Raspberry Pi, a UK-based single board computer (SBC) company, launched an AI camera on Monday. The device, focused on artificial intelligence (AI) projects and workflows, aims to enable users to take full advantage of external AI accelerators, such as the Raspberry Pi AI Kit, which launched in June. The AI camera has a 12-megapixel Sony IMX500 Intelligent Vision Sensor that can capture visual data up to a resolution of 4056 x 3040 at 10 fps. It is compatible with all Raspberry Pi models.
Raspberry Pi AI Camera: Price and Availability
The Raspberry Pi AI Camera costs $70 in the US. The visual data sensor is available to order worldwide. In India, users can order it online from Robu.in, the company’s only authorized reseller in the country, where it is priced at Rs. 7,899. Namely, it is only available by order (currently out of stock, but will be shipped when the next batch arrives). The Raspberry Pi AI Camera is expected to start shipping from October 20.
Raspberry Pi AI Camera: Specifications and Applications
Equipped with a 12-megapixel Sony IMX500 Intelligent Vision sensor, the Raspberry Pi AI Camera can record visual data at a resolution of 4056 x 3040 at 10 fps or 2028 x 1520 at 30 fps. The sensor has a field of view of 78 degrees and comes with manually adjustable focus. The cell size in the chip is 1.55 x 1.55 micrometers. It is compatible with all Raspberry Pi models and can be connected to the RP2040 microcontroller with an ordinary ribbon cable.
Being an AI-focused device, it uses Sony’s AI toolkit to program frameworks for neural network models such as TensorFlow or PyTorch. The company points out that new models can be designed to take advantage of AI accelerator capabilities.
Furthermore, the device can be interfaced with the Raspberry Pi camera software package and the libcamera enhancement can process the Bayer frame using a company-specific ISP, a similar workflow for all Raspberry sensors.
The Raspberry Pi AI Camera is suitable for AI projects that require visual data collection. These could be robots with vision, automotive systems for driving automation or road mapping, or something as simple as an artificial intelligence model on a device that can process images from the real world. Furthermore, they can also be used for augmented reality use cases.