This simple software makes the work of ecologists easier

Most fall days, David Sopjes can be found in the Eel River in northwestern California, counting fish. As a retired high school science teacher and citizen scientist, Sopjes has spent the past 10 years monitoring the Chinook salmon population in the Eel River, which he says has the third-largest watershed in the state. . Every autumn, Sopjes counts the salmon while waiting for the winter rains to spawn.

“They don’t eat anymore. They only have one thing on their mind, and that’s just sex,” says Sopjes.

Before acquiring a drone three years ago, Sopjes and his colleagues counted salmon by diving into the river and standing on paddle boards, which greatly disturbed the fish and was not very accurate.

The drone produced clear photographs of the salmon, but counting the fish in the images using pen and paper was tedious. While scouring the internet for a better way to count and organize his data, he found software called PointPointGoose and have been using it ever since.

Designed at the American Museum of Natural History Center for Biodiversity and Conservation, DotDotGoose is a free, open-source tool that helps researchers manually count objects in images. Peter Ersts, the center’s senior software developer, created DotDotGoose in May 2019. He came up with the idea through discussions with colleagues.

[Related: Alexa will tag along on an uncrewed mission to the moon]

At the time, the most popular ways for conservation researchers to account for different categories of animals in photos were very convenient. “A lot of people were still literally projecting images onto a dry-erase board, circling the animals and turning off the projector, then counting them as they wiped [off the markings]says Ersts. “I saw the need for a really simple tool that allowed you to quickly and easily put dots on an image.”

Although the tool has only been online for about two and a half years, it is already helping many researchers around the world. Since finding DotDotGoose, Sopjes says he’s counted thousands of fish and the accuracy of his data has improved “significantly,” so much so that the California Department of Fish and Wildlife is interested in using its datasets. Accurately recording the total number of fish associated with drone footage has provided Sopjes with a useful way to track each fish.

DotDotGoose allows users to customize the interface to suit their needs. David Sopjes

How it works

DotDotGoose has a very simple interface that allows users to import images they wish to analyze. Then they can divide different objects in the images into “classes” or categories. For example, Sopjes defines classes as different life stages of salmon. Each category corresponds to a point color.

To count each class, researchers can click on each object in the image to place the dot. DotDotGoose counts the number of dots per class as they are placed. Users can add custom notes, latitude and longitude coordinates, or other data points to describe the image.

DotDotGoose was originally intended to count animals for conservation research, but Ersts has seen users repurpose it to count inventory in warehouses, components on circuit boards, and even flowers on candidate tomato plants. at the Guinness World Record.

Why it’s useful

Rochelle Thomas, a graduate student in the Department of Ecology, Evolution, and Environmental Biology at Columbia University, used DotDotGoose with real geese.

From 1995 to 2019, Thomas’ advisor Robert Rockwell had taken aerial photographs of flocks of lesser snow geese in the Hudson Bay region of Canada. In the early years of the project, Thomas says Rockwell printed the photographs to count the geese by hand.

When Thomas joined the project in 2018, she tried to count the geese using Photoshop, but it was hard to count geese simultaneously by species and age. She was introduced to Ersts while he was building DotDotGoose and became the program’s beta tester. The name of the program is a nod to its work with lesser snow geese.

“I spent several days stitching the geese, and it just came [to me] to call it DotDotGoose,” says Ersts.

[Related: AI turned a Rembrandt masterpiece into 5.6 terabytes of data]

Compared to similar software, such as Photoshop and ImageJ, Thomas likes that DotDotGoose was designed for a conservation biologist and allows him to modify the image quality or insert information indicating the presence of water on the picture.

“Conservation biologists and ecologists are sitting on tons and tons of photographic data,” says Thomas.

And while the current manual version of the program already makes data easier to manage for analysis, she thinks making counting in DotDotGoose more automated could help further support research projects like hers.

The future of DotDotGoose

Ersts has planned to semi-automate the process since its inception.

“If you are able to record these coordinates of your locations on an image, then you have a training set that you can use [to power] a machine learning model to help automate things in the future,” says Ersts. “[But] it’s quite a difficult task to automate this when you really start to think about all the different types of data that exist.

Ersts imagines the researchers could train him with a few similarly oriented photos unique to their project that contain the same types of objects.

But even an automated, personalized DotDotGoose would have its limitations. Images with many objects grouped together would be very difficult to analyze. And while an automated version of the program could free up time for researchers, Ersts says a human should still be part of the process, at least to check the computer’s work.

Comments are closed.