Why finding a place to park in Montreal just got a whole lot easier | 24CA News
It’s no secret that it may be difficult to search out authorized parking on Montreal streets. The guidelines are infinite: street cleansing schedules, permit-only stretches and site visitors lanes, to call just a few.
Standing in entrance of a pole with a number of parking restriction indicators connected to it in Old Montreal, one driver marveled at how tough it’s to grasp and rapidly summed up the complications behind discovering a secure spot.
“The stars must align,” he mentioned. “Jupiter and Saturn must align. It’s a little weird.”
But what if there was an app for that?
A Quebec firm launched a brand new AI-driven software in May to assist drivers decipher complicated parking indicators and, in the end, keep away from steep fines and having their automobiles towed away.
Underlabs got here up with the thought of Parky.ai after certainly one of its members, its chief expertise officer, was confused by an indication and got here again to discover a ticket on the windshield.
“We thought that artificial intelligence could solve this problem,” mentioned Andrei Chira, senior software program engineer at Underlabs. “So we decided to create the most simple app where you just take a picture of all the parking signs and boom — it tells you if you’re allowed to park there using artificial intelligence.”
A parking ticket is proven on a automotive in Montreal, Wednesday, April 11, 2018.
Graham Hughes/The Canadian Press
All drivers need to do is take a photograph of the parking restrictions within the app. Parky.ai then processes the picture and offers a sure or no reply on whether or not you’ll be able to safely park there or not.
How does it be taught all that? Underlabs builders took greater than 1,000 footage of various indicators to show the app learn how to decode town’s plethora of parking laws.
“Our goal was to provide an answer faster than humans would be able to read and interpret the signs for themselves,” Chira mentioned.
While the initiative is supposed to take the stress out of driving in Montreal, Parky.ai isn’t excellent. The AI-driven app remains to be studying and motorists who use it additionally assist hones its abilities.
At the second, the corporate says the present accuracy for the app is 83 per cent for single indicators and 74 per cent for a number of indicators. If the person notices a mistake, they’re inspired to flag it.
“We suggest people report inaccuracies in the app. There is a button for that because that will allow us to train the model even further,” Chira mentioned.
Parky.ai is concentrated on Montreal for now because it’s nonetheless new, however Chira says Underlabs may take their thought to different provinces down the street.
— with information from Global News’ Mike Armstrong
© 2023 Global News, a division of Corus Entertainment Inc.


