Localization and spatially anchoring objects of an augmented reality headset using an onboard fisheye lens
Bibliographic record
Abstract
The development of improved Augmented Reality (AR) Head-Mounted Devices (HMDs) have led to increasing use cases for AR applications. In the case of surgery, an HMD can be used as an assistive tool to help surgeons operate. With a triplanar surgical navigation system as an industry standard, the use of an HMD can improve the surgeon’s comfort, and overall experience. An HMD can offer the surgeon a consistent flow of information in front of their eyes with medically relevant images, such as craniospinal computed tomography (CT) data that can be displayed as they operate. This paper aims to bring an HMD-based overlay framework that can be used in the operating room. With a combination of Android Studio, OpenCV, and OpenGL, an inside-out localization method with Aruco Markers is demonstrated. The framework estimates the head pose of the user and subsequently renders a patient specific CT scan that will be spatially anchored to the real world. The CT reconstruction can then be virtually superimposed onto the physical patient. The HMD’s (ODG R9) fisheye lens will also be used to enhance and enable a larger field of view for better object detection. This paper also introduces a “focus mode” that improves the localization accuracy. The framework will be evaluated in each of the 3-axes for translational and rotational movement error. It will be evaluated on the detection accuracy of different numbers of markers and at different distances. It will also be evaluated using an ultra-high definition (UHD) camera.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".