Getting computers to recognize objects has been a historically difficult problem in computer science, but with the rise of machine learning it is becoming easier to solve. One of the tools that can be put to work in object recognition is an open source library called TensorFlow, which [Evan] aka [Edje Electronics] has put to work for exactly this purpose.
His object recognition software runs on a Raspberry Pi equipped with a webcam, and also makes use of Open CV. [Evan] notes that this opens up a lot of creative low-cost detection applications for the Pi, such as setting up a camera that detects when a pet is waiting at the door to be let inside or outside, counting the number of bees entering and exiting a beehive, or monitoring parking spaces at an office.
This project uses a number of other toolkits as well, including Protobuf. It also makes extensive use of Python scripts, but if you’re comfortable with that and you have an application for computer vision, [Evan]’s tutorial will get you started.
Continue reading “Object Detection, With TensorFlow”
The only useful data you’ll ever find is already digitized, but a surprising number of gauges and meters are still analog. The correct solution to digitizing various pressure gauges, electric meters, and any other analog gauge is obviously to replace the offending dial with a digital sensor and display. This isn’t always possible, so for [Egar] and [ivodopiviz]’s Hackaday Prize entry, they’re coming up with a way to convert these old analog gauges to digital using a Raspberry Pi and a bit of computer vision.
The idea behind this instrument digitizer isn’t to replace the mechanics and electronics, as we are so often wont to do. Instead, this team is using a 3D printed bracket that mounts a Raspberry Pi and camera directly in front of an analog gauge. Combine this contraption with OpenCV, and you have a device that’s just smart enough to look at a needle on a dial, convert that to a number, and save it to a file or send it out over WiFi.
It’s an extremely simple device for what [Egar] and [ivodopiviz] admit is a relatively niche application. However, if you only need digital measurements of an analog meter for a month or so, or you don’t want to mess up your steampunk decor, it’s an ingenious build.
The creation you see above is the work of art student [Daniel Bertner] who is wrapping up his Bachelor of Fine Arts degree at the School of the Art Institute of Chicago. He calls the incredibly intriguing, yet somewhat disturbing device “TIM”, which is short for Tracking Interactive Mechanism.
A culmination of different projects he has tinkered with over the last year or so, TIM is an interactive delta bot with an attitude. Mounted on the wall of the Art Institute’s Sullivan Galleries, TIM is as interested in you as you are in it. While passers by investigate the curious device, it watches them back, following their every movement.
The robot’s motors are controlled using an Arduino, and its ability to track people standing nearby is provided via a video stream processed with Open CV.
It really is a cool project, and we think it would make for an awesome prop in some sci-fi horror flick. Check out the video below to see TIM’s personality in action – he doesn’t like it when people stand too close!
Continue reading “Creepy Delta Bot Follows Your Every Move”