On most autumn days, David Sopjes might be discovered within the Eel River in Northwest California counting fish. As a retired highschool science trainer and citizen scientist, Sopjes has spent the final 10 years monitoring the Chinook salmon inhabitants within the Eel River, which he says has the third-largest watershed within the state. Each fall, Sopjes counts the salmon as they watch for the winter rains to breed.
“They don’t eat anymore. They’ve one factor on their thoughts, and that’s simply intercourse,” Sopjes says.
Earlier than getting a drone three years in the past, Sopjes and his colleagues counted the salmon by snorkeling within the river and standing on paddleboards, each of which tremendously disturbed the fish and weren’t very correct.
The drone produced clear images of the salmon, however counting the fish within the pictures utilizing pen and paper was tedious. Whereas scouring the web for a greater technique to rely and manage his information, he discovered a software program known as DotDotGoose and has been utilizing it ever since.
Designed on the American Museum of Pure Historical past’s Center for Biodiversity and Conservation, DotDotGoose is a free, open-source device that assists researchers with manually counting objects in pictures. Peter Ersts, the senior software program developer on the heart, created DotDotGoose in Might 2019. He received the thought by discussions with colleagues.
[Related: Alexa will tag along on an uncrewed mission to the moon]
On the time, the most well-liked methods for conservation researchers to tally up completely different classes of animals in pictures had been very hands-on. “Lots of people had been nonetheless simply actually projecting pictures onto a dry erase board, circling the animals and turning the projector off, after which counting them as they wiped [off the markings],” Ersts says. “I noticed a necessity for a very easy device that permits you to rapidly and simply put dots on a picture.”
Though the device’s solely been on-line for about two and a half years, it’s already serving to many researchers internationally. Since discovering DotDotGoose, Sopjes says he’s counted hundreds of fish, and the accuracy of his information improved “dramatically,” a lot in order that the California Division of Fish and Wildlife turned all for utilizing his datasets. The correct document of the whole fish paired with pictures from the drone offered a helpful approach for Sopjes to trace each fish.
The way it works
DotDotGoose has a quite simple interface that enables customers to import pictures they need to analyze. Then, they will divide completely different objects within the pictures into “courses” or classes. For instance, Sopjes units the courses as completely different life phases of salmon. Every class corresponds to a dot coloration.
To rely every class, researchers can click on on every object within the picture to put the dot. DotDotGoose tallies the variety of dots by class as they’re positioned. Customers can add customized notes, latitude and longitude coordinates, or different information factors to explain the picture.
DotDotGoose was initially supposed to rely animals for conservation analysis, however Ersts has seen customers repurpose it to rely stock in warehouses, elements on circuit boards, and even flowers on tomato plant entries for the Guinness World Document.
Why it’s helpful
Rochelle Thomas, a graduate pupil in Columbia College’s Division of Ecology, Evolution, and Environmental Biology, has used DotDotGoose with real-life geese.
From 1995 to 2019, Thomas’ advisor, Robert Rockwell, had taken aerial images of lesser snow goose flocks within the Hudson Bay area of Canada. Within the early years of the venture, Thomas says Rockwell would print out the images to rely the geese by hand.
When Thomas joined the venture in 2018, she tried counting the geese utilizing Photoshop, however it was arduous to rely geese concurrently by species and age. She was launched to Ersts whereas he was constructing DotDotGoose and have become this system’s beta-tester. This system’s identify is a nod to her work with lesser snow geese.
“I spent many days placing dots on geese, and it simply form of got here [to me] to name it DotDotGoose,” Ersts says.
[Related: AI turned a Rembrandt masterpiece into 5.6 terabytes of data]
In comparison with related software program, akin to Photoshop and ImageJ, Thomas likes that DotDotGoose was constructed with a conservation biologist in thoughts and permits her to tweak the standard of the picture or insert info indicating the presence of water within the photograph.
“Conservation biologists and ecologists are sitting on simply tons and tons of photographic information,” Thomas says.
And whereas the present guide model of this system already makes the info extra manageable for evaluation, she thinks that making counting in DotDotGoose extra automated might additional assist help analysis tasks like her’s.
The way forward for DotDotGoose
Ersts has had plans to semi-automate the method since its inception.
“In the event you’re capable of save these coordinates of your places on a picture, you then mainly have a coaching set that you would use [to power] a machine studying mannequin to assist automate issues sooner or later,” Ersts says. “[But] it’s fairly a difficult process to automate this if you actually begin interested by all of the various kinds of information that exists.”
Ersts imagines that researchers would possibly practice it with a few equally oriented pictures distinctive to their venture that comprise the identical varieties of objects.
However even a tailor-made, automated DotDotGoose would have its limits. Pictures with many objects bunched collectively could be very tough to parse by. And whereas an automatic model of this system might liberate researchers’ time, Ersts says a human would nonetheless should be part of the method, at the least to verify the pc’s work.