Raspberry Pi Unveils AI-Powered Camera with On-Device Processing

Raspberry Pi takes a shot at AI with a camera and on-device processing

Raspberry Pi has joined the world of AI with a new camera that processes visual data with AI models on the device. The $70 Raspberry Pi AI Camera was built in collaboration with Sony Semiconductor Solutions Corporation (SSS). The camera embeds Sony's IMX500 intelligent vision sensor to process images with AI on the chip. That means there is no need for high-end GPUs or accelerators. It's compatible with Raspberry Pi's single-board computers, making it relatively cheap and easy to make AI tools that rely on images. The AI Camera has around 12.3 megapixels and can film at ten frames per second in 4056 x 3040 or 40 fps at 2028 x 1520. The neural network firmware onboard lets the AI image processing run on the camera. This lets the Raspberry handle other elements of an integrated device, opening up options for Raspberry Pi users who don't want to use the Raspberry Pi AI Kit alone. The on-chip AI processing reduces the burden on the host device and enables real-time data processing without requiring cloud-based computing power. Processing data locally makes for faster, more efficient AI tools. Because it's compatible with much of the Raspberry Pi ecosystem, users can still use hardware and software libraries they are familiar with and enjoy using. For instance, the AI Camera is compatible with popular libraries such as lib-camera and Picamera2. "AI-based image processing is becoming an attractive tool for developers around the world," said Raspberry Pi Ltd. CEO Eben Upton. "Together with our longstanding image sensor partner Sony Semiconductor Solutions, we have developed the Raspberry Pi AI Camera, incorporating Sony's image sensor expertise. We look forward to seeing what our community members are able to achieve using the power of the Raspberry Pi AI Camera."

Raspberry Pi and Sony have revealed an AI camera with its own on-board processor

People interested in running AI on an SBC have been having a fantastic time lately. We've seen an official Raspberry Pi AI kit and a ton of alternatives you can check out. Now, SBC AI fans are eating well once again, after Sony teamed up with Raspberry Pi to bring an AI camera to the board. Best of all, the camera itself has an AI processor on it, making it a nice all-in-one package for getting visual AI tasks done. Related Raspberry Pi 5 review: The holy grail of DIY projects got even better (and rarer) The Raspberry Pi 5 is one of the most powerful consumer-grade SBCs out there. Sadly, its limited stock means you'll have a hard time finding one. Sony and Raspberry Pi reveal an AI camera for its SBCs As announced on the Sony Semiconductor Solutions Group news feed, Sony and Raspberry Pi have teamed up to release an AI camera. The camera is a 12.3-megapixel model and can hit 10FPS at 4056x3,040 resolution, or 40FPS at 2,028x1,520. So, what makes this camera an "AI camera"? Well, you don't have to worry about your SBC having an AI module: Because vision data is normally massive, using it to develop AI solutions can require a graphics processing unit (GPU), an accelerator, and a variety of other components in addition to a camera. The new Raspberry Pi AI Camera, however, is equipped with the IMX500 intelligent vision sensor which handles AI processing, making it easy to develop edge AI solutions with just a Raspberry Pi and the AI Camera. As you might imagine, the additional hardware raises the price a little higher than a typical Raspberry Pi camera. It comes in at $70, and you can snag one for yourself by visiting the Raspberry Pi AI camera website, clicking "Buy AI Camera" and then selecting a trusted reseller. And if that's a bit too pricey for your liking, you can instead check out the best Raspberry Pi cameras for some cheaper alternatives without the AI hardware. Raspberry Pi AI Camera The Raspberry Pi AI Camera is a compact camera module from Raspberry Pi, based on the Sony IMX500 Intelligent Vision Sensor. The IMX500 combines a 12-megapixel CMOS image sensor with on-board inferencing acceleration for a variety of common neural network models, enabling users to develop sophisticated vision-based AI applications without the need for a separate accelerator. $70 at The Pi Hut

