OpenEM: Open Source Electronic Monitoring Library

OpenEM is a library that provides advanced video analytics for fisheries electronic monitoring (EM) data. It currently supports detection, classification, counting and measurement of fish during landing or discard. This functionality is available via a deployment library with pretrained models available in our example data (see tutorial). The base library is written in C++, with bindings available for both Python and C#. Examples are included for all three languages.

The current release also includes a training library for the all OpenEM functionality. The library is distributed as a native Windows library and as a Docker image.

Watch the video below to see a video of OpenEM in action:

Change Log

Version Date Description of changes
0.1.4 XXX-2020
  • Add support and scripts for Tator support
  • Make image models multi-process capable
  • Documentation improvements
0.1.3 Jan-2020
  • Add RetinaNet based detector
  • Add pure python inference library
  • Deprecate C++ library
  • Alpha support for Xavier-based platforms
0.1.2 June-2019
  • Docker image cleanups
  • Add Improved documentation
0.1.1 Feb-2019
  • Fix training in Docker
0.1.0 Jan-2019
  • First stable release
  • Training/Inference examples

Indices and tables