https://github.com/kitware/dive

Media annotation and analysis tools for web and desktop. Get started at https://viame.kitware.com
https://github.com/kitware/dive

annotation computer-vision docker image-annotation machine-learning marine-biology object-detection video video-analytics video-annotation

Last synced: 3 days ago
JSON representation

Media annotation and analysis tools for web and desktop. Get started at https://viame.kitware.com

• Host: GitHub
• URL: https://github.com/kitware/dive
• Owner: Kitware
• License: apache-2.0
• Created: 2019-11-01T19:03:12.000Z (about 5 years ago)
• Default Branch: main
• Last Pushed: 2024-12-15T11:27:34.000Z (16 days ago)
• Last Synced: 2024-12-21T16:15:15.887Z (10 days ago)
• Topics: annotation, computer-vision, docker, image-annotation, machine-learning, marine-biology, object-detection, video, video-analytics, video-annotation
• Language: Vue
• Homepage: https://kitware.github.io/dive
• Size: 65.1 MB
• Stars: 83
• Watchers: 10
• Forks: 21
• Open Issues: 166
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Support: docs/Support.md

Awesome Lists containing this project

README

        


DIVE is a web interface for performing data management, video annotation, and running a portion of the algorithms stored within the [VIAME](https://github.com/VIAME/VIAME) repository. When compiled, docker instances for DIVE can be run either as local servers or online in web services. A sample instance of DIVE is running on a public server at [viame.kitware.com](https://viame.kitware.com).

![docs/images/Banner.png](docs/images/Banner.png)

## Features

* video annotation

* still image (and image sequence) annotation

* deep integration with [VIAME](https://github.com/VIAME/VIAME) computer vision analysis tools

* single-frame boxes, polygons, and lines

* multi-frame bounding box tracks with interpolation

* Automatic transcoding to support most video formats

* Customizable labeling with text, numeric, multiple-choice attributes

## Documentation

* [Client User Guide](https://kitware.github.io/dive/)

* [Client Development Docs](client/README.md)

* [Server Development Docs](server/README.md)

* [Deployment Overview](https://kitware.github.io/dive/Deployment-Overview/)

* [Running with Docker Compose](https://kitware.github.io/dive/Deployment-Docker-Compose/)

## Technologies Used

DIVE uses [Girder](https://girder.readthedocs.io/en/stable/) for data management and has a typical girder + girder worker + docker architecture.  See docker scripts for additional details.

* The client application is a standard [@vue/cli](https://cli.vuejs.org/) application.

* The job runner is built on celery and [Girder Worker](https://girder-worker.readthedocs.io/en/latest/).  Command-line executables for VIAME and FFmpeg are built inside the worker docker image.

## Example Data

### Input

DIVE takes two different kinds of input data, either a video file (e.g. .mpg) or an image sequence. Both types can

be optionally accompanied with a CSV file containing video annotations. Example input sequences are available at

https://viame.kitware.com/girder#collections.

### Output

When running an algorithmic pipelines or performing manual video annotation (and saving the annotations with the save

button) output CSV files are produced containing output detections. Simultaneously a detection plot of results

is shown underneath each video sequence.