NASA Vision Workbench

NASA Vision Workbench is a C++ image processing and machine vision library.

The Vision Workbench has been used within NASA for a wide range of image processing tasks, including alignment and stitching of panoramic images, high-dynamic-range imaging, texture analysis and recognition, lunar and planetary map generation, and the production of 3D models from stereo image pairs.

NASA Vision Workbench was designed to support a variety of space exploration tasks, including automated science and engineering analysis, robot perception, and 2D/3D environment reconstruction, though it can also serve as a general-purpose image processing and machine vision framework in other contexts as well.

It is specifically designed for image processing in the context of machine vision.

Features include:

• Solid efficient foundation
• 'Lazy' computation model
• Scalable support for block-level operations on images
• Easy to understand end-user syntax
• Modules:
• Camera
• pinhole and linescan camera models
• EXIF metadata parsing
• bayer filter decoding
• Cartography
• transformation between map projections
• geo-referenced file IO (GeoTIFF, etc)
• Core
• exception handling
• debugging support
• type system support
• cache support
• FileIO
  • reading and writing JPEG, PNG, TIFF, PDS, OpenEXR files (requires 3rd party libraries)
  • image paging support for large files
• HDR
  • high dynamic range image creation from bracketed low dynamic range exposures
  • camera response curve estimation
  • global and local tone mapping operators
• Image
  • convolution — convolve images with linear filters
  • algebra — image addition, subtraction, and multiplication by a scalar
  • math — perform per pixel math operations on images (e.g., abs, hypot, sqrt, pow, exp, log, sin, cos, asin, acos, atan2, etc.)
  • transformations — translation, rotation, scale, resampling, arbitrary warps
  • image statistics
• Math
  • vector, matrix, quaternion and linear algebra (interface to LAPACK)
  • optimization — levenberg-Marquardt, conjugate gradient
  • homographies — estimation of relations between geometric entities
  • bounding boxes — Determination of geometric extent
• Mosaic
  • assembling large image composites from many source images
  • multi-band blending
  • generating on-disk quad-tree representations of extremely large images
• Stereo
  • correlating stereo pairs of images
  • stereo camera models for 3D reconstruction
  • outlier rejection

Return to Robotics Home Page

Last Updated Saturday, April 13 2013 @ 04:40 PM EDT