MAPPING QUALITY EVALUATION OF MONOCULAR SLAM SOLUTIONS FOR MICRO AERIAL VEHICLES
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract. Monocular simultaneous localization and mapping (SLAM) attracted much attention in the mobile-robotics domain over the past decades along with the advancements of small-format, consumer-grade digital cameras. This is especially the case for micro air vehicles (MAV) due to their payload and power limitations. The quality of global 3D reconstruction by SLAM solutions is a critical factor in occupancy-grid mapping, obstacle avoidance, and map representation. Although several benchmarks have been created in the past to evaluate the quality of vision-based localization and trajectory-estimation, the quality of mapping products has been rarely studied. This paper evaluates the quality of three state-of-the-art open-source monocular SLAM solutions including LSD-SLAM, ORB-SLAM, and LDSO in terms of the geometric accuracy of the global mapping. Since there is no ground-truth information of the testing environment in existing visual SLAM benchmark datasets (e.g., EuRoC, TUM, and KITTI), an evaluation dataset using a quadcopter and a terrestrial laser scanner is created in this work. The dataset is composed of the image data extracted from the recorded videos by flying a drone in the test environment and the high-fidelity point clouds of the test area acquired by a terrestrial laser scanner as the ground truth reference. The mapping quality evaluation of the three SLAM algorithms was mainly conducted on geometric accuracy comparisons by calculating the deviation distance between each SLAM-derived point clouds and the laser-scanned reference. The mapping quality was also discussed with respect to their noise levels as well as further applications.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it