computing
Background:
- Real-time 6DOF (six degrees of freedom) natural feature tracking is crucial for mobile augmented reality (AR).
- Existing state-of-the-art feature descriptors like SIFT (Scale-Invariant Feature Transform) and Ferns are computationally expensive or memory-intensive, limiting their use on mobile devices.
Framework:
- This research presents modified SIFT and Ferns feature descriptors optimized for mobile platforms.
- A template-matching-based tracker is integrated to enhance the performance and robustness of the feature tracking system.
Implementation:
- The paper details modifications to SIFT and Ferns to overcome computational and memory constraints on mobile phones.
- The combined approach achieves interactive frame rates of up to 30 Hz for tracking textured planar targets.
Implications:
- The developed techniques enable efficient and robust 6DOF natural feature tracking on current mobile phones.
- This advancement has significant potential for enhancing mobile AR experiences and applications.
