Detection and tracking demo recording
GitHub-hosted recording from the repository showing the Anti-UAV detection and tracking application workflow.
Computer Vision · Detection & TrackingComplete
Anti-UAV Detection
Detect, classify, and track UAVs in RGB images and video through a full computer vision workflow.
YOLOv11RT-DETRByteTrackMLflowDockerizedStreamlit appGitHub Actions
Local project explainer
Ask about this system
A local, predefined assistant for the documented details in Anti-UAV Detection.
Problem
What this project had to solve
Real-time UAV detection is not just a model-selection problem. It also needs training discipline, model comparison, tracking, and a way to inspect outputs through an actual application workflow.
Role / contribution
What I owned in the system
Project author responsible for the detection/tracking pipeline, model comparison setup, MLflow tracking, Streamlit application path, and CI/CD structure described in the repository.
Technical implementation
How the system is built
The system compares YOLOv11-S and RT-DETR-R50 while keeping training configurations organized so experiments remain reproducible.
ByteTrack is integrated so the project covers tracking behavior instead of limiting itself to frame-level detection.
MLflow, Docker, tests, and GitHub Actions push the repository toward a full MLOps workflow rather than a single-model demo.
Architecture flow
System flow from input to output
Step 01
Dataset preparation
What happens
Detection data is organized and split for repeatable training and evaluation.
Why it matters
Repeatable data splits are necessary before model comparisons and tracking results can mean anything.
Related tools
No explicit tool is called out for this step in the shared project data.
Engineering decisions
Tradeoffs that shaped the build
Compare architectures explicitly
The project keeps one-stage and transformer-based detectors in the same evaluation story instead of assuming a single model choice.
Include tracking as part of the system boundary
Tracking is treated as a product requirement rather than a separate bonus experiment.
Wrap the repo in MLOps structure
Configs, tests, MLflow, Docker, and CI/CD make the pipeline inspectable and repeatable.
Stack
Core tools and system layers
YOLOv11RT-DETRByteTrackMLflowStreamlitDockerGitHub ActionsRuffPytest
What I would improve next
Next technical upgrades
- Add broader scenario coverage beyond the current single-class framing.
- Evaluate domain adaptation paths for thermal or more difficult low-visibility footage.
- Tighten model-promotion and deployment criteria around tracked evaluation results.
Evidence