Skip to main content

edge_vision_core 0.1.0 copy "edge_vision_core: ^0.1.0" to clipboard
edge_vision_core: ^0.1.0 copied to clipboard

Deterministic C++17 image & camera frame preprocessor, EXIF orienter, letterbox resizer, tensor normalizer, and YOLO postprocessor for Flutter Edge AI.

0.1.0 #

  • Initial release of edge_vision_core.
  • Shared C++17 core (src/edge_vision_core.cpp, src/exif.cpp) with a clean extern "C" ABI (src/edge_vision_core.h) reusable across Flutter, React Native, and Python.
  • Built-in JPEG APP1 TIFF/IFD0 EXIF orientation parser (1..8, little-endian and big-endian) and physical pixel rotation/flip normalization.
  • Deterministic letterbox (114 padding), stretch, and centerCrop resizing across Android, iOS, Windows, macOS, and Linux.
  • Single-pass RGB/BGR, NCHW/NHWC, scale/mean/stdDev float32 tensor normalization with presets for YOLO, ImageNet, and CLIP.
  • Live camera YUV420 / NV12 / NV21 deterministic BT.601 conversion with clockwise sensor rotation (0, 90, 180, 270).
  • EXIF-free resized JPEG encoding (resizeAndEncodeJpeg) for deterministic cloud VLM / LLM Vision upload reduction.
  • Native YOLO post-processor (postprocessYolo) supporting both classic [1, 4 + C, N] (with class-aware Greedy NMS) and end-to-end NMS-free [1, N, 6] (YOLO26 / YOLOv10) outputs, automatically unscaling boxes back to oriented source coordinates.
  • Thread-safe serialized Dart FFI queue and background Isolate.run helper (preprocessInIsolate).
1
likes
160
points
69
downloads

Documentation

API reference

Publisher

unverified uploader

Weekly Downloads

Deterministic C++17 image & camera frame preprocessor, EXIF orienter, letterbox resizer, tensor normalizer, and YOLO postprocessor for Flutter Edge AI.

Repository (GitHub)
View/report issues

Topics

#ai #computer-vision #yolo #image-processing #ffi

License

MIT (license)

Dependencies

ffi, flutter

More

Packages that depend on edge_vision_core

Packages that implement edge_vision_core