An Open Source Framework for Video and Image Processing
In cooperation with NOAA’s Automated Image Analysis Strategic Initiative (AIASI), Kitware and it’s partners have developed VIAME (Video and Image Analytics for Marine Environments), an open-source system for analysis of video and imagery for fisheries stock assessment and a variety of other applications. VIAME contains a number of different workflows for the generation of different object detectors, full frame classifiers, image mosaics, and methods for stereo measurement. Both a desktop and web version exists for deployments in different types of environments.
Installers and Documentation
- Desktop Software Installers: Downloadable software installers (pre-built binaries)
- Quick-Start Guide: Introductory user manual
- Tutorial Videos: Videos covering basic functionality (work in progress)
- Web Annotator and Data: Public online web video/image annotator and training data
- 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)
- 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
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...
The fully-annotated data for training detectors is now available. You can download the data or learn more about the data format.