VIAME
Video and Image Analytics for Multiple Environments (VIAME) is a computer vision application designed for do-it-yourself artificial intelligence including object detection, object tracking, image/video annotation, image/video search, image mosaicing, image enhancement, size measurement, multi-camera data processing, rapid model generation, and tools for the evaluation of different algorithms. Originally targetting marine species analytics, VIAME now contains many common algorithms and libraries, and is also useful as a generic computer vision toolkit. It contains a number of standalone tools for accomplishing the above, a pipeline framework which can connect C/C++, python, and matlab nodes together in a multi-threaded fashion, and multiple algorithms resting on top of the pipeline infrastructure. Lastly, a portion of the algorithms have been integrated into both desktop and web user interfaces for deployments in different types of environments, with an open annotation archive and example of the web platform available at viame.kitware.com.
Documentation Overview
This manual is synced to the VIAME “main” branch and is updated frequently, though you may have to press ctrl-F5 to see the latest updates to avoid using your browser cache of this webpage if you have used it priorly. In addition to this manual, there are 4 useful types of documentation:
A quick-start guide meant for first time users using the desktop version
An overview presentation covering the basic design of VIAME
The VIAME Web and DIVE Desktop docs and in-GUI help menu
Our YouTube video channel (work in progress)
Contents
- Documentation Overview
- Installing VIAME from Binaries
- Building VIAME From Source
- User Interfaces and Visualization
- Scripts and Example Folders
- Project Folders
- Detection File Formats and Conversions
- Object Detection Examples
- Detector Training Examples
- Size Measurement Examples
- Object Tracking Examples
- Image Enhancement and Filtering
- Video and Image Search Examples
- Rapid Model Generation
- Scoring Detectors and Trackers
- Registration and Mosaicing
- Frame Level Classification
- Archive Summarization
- Core C++/Python Object Types
- Core Pipelining Architecture
- Basic Pipeline Nodes
- New Module Creation Examples
- Plugin Creation
- KWIVER Full Manual
Example Capabilities
There are a number of core capapbilities within the software, click on each of the below images to learn more. | Object Detection
User Interfaces for Visualization and Detector Model Training
Measuring Animal Lengths Using Metadata or Stereo
Image and Video Search for Rapid Model Generation
Illumination Normalization and Color Correction
Detector and Tracker Evaluation