There are some Raspberry Pi projects that are built to change the world, and this is definitely one of them. Maker and developer Md. Khairul Alam has created a wearable headset made of glasses with a special camera system to help the visually impaired navigate. Alam sums up the project succinctly, calling it “a third eye for the blind.”
The project relies heavily on AI to interpret the surroundings for the wearer, using a Xiao ESP32S3 Sense module for video input, which scans each frame to assess the environment. Alam says the goal of the project is to help the visually impaired become more independent and less reliant on third parties to help them walk.
If you're wondering how the person wearing the headset receives input from the module, you'll be happy to know that all you need is a simple pair of headphones. The Xiao ESP32S3 Sense module sends information to a Raspberry Pi, which creates a text-based description of what it sees. This text is converted to speech and played through the wearer's earpiece.
Image 1 of 2
(Image courtesy of Md. Khairul Alamhas)(Image courtesy of Md. Khairul Alamhas)
Alam has shared some detailed photos of the development process, and it looks like he's using an original Raspberry Pi Model B, but you could use anything between that and the latest Raspberry Pi 5. The Pi is connected to a Xiao ESP32S3 Sense, which has a built-in camera sensor and digital microphone. It has 8MB of flash, but also has a microSD card slot. The Xiao ESP32S3 gets power from the Pi, which can be powered by a battery bank in your pocket.
Alam has kindly provided the full source code for anyone interested in replicating the project at home. He used Edge Impulse Studio for object detection and model training. Full details on how to set up the system and train the model can be found on the official project page.
If you want to learn more about this Raspberry Pi project, you can check it out on Hackster.