There's a New Camera for Your Raspberry Pi

Sony Semiconductor Solutions (SSS) and Raspberry Pi Ltd. have just released the Raspberry Pi AI Camera. This camera comes with the SSS's IMX500 intelligent vision sensor, which lets it use on-chip image processing. This removes any need for additional hardware like GPUs or accelerators. The Raspberry Pi AI Camera is the first product that comes from the collaboration between SSS and Raspberry Pi Ltd. The Raspberry Pi AI Camera is compatible with all Raspberry Pi single-board computers, including the latest Raspberry Pi 5. It integrates with the popular libcamera and Picamera2 software libraries, which gives the buyer a familiar development environment if they're used to other Raspberry Pi devices. The camera is pre-loaded with the MobileNetSSD model and supports other neural network models through Sony's AI tools. Both companies have stated they are excited about this new product's potential and are looking forward to further collaborations. One collaboration mentioned was the integration of Sony's AITRIOS edge AI solution development and operations platform. The Raspberry Pi AI Camera has a 12.3 MP Sony IMX500 Intelligent Vision Sensor, which includes a neural network accelerator. The camera offers two sensor modes: a full resolution of 4056x3040 pixels at 10 frames per second (fps) and a 2x2 binned mode of 2028x1520 pixels at 30 fps, both with 10-bit color depth. The sensor's physical dimensions are 7.857 mm, with a pixel size of 1.55 μm x 1.55 μm. It features a 78-degree field of view (FoV) with manual/mechanical adjustable focus, and a focal ratio of F1.79. The camera module itself measures 25 x 24 x 11.9 mm. In other words, it's incredibly small. One of the main challenges in this kind of product is the massive amount of data involved, particularly with vision data. Traditional solutions often use powerful hardware to process this data. The Raspberry Pi AI Camera instead integrates the AI processing capability directly into the sensor. This should make it much easier to get data to the computer without the need for multiple chips, which would force the camera to be bigger. The Raspberry Pi AI Camera is available on the official website for $70. Source: Raspberry Pi, PR Newswire

Raspberry Pi built an AI camera with Sony

AI enthusiasts who like the Raspberry Pi range of products can rejoice, as the company is now announcing its new Raspberry Pi . This product is the result of the company's collaboration with (SSS), which began in 2023. The AI Camera is compatible with all of Raspberry Pi's single-board computers. The approximately 12.3-megapixel AI Camera is intended for vision-based AI projects, and it's based on SSS' IMX500 image sensor. The integrated RP2040 microcontroller manages the neural network firmware, allowing the camera to perform onboard AI image processing and freeing up the Raspberry Pi for other processes. Thus, users who want to integrate AI into their Raspberry Pi projects are no longer limited to the Raspberry Pi AI Kit. The AI Camera isn't a total replacement for Raspberry Pi's , which is still available. For those interested in the new AI Camera, it's available right now from Raspberry Pi's approved resellers for $70.

Raspberry Pi offloads AI inferencing to the camera itself

HANDS ON Raspberry Pi has launched a camera module with AI smarts on board. But all that inferencing goodness comes at a price. Looking for all the world like a normal camera module - if ever so slightly thicker - the Raspberry Pi AI Camera is based on Sony's IMX500 Intelligent Vision Sensor, which combines a 12.3-megapixel CMOS image sensor with on-board inferencing. The AI camera will add tensor metadata to still images or video, rather than requiring a separate accelerator for processing or loading up the CPU with tasks to deal with vision-based AI workloads. While recent Pi units have had relatively powerful processors compared to their predecessors, they are still comparatively weedy compared to pricier silicon - so some dedicated AI vision processing is most welcome. We were sent a sample unit for review and found that, assuming a user is familiar with the existing camera libraries, getting up and running was simple. Some demonstration bits of Python code from GitHub showed off the unit's capabilities; we ran up samples that classified the contents of images and drew boxes around what it reckoned it had found. According to monitoring software, the CPU cores were barely ticking over while the AI Camera took care of the heavy lifting. That would change, should further processing or refinement be required on the Pi. Hardware-wise, the unit has two sensor modes: 10 fps is possible at a resolution of 4,056 x 3,040; and 30 fps can be achieved at 2,028 x 1,520. The device is not infrared-sensitive, and the focus is manual. This is a real shame, given the Camera Module 3 has autofocus as well as a higher frame rate and wider field of view - but lacks AI capabilities. There is 8MB on board for firmware and weighting files and an RP2040 for neural network firmware management. We noted a short delay as the neural firmware was loaded onto the module - though on our Pi 5, that was measured in seconds rather than minutes. The camera is compatible with all Raspberry Pi devices. A spokesperson told us that the shipping item would also be supplied with 200mm cables for both types of connectors on the hardware: the "mini" used on the Pi 5 and Zero, and the wider "standard" cable for everything else. The price is understandably up a bit from the cost of the non-AI-enabled camera modules - it's expected to retail for $70 plus local taxes. To put that in context, the Camera Module 3 starts at $25, or you can pick up the HQ camera module for just over $50. All of which means that customers need to consider their use case. If you just want to snap images, then the AI camera is not for you - particularly considering the nifty autofocus of the Camera Module 3. However, if you're working on a project that requires image classification, then the AI Camera is worthy of consideration - particularly given how easy it is to use. It could also be an opportunity to perform inferencing on hardware that might otherwise not be up to it - Pi supremo Eben Upton told us that the unit tended to be paired with the Pi Zero 2 W at trade shows. Upton added that the Pi 5-only AI kit - which can be had for slightly more than $70 - had seen strong demand since its June launch. He was optimistic that the AI Camera, which works with all Raspberry Pi devices, would be more popular still. ®

