EventCV

“OpenCV for event-based vision.” EventCV pairs a fast Rust core (eventcv-core) with a NumPy-friendly Python API for loading, transforming, and representing event-camera data.

• Read any common format — .npz, .txt/.csv, ROS .bag, .hdf5, .aedat (AEDAT 2.0), and Prophesee .dat — through one eventcv.load().

• Stream multi-gigabyte recordings without loading them whole via eventcv.open(), with on-disk indexed slicing.

• Transform streams with chainable, functional geometry / temporal / polarity ops.

• Represent events as dense tensors (voxel grids, time surfaces, count images, …) ready for NumPy and PyTorch.

• Call it your way — every operation is available both as a method (stream.voxel()) and as an OpenCV-style free function (eventcv.voxel(stream)).

Contents

• Quickstart
  • Load a recording
  • Transform (chainable, functional)
  • Represent as a dense tensor
  • Stream a large file
  • Save
• Representations
  • Summary
  • Polarity
  • Binary
  • Count
  • Voxel grid
  • Time surface (tsurf)
  • Averaged time surface (atsurf)
  • Tencode
  • MCTS (multi-channel time surface)
  • Optical flow
  • Sparse point set
  • Connected-component labels
  • By name
• Tutorials
  • Getting started
  • Transforms & representations
  • Streaming large files
• API Reference
  • Loading & saving
  • Core types
  • Functional (OpenCV-style) API

Installation

pip install eventcv

The wheel bundles its own libhdf5, so .h5/.hdf5 support works with no extra installs. The Rust core’s API is documented separately on docs.rs.