An Open Source Framework for Underwater Image Processing
Video and Image Analytics for Marine Environments
In cooperation with NOAA’s Automated Image Analysis Strategic Initiative (AIASI), Kitware and it’s partners have developed VIAME, an open-source system for analysis of video and imagery for fisheries stock assessment. VIAME contains a number of different workflows for the generation of different object detectors, full frame classifiers, image mosaics, and methods for stereo measurement.
Installers and Documentation
- Software Installers: Downloadable software installers (pre-built binaries)
- Quick-Start Guide: Introductory user manual
- Tutorial Videos: Videos covering basic functionality
- VIAME Developer’s Manual: More comprehensive guide covering building from source and integration
- CVPR Training Data Release: Training and testing data released for the CVPR challenge (2018), will be updated shortly
- VIAME Design Overview: Overview covering VIAME’s goals and design
- NOAA Data Overview: Overview of relevant NOAA collection platforms datasets
- Open Source basis fosters easy collaboration and transparent development for the widest possible community involvement.
- Multiple Baseline Algorithms allows users to train detector, classification, and size estimation models based on varying amounts of training data.
- Modular Dataflow Architecture enables straightforward integration of a wide variety of third party analytics, libraries and tools. The Kitware Video and Image Exploitation and Retrieval toolkit, which includes a pipelined image processing framework, baseline algorithms, and wrappers around algorithms from the broader computer vision community, allows user to connect C++, Python, and Matlab processing nodes into distributed pipelines.
- Github Project Page Project development
- VIAME Blog Announcements and News
- Mailing List VIAME Discussion
Due to the delays in rolling out the challenge data, we have extended the submission deadline from May 16 until May 23. The competition results will now be announced on May 30. For information about submissions, please see the previous blog post.
The submission server is now open and accepting submissions. Please see our Submission Guidelines page for information about properly formatting your submission and a step-by-step process of completing a submission.
We're excited to announce that the challenge data is now available for download. The challenge data is structured similarly to the imagery released in the previous training data phase, with folders consisting of imagery for a particular data set. You should submit one...