DecayDock Keeps Track Of Spoilage

Many of us have suffered the common experience of buying a great deal of (now very expensive) food, only to have it go off before it can be consumed. [ptallthings93] has whipped up a simple device to try and tackle this problem.

The result is DecayDock, which lives on a fridge and tries to keep track of what’s going on inside. It achieves this with the use of an ESP32-CAM module, which combines the capable microcontroller with a camera for image detection work. With the aid of an Edge AI model, it’s able to detect common food items that are held in front of the camera, which are in turn added to an internal inventory. The items are tracked over time based on expected shelf lives, and the freshness of various items in the fridge is displayed on an attached LCD screen with a green/yellow/red color coding system.

The system is only making estimates—it’s not able to actually identify when the cheese has gone moldy or the milk has gone sour. Still, if you struggle to remember what you should be prioritizing to use in your fridge, it might be a handy aid.

Ultimately, we never really saw smart fridges dominate the market, even though the idea has long been a popular one in futurist circles. Perhaps none of them thought that nobody really wants to stand staring down at a screen on the fridge all day. In reality, some areas of the home are best left unsmartified.

This Standalone Camera Gets The Picture Through With SSTV

These days, sending a picture to someone else is as simple as pulling out your smartphone and sending it by email or text message. It’s so simple a child can do it, but that simple user experience masks a huge amount of complexity, from the compression algorithms in the phones to the huge amount of distributed infrastructure needed to connect them together. As wonderful and enabling as all that infrastructure can be, sometimes it’s just too much for the job.

That seems to have been the case for [Dzl TheEvilGenius], who just wanted to send a low-resolution image from a remote location. It turns out that hams solved that problem about 70 years ago with slow-scan television, or SSTV. While most of the world was settling down in front of “I Love Lucy” on the regular tube, amateur radio operators were figuring out how to use their equipment to send pictures around the world. But where hams of yore had to throw a considerable amount of gear at the problem, [Dzl] just used an ESP-32 with a camera and some custom code to process the image. The output from one of the MCU’s GPIO pins is a PWM audio signal which can be fed directly into the microphone input of a cheap portable transceiver.

To decode the signal, [Dzl] used one of the many SSTV programs available. There’s no mention of the receiver, although it could be pretty much anything from another Baofeng to an SDR dongle. The code is available in the article, as is an audio file of an encoded image, if you just want to play around with the receiving and decoding side of the equation.

We could see something like this working for a remote security camera, or even for scouting hunting spots. If you want to replicate this, remember that you’ll need a license if you want to transmit on the ham bands — relax, it’s easy.

An ESP Will Read Your Meter For You

As home automation starts to live up to its glossy sci-fi promise there remains a deficiency when it comes to interfacing between the newer computerised components and legacy items from a previous age. A frequent example that appears in projects on Hackaday is the reading of utility meters, and in that arena [jomjol] has a very neat solution involving an ESP32 camera module and a software neural network to identify meter readings directly.

The ESP and camera sit at the top of a 3D-printed housing that fits over the meter. The clever trick comes as each photo’s orientation is determined, and not only is OCR used to read digits but also figures are derived from small dial meters and other indicators on the meter face. It’s a very well-thought-out system, with a web-based configuration tool that allows full customisation of the readable zones and how they should be treated.

This project makes full use of the ESP32’s capabilities, and the attention to detail that has gone into making it usable is particularly impressive. It certainly raises the bar against previous OCR meter reading projects.

[Thanks for the tip Sascha]