Image Recognition On 0.35 Watts

Much of the expense of developing AI models, and much of the recent backlash to said models, stems from the massive amount of power they tend to consume. If you’re willing to sacrifice some ability and accuracy, however, you can get ever-more-decent results from minimal hardware – a tradeoff taken by the Grove Vision AI board, which runs image recognition in near-real time on only 0.35 Watts.

The heart of the board is a WiseEye processor, which combines two ARM Cortex M55 CPUs and an Ethos U55 NPU, which handles AI acceleration. The board connects to a camera module and a host device, such as another microcontroller or a more powerful computer. When the host device sends the signal, the Grove board takes a picture, runs image recognition on it, and sends the results back to the host computer. A library makes signaling over I2C convenient, but in this example [Jaryd] used a UART.

To let it run on such low-power hardware, the image recognition model needs some limits; it can run YOLO8, but it can only recognize one object, runs at a reduced resolution of 192×192, and has to be quantized down to INT8. Within those limits, though, the performance is impressive: 20-30 fps, good accuracy, and as [Jaryd] points out, less power consumption than a single key on a typical RGB-backlit keyboard. If you want another model, there are quite a few available, though apparently of varying quality. If all else fails, you can always train your own.

Continue reading “Image Recognition On 0.35 Watts”

Smart Lamp Keeps Students On Track With Image Recognition

It’s a common enough problem: you’re hitting the books, your phone dings with a notification, and suddenly it’s three hours later. While you’ve done lots of scrolling, you didn’t do any studying. If only there were a quick, easy project that would keep an eye on you and provide a subtle nudge to get you off the phone. [Makestreme] has that project, an AI study lamp that shifts from warm white to an angry red to remind students to get back to work. See it in action in the demo video below.

Continue reading “Smart Lamp Keeps Students On Track With Image Recognition”

Making A Kit-Kat Clock Even Creepier

If there’s anything as American as baseball and apple pie, it’s gotta be the Kit-Kat clock in the kitchen. For the unfamiliar, the Kit-Kat clock is special in that its pendulum tail and eyes move back and forth with each passing second. They’re equal parts cute and creepy.

But not this particular Kit-Kat, not once [Becky Stern] got a hold of it. The cute/creepy scales have been tipped, because the eyes of this Kat follow you around the room. “You” in this case is fellow maker [Xyla Foxlin], whom [Becky] drew in the Maker Secret Santa pool. See, [Xyla] loves cats, but is deathly allergic to them. So really, what better gift is there?

In order to make this happen, [Becky] started by disconnecting the long lever that link the eyes and the tail, which move together, and connected a servo horn to the eyes. [Becky] drilled out the nose in order to fit the camera, which is connected to a Seeed Grove AI Vision board with a Xiao RP2040 piggybacked on top.

While soldering on the servo wires, [Becky] accidentally detached a tiny capacitor from the AI Vision board, but it turns out that it wasn’t critical. Although she only had to write one line of code to get it to work, it ended up working too well, with the eyes darting around really quickly. By making the servo move in timed increments to the new positions, it’s now much more creepy. Be sure to check out the build video after the break.

You know we can’t resist a clock build around here, especially when those clocks are binary.

Continue reading “Making A Kit-Kat Clock Even Creepier”