The American Museum of Natural History’s Center for Biodiversity and Conservation (CBC) has released an open source tool to assist with manually counting objects in images called DotDotGoose. This purpose-built tool was created since most conservation researchers and practitioners working on counting objects in images were using software such as Adobe Photoshop and ImageJ which are not ideally suited for many conservation applications.
The DotDotGoose user interface makes it easy to create and edit classes of objects to be counted and you can pan and zoom to accurately place points to identify individual objects.
Information about objects can be stored in custom fields and this metadata can be exported for use in spreadsheet or statistics software. Point data collected with DotDotGoose will be very valuable validation data for any future efforts with computer-assisted counting.
Download DotDotGoosge from
https://biodiversityinformatics.amnh.org/open_…/dotdotgoose/ or it can be accessed directly on GitHub : https://github.com/persts/DotDotGoose.
If you have any questions about DotDotGoose please contact Peter Ersts: ersts@amnh.org
For more information on the CBCs Machine Learning for Conservation initiative visit,
https://www.amnh.org/…/re…/machine-learning-for-conservation