Why you should consider Raspberry Pi AI Camera

The Raspberry Pi Foundation has announced a new AI Camera module for $70 in collaboration with Sony. Being the newest addition to the Raspberry Pi platform, this new AI Camera is designed to help developers in AI image processing tasks with ease. Built-in with Sony's IMX500 image sensor and Raspberry funded's RP2040 microcontroller, this new AI camera performs all the processing on board and does not even require GPUs Resolution of the camera is 12.3 MP, with the ability to record at a rate of 10 frame per second in 4056 x 3040 resolution or 40 frame per second in 2028 x 1520 resolution. The AI Camera is fairly similar in size to the Camera Module 3 at a size of 25 x 24 x 11.9mm. As much as the Raspberry Pi AI Camera is designed for the hobbyist, it serves the overall tactile and hardware geek beyond the do-it-yourselfer. The organization has noted that as popular industries using Raspberry Pi, noted that already 72% of its sales were in organizations that were incorporating Raspberry Pi products into their operations. With the AI Camera, this is set to rise with the application of smart. Raspberry Pi has given its word that the AI Camera will remain in production through to, at the very minimum, January 2028 to provide adequate continuity for the developers and businesses that rely on it. This follows suitable supply line issues that were hugely impacted by the pandemic and have since been mainly addressed when it comes to Raspberry's products, thus enabling the organization to consistently offer dependable market offerings to its increasingly expanding industrial consumers. For instance, when connected to an artificial intelligence algorithm, you can convert this camera into a smart doorbell. The AI Camera is able to detect whether a person is standing in the doorway or objects such as packages. This would allow you to set up alarms that are smarter than simple motion detection, or as some of you mentioned, an alarm system that was sophisticated enough could just turn into a sentiment analysis engine. Instead of receiving notifications Any time a branch moves, you only get notified During occurrences such as a delivery. If you prefer do-it-yourself home security, the camera can assist you to keep a watchful eye on certain areas of activity and because the image processing is done on camera, it does not overwhelm the rest of Raspberry Pi system. Therefore, you could also run other smart home features at the same time such as operating on lights or managing your sensors without much of a problem. Raspberry Robin malware is the danger lurking inside your USB For industrial or business projects, the camera can be used in quality control systems. Suppose you are overseeing a small production line and could place the camera in such a way that it checks if the products are assembled correctly and warn if something is off. Because the current camera is compact and easily collapsible onto existing Raspberry Pi systems, this solution is scalable to points in the production line. Another feasible use case can be implemented in smart city initiatives, for example, in the case of traffic analysis with the help of AI Camera. It could determine vacant parking space zones or study traffic patterns at some junctions. Since the design is inherently optimized for performance and modularity, it is possible to introduce the system with one camera and extend it to multiple cameras in different areas, such as a city block, without having to redesign most of the system. You should choose between the Raspberry Pi AI Kit and the AI Camera based on your needs. The AI Kit, in general, unleashes more performance with 13 trillion operations per second but is compatible only with Raspberry Pi 5, and you will need to incorporate a camera module. Modern AI cameras are smaller, cheap, and compatible with all ranges of Raspberry Pi, which is why they can be used in a wide array of endeavors. As for image processing and computational tasks linked to a neural network, the AI Camera, because of the use of the Sony IMX500, performs these directly on the vehicle.

