Hardware-Accelerated Pedestrian Detection and Low-Latency Video Streaming for Drone Applications
Bibliographic record
Abstract
The increasing deployment of drones in public security and surveillance necessitates real-time, efficient aerial pedestrian detection and low-latency video transmission technologies. In this work, we present a real-time, hardwareaccelerated system for aerial pedestrian detection and lowlatency video streaming, specifically designed for resourceconstrained edge devices. To address the challenges of aerialview person recognition, we augment an existing person reidentification benchmark with dense urban imagery and diverse image transformations, and subsequently enhance a popular object detection framework by training it on this combined dataset. The optimized model is converted to a standard format, further optimized for efficiency, and deployed onto a specialized chip integrating a multi-core processor, AI accelerator, and graphics engine. Through hardware-aware optimizations, the model size is significantly reduced with minimal accuracy loss, enabling real-time processing and efficient video encoding. Additionally, we develop a streaming pipeline incorporating adaptive techniques to ensure robust performance under fluctuating network conditions, achieving ultra-low latency. Experimental results demonstrate that our system outperforms several existing methods in accuracy, inference speed, and resource utilization.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".