Efficient Edge Computing Device for Traffic Monitoring Using Deep Learning Detectors
Bibliographic record
Abstract
This article presents a smart camera device for traffic monitoring at intersections. The device is based on the Nvidia Jetson Nano, a small form factor, efficient artificial intelligence (AI) computational device that is capable of deep learning inference. The state-of-the-art deep learning detection models were investigated, and the full YOLOv4 was selected for deployment on the edge device. The deployed model and analytics achieved an average frame rate of 7.8 frames/s (fps). A fisheye lens and camera were selected and integrated with the Jetson processing unit. The original YOLOv4 performed less optimally on fisheye-distorted images. Therefore, we applied transfer learning to the YOLOv4 model using data collected from a local intersection. The final models were evaluated in three different use cases detecting different types of road objects, achieving 100% precision and around 90% accuracy when detecting road vehicles in real time. This article demonstrates the feasibility of running large deep learning models for traffic monitoring services, even on resource-restrained AI edge devices.
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.002 |
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".