Raspberry Pi and Sony Combine to Create an AI-Powered Camera Module

Raspberry Pi, the company that sells small, single-board computers, released the Raspberry Pi AI camera which utilizes Sony's IMX500 Intelligent Vision Sensor. The unit is priced at $70 and will be useful to experimental photography engineers who enjoy making Frankenstein cameras. "Compatible with all Raspberry Pi computers, the Raspberry Pi AI Camera takes advantage of Sony's IMX500 Intelligent Vision Sensor to help you create impressive vision AI applications and neural network models using the on-module AI processor," Raspberry Pi writes on its website. The camera is 12.3 megapixels that can capture footage at 10 frames per second in 4056 x 3040 or 40 frames per second at 2028 x 1520. It has a 76-degree field of view with a manually adjustable focus. The entire unit measures 25 x 24 x 11.9 mm. The Raspberry Pi AI camera combines the company's RP2040 microcontroller chip with Sony's IMX500 image sensor. Tech Crunch notes that because the AI camera module has onboard processing, the host Raspberry Pi computer won't be affected by visual data processing meaning users won't need a separate accelerator or graphics processing unit (GPU) which are typically needed for camera modules to handle large-scale visual data. It's not the first time Raspberry Pi has released a camera module -- the company still sells the Raspberry Pi Camera Module 3 for $25 -- and this new version isn't replacing existing products. The AI camera is about the same size as Camera Module 3 but with a slightly thicker optical sensor. A real-time object detection model called MobileNet-SSD comes pre-loaded with the module. "AI-based image processing is becoming an attractive tool for developers around the world," Raspberry Pi CEO Eben Upton says in a press release. "We look forward to seeing what our community members are able to achieve using the power of the Raspberry Pi AI Camera." "Sony Semiconductor Solutions and Raspberry Pi Ltd aim to provide Raspberry Pi users and the development community with a unique development experience," says Eita Yanagisawa, General Manager, System Solutions Division, Sony Semiconductor Solutions Corporation. "I'm very excited to share SSS edge AI sensing technology with the world's largest development community as the first fruits of our strategic partnership. We look forward to further collaboration with Raspberry Pi using our AITRIOS™ edge AI solution development and operations platform. We aim to make the most of AI cameras equipped with our image sensors in our collaborative efforts with Raspberry Pi."

$70 AI Camera From Raspberry Pi, Sony Works With All Pi Models

Earlier this year, Raspberry Pi released an AI Kit for those tinkering with artificial intelligence projects, but it's only compatible with the Raspberry Pi 5 and needs a separate camera module to capture visual data. If you had an older Raspberry Pi, you were out of luck, until now. The new Raspberry Pi AI Camera is compatible with all models of Raspberry Pi and connects via one of the company's camera ribbon cables. It's "built around a Sony IMX500 image sensor with an integrated AI accelerator [and] can run a wide variety of popular neural network models, with low power consumption and low latency, leaving the processor in your Raspberry Pi free to perform other tasks," Raspberry Pi says. The $70 camera is on sale now. Specs include: "Using Sony's suite of AI tools, existing neural network models using frameworks such as TensorFlow or PyTorch can be converted to run efficiently on the AI Camera," Raspberry Pi says. "Alternatively, new models can be designed to take advantage of the AI accelerator's specific capabilities." The AI Camera integrates with the Raspberry Pi camera software stack. "Under the hood, libcamera processes the Bayer frame using our own ISP, just as it would for any sensor," it says. The company worked with Sony to release "a number of popular visual neural network models optimized for the AI Camera in our model zoo, along with visualization example scripts using Pcamera2." Raspberry Pi says that the AI Kit is stronger than the AI Camera in terms of sheer computational power. However, it's cheaper for people with an older model who don't already own a camera.

Raspberry Pi and Sony release an AI-powered camera module

The Raspberry Pi AI Camera works with all Raspberry Pi models and is now available for purchase. Raspberry Pi, in collaboration with Sony Semiconductor Solutions Corporation, just launched an AI-powered camera module called the Raspberry Pi AI Camera. The module is based on Sony's IMX500 image sensor with an integrated AI accelerator, which means it can do AI-based image processing directly on a Raspberry Pi device without any external processors. The IMX500 image sensor is capable of 12MP images and has two modes: a larger 4056×3040 resolution at 10 FPS and a smaller 2028×1520 resolution at 30 FPS. The camera itself has a 78-degree field of view with a manually adjustable focus. The Raspberry Pi AI Camera module is compatible with all Raspberry Pi models (including the Raspberry Pi Zero) via Raspberry Pi's camera ribbon cable. You can buy it now for $70 at authorized retailers. Note: If you have a Raspberry Pi 5, you should consider getting the Raspberry Pi AI Kit that was released back in June instead. (The AI Kit is more performant but only works with Raspberry Pi 5, whereas the AI Camera is smaller, cheaper, and more broadly compatible.)

