Visual Heading Estimation for UAVs in Indoor Environments
Bibliographic record
Abstract
Recently, The UAV (Unmanned Aerial Vehicle) industry is getting a lot of attention, especially for very small drones that could fly indoors. Such a small drone can help perform rescue tasks such as investigating gas leaks or emergency situation that imposes risk on human intervention. Additionally, the UAVs can be utilized for indoor inspection and 3D mapping. The indoor environment is very challenging for the UAVs since the Global Navigation Satellite System (GNSS) cannot be reliably accessed to help UAV to locate itself. Various sensors could be mounted on UAVs to help the surveillance and navigation aspects of the operation. Range sensors such as 2D Lasers and LIDAR are very useful for providing valuable measurements towards reliable localization algorithms. Including such sensors will typically raise the system cost and limit the flight time due to increased power consumption. This research aims to assess the potential of using the typically installed UAV main camera to help estimate the UAV heading. The typical indoor environment includes many challenging situations such as monochrome surfaces and identical repeated patterns, especially in the ground surface. The research investigates the performance of different heading estimation approaches using a minimum cost configuration (without laser scanners). The proposed integration between the drone forward camera and the downward camera enhanced the navigation result compared to the other individual solutions using the downward camera only, forward camera only, or magnetometer. The performance of the investigated approaches in a real indoor flight is presented and discussed.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".