Lightweight Real-Time Drone Detection and Trajectory Forecasting Using YOLOv8 and LSTM Networks
Bibliographic record
Abstract
Unmanned aerial vehicles (UAVs) are becoming increasingly used across civilian and defense sectors, creating a growing demand for systems that can detect and anticipate their movements with minimal delay. In this work, we propose a compact deep learning framework that unites YOLOv8n for drone detection with a Long Short-Term Memory (LSTM) network for trajectory forecasting. The detector identifies drones accurately in each frame, and the LSTM predicts their upcoming positions by learning motion patterns from recent observations. This combination enables early response to aerial intrusions rather than the usual frame-by-frame tracking approach. Our experiments on a drone-specific dataset indicate that the model reaches a mean average precision close to 0.89 and processes around nine frames per second on a standard CPU setup. These outcomes suggest that the system can provide reliable detection and trajectory prediction even on limited hardware, making it practical for field applications like airspace security and surveillance. The lightweight design ensures operational feasibility on low-power platforms, enabling realtime performance without reliance on high-end computing resources
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 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".