Skip to main content

Ad

technology-iconTechnology
clock-iconPUBLISHEDMarch 29, 2021
comments icon1

YouTuber Creates Roadside AI-Powered Camera To Compliment Dogs That Pass By

Jack Dunhill headshot

Jack Dunhill

Jack Dunhill headshot

Jack Dunhill

Social Media Coordinator and Staff Writer

Jack has a degree in Medical Genetics from the University of Leicester.

Social Media Coordinator and Staff Writer

Jack has a degree in Medical Genetics from the University of Leicester.View full profile

Jack has a degree in Medical Genetics from the University of Leicester.

View full profile
article image

Welsh corgi that requires no owner for walks. Image Credit: Jus_Ol/Shutterstock.com


Every dog is the best dog. It doesn’t matter whose dog they are, what breed, or how well-behaved they are, they are all good dogs. But do you ever wish that you could tell the dogs how amazing they are, constantly? 

The rest of this article is behind a paywall. Please sign in or subscribe to access the full content.

Fear not, as YouTuber Ryder Calm Down has the answer. Using a megaphone, a camera, and a smart integrated machine-learning system, the nifty technology and comedy commentator created a device that recognizes dogs as they walk down the street and shouts compliments to them. After all, they deserve it. 

Titled "The dog detector to make me feel better", Ryder designed the machine to help "increase his dopamine" and for his friend Heather, who appears to be quite the fan of people’s best friend. 

Ryder explains the creation of the device and demonstrates it in action. Video Credit: Ryder Calm Down

The creation began with a Raspberry Pi, which is a miniature computer popular among tinkerers and programmers for its crazy customization and cheap price. With some programming prowess, the Raspberry Pi will be able to run any algorithms Ryder wishes. Hooking it up to a live-streaming camera, the entire system then runs through a machine-learning model to identify any wandering pups. 

The difficult part of the system lies in the detection of dogs without any control by a human. To do this, Ryder uses the YOLOv3 Object Detection Model. Much like other machine learning models, YOLOv3 is the product of software developers sifting through swathes of pictures, highlighting different objects, and telling the model what each is. For example, a picture of a kitchen might have "kettle", "microwave", "oven" and more highlighted to the model. Once these are identified, the model will then slowly learn to identify these objects without help. 

This model is also extremely fast, and able to be altered depending on your needs, making it perfect for running on a small system like the Raspberry Pi.  

Once the identification system was up and rocking, the next step was to add a notification system to ensure Ryder was able to enjoy the passing dogs. This wasn’t enough for Ryder, however – when he wasn’t home, he felt like the dogs still needed appreciation. Turning the megaphone round, Ryder hooked the system up to some preset messages to yell appreciation at the dogs and owners, such as "I like your dog!". 

While it’s understandable some may find the messages a little unsettling, everyone in the video seems to have good fun. However, as one commenter points out, maybe it would be better if it could launch treats for the dogs – food for thought, Ryder. 

[H/T: Gizmodo]


Written by 

Add us as a Google preferred source to see more of our
trusted coverage in Search