KWIVER is a collection of software tools designed to tackle challenging image and video analysis problems and other related challenges. Significant features of KWIVER are:

  • Written in C++ and runs on Windows, Linux, and Mac OSX
  • Supports integrating modules from other open-source vision projects such as OpenCV and VxL
  • Pipeline architecture enables modular algorithmic implementation, including support for alternate development languages such as Python
    and MATLAB
  • Application scaling from a single research desktop using file-based I/O up to multi-node cluster with database backends, via
    synchonization and data abstraction frameworks
  • Metrics framework enabling experimental reproducibility by integrating evaluation into the workflow
  • State-of-the-art visualization tools for video exploitation, allowing geopsatial compositing of algorithmic results with imagery
    and map data