cortenforge-vision-core
| Crates.io | cortenforge-vision-core |
| lib.rs | cortenforge-vision-core |
| version | 0.6.0 |
| created_at | 2026-01-03 16:04:03.564164+00 |
| updated_at | 2026-01-14 00:52:55.898319+00 |
| description | Core vision interfaces and capture/overlay helpers for the CortenForge stack. |
| homepage | https://github.com/via-balaena/CortenForge |
| repository | https://github.com/via-balaena/CortenForge |
| max_upload_size | |
| id | 2020389 |
| size | 90,928 |
(bigmark222)
documentation
https://docs.rs/cortenforge-vision-core
README
vision_core
Vision interfaces and overlay helpers shared by sims, tools, and inference.
Contents
interfaces: Frame/DetectionResult/Label/FrameRecord; Detector/FrameSource/Recorder traits.overlay: box normalize + draw helpers.capture: CaptureLimit (max frames).prelude: re-exports interfaces, overlay helpers, CaptureLimit.
Usage
- Add
vision_coreas a dependency. - Import via
vision_core::prelude::*for interfaces/overlay helpers. - Implement
Detector/DetectorFactoryin your crate; keep heavy backends (Burn) behind feature flags outside vision_core. - Use
BurnDetectorFactoryonly if you need a feature-gated Burn loader; keep the trait implementations out of vision_core to stay lean.
License
Apache-2.0 (see LICENSE in the repo root).