Visual SLAM with a Multi-Modal Semantic Framework for the Visually Impaired Navigation-Aided Device
Bibliographic record
Abstract
Visual Simultaneous Localization and Mapping (VSLAM) based on image feature points often contains feature points on non-stationary objects in dynamic scenes, resulting in poor localization performance. Recent research has improved VSLAM performance by removing dynamic feature points utilizing optical flow, deep learning, or multi-view geometry, however, the volume of data makes real-time operation challenging. In this study, we propose a multimodal framework for semantic VSLAM. To eliminate dynamic feature points, the system effectively blends object detection, instance segmentation, and geometry modules. To ensure high-precision pose estimation and quick back-end optimization, we exclusively use object detection in the front-end of VSLAM to mask dynamic feature points. In the keyframes of the local map, semantic segmentation is utilized to remove dynamic feature points, and an effective geometric module is employed to assess the dynamic consistency of objects that are challenging to categorize. Therefore, more feature points are retained, and the running speed is also ensured. Evaluations of the system on public datasets and in the real world show that it improves the accuracy and stability of VSLAM in dynamic environments.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".