LabeloxAV
A data engine for autonomous driving, built for Indian roads. Raw fleet footage in, governed labels and retrained models out, with a confidence gate between the machine and the ground truth.
The classes global datasets never saw
Open autonomous-driving datasets were collected on roads that are lane-marked, largely rule-following, and populated by a short list of vehicle types. An ontology trained on them has no category for an autorickshaw, no prior for cattle on the carriageway, and nothing sensible to say about an overloaded two-wheeler, a hand cart, or a pothole deep enough to matter.
The usual answer is to label more data. That runs into the second problem: at fleet scale, most footage is redundant. Labelling it uniformly spends the budget on the ordinary and starves the rare-and-risky moments that actually move the model.
A closed loop, not a labelling queue
Machine labels come from a three-path fusion pipeline rather than a single detector. Every label then passes a calibrated confidence gate that decides what a human ever sees: high-confidence labels flow through, uncertain ones are routed to review. Active learning mines the rare and risky moments out of the remaining footage, and the models retrain on what came back. The loop is governed: one ontology, versioned classes, and an audit trail behind every export.
Install and constraints
| Property | Detail |
|---|---|
| Install | One command on any machine with Docker: generates secrets, migrates the schema, seeds the ontology, creates the first admin, prints the token |
| Ontology | One ontology, 178 governed classes |
| No GPU needed | Annotation, review, governance, export and search all work without CUDA |
| Failure mode | The model paths that need CUDA refuse rather than fabricate |
| Console | Web console at localhost:3000 |
| Deployment | GPU, TLS and backups documented separately |
The rest of the pipeline
- DriveLab: desktop workbench for dashcam footage: GPS telemetry extraction, domain-gap evaluation on Indian roads, annotation and fine-tuning, privacy-blurred Mapillary export. Part of LabeloxAV.
- RabbitAV: the on-device end: a windshield phone doing forward collision warning and IMU-plus-vision road hazard mapping, floor device class 3-4 GB RAM with CPU-only INT8 inference.
- Orvex: the ingest side: telemetry extraction, calibration, synchronization and dataset assembly from GoPro, Insta360 and Android recordings.