Raspberry Pi and Sony made an AI-powered camera module

Raspberry Pi and Sony have co-developed a Raspberry Pi AI Camera module that's launching today for $70. It comes with onboard AI processing that can help Raspberry Pi users develop "edge AI solutions that process visual data" with ease, according to the tiny computer maker. The new camera builds on Raspberry Pi's plans to offer chips and add-ons for AI developers, having previously released several non-AI camera modules since its first 5-megapixel offering in 2013. "AI-based image processing is becoming an attractive tool for developers around the world," Raspberry Pi CEO Eben Upton said in a press release. "We look forward to seeing what our community members are able to achieve using the power of the Raspberry Pi AI Camera."

Raspberry Pi launches camera module for vision-based AI applications | TechCrunch

Raspberry Pi, the company that sells tiny, cheap, single-board computers, is releasing an add-on that is going to open up several use cases -- and yes, because it's 2024, there's an AI angle. Called the Raspberry Pi AI Camera, this image sensor comes with on-board AI processing and is going to cost $70. In more technical terms, the AI Camera is based on a Sony image sensor (the IMX500) paired with a RP2040, Raspberry Pi's own microcontroller chip with on-chip SRAM. Like the rest of the line-up, the RP2040 follows Raspberry Pi's overall philosophy -- it is inexpensive yet efficient. In other words, AI startups aren't going to replace their Nvidia GPUs with RP2040 chips for inference. But when you pair it with an image sensor, you get an extension module that can capture images and process those images through common neural network models. As an added benefit, on-board processing on the camera module means that the host Raspberry Pi isn't affected by visual data processing. The Raspberry Pi remains free to perform other operations -- you don't need to add a separate accelerator. The new module is compatible with all Raspberry Pi computers. This isn't Raspberry Pi's first camera module. The company still sells the Raspberry Pi Camera Module 3, a simple 12-megapixel image sensor from Sony (IMX708) mounted on a small add-on board that you can pair with a Raspberry Pi with a ribbon cable. As Raspberry Pi promises to keep production running for many years, the Camera Module 3 will remain available for around $25. The AI Camera is the same size as the Camera Module 3 (25mm x 24mm) but slightly thicker due to the structure of the optical sensor. It comes pre-loaded with the MobileNet-SSD model, an object detection model that can run in realtime. At this point, you might be wondering who is going to use the Raspberry Pi AI Camera. While the tiny computers were originally designed for tech hobbyists and homelab projects, Raspberry Pi now sells most of its devices to companies that use Raspberry Pi devices in their own products or as part their assembly lines for internal industrial use cases. When Raspberry Pi became a public company, it reported that the industrial and embedded segment represented 72% of its sales. That ratio is likely going to be even higher for the AI Camera. I could imagine companies using the AI Camera module for smart city sensors that detect empty parking spots, say, or track traffic flows. In an industrial environment, the hardware could be used for basic, automated quality assurance with objects passing under the camera module. The reason why companies like using Raspberry Pi is because they can produce computers and modules at scale -- they faced some post-Covid supply constraints but those seem to be resolved. Companies know they can reliability source Raspberry Pi products without suffering delays in a production pipeline. That's also part of the reason why Raspberry Pi promises that the AI Camera will remain in production until at least January 2028.

Sony has just created an AI camera for the best-selling Raspberry Pi - Softonic

The AI camera is compatible with all Raspberry Pi single-board computers For those who use the world's most famous minicomputer, the Raspberry Pi, they can rejoice with the collaboration they have made with Sony, where the star is a camera powered by artificial intelligence. Raspberry Pi and Sony have jointly developed a Raspberry Pi AI camera module that launches today for $70. It comes with built-in AI processing that can help Raspberry Pi users develop "advanced AI solutions that process visual data" with ease, according to the small computer manufacturer. The new camera is based on Raspberry Pi's plans to offer chips and add-ons for AI developers, having previously launched several non-AI camera modules since its first 5-megapixel offering in 2013. "AI-based image processing is becoming an attractive tool for developers around the world," said Raspberry Pi CEO, Eben Upton, in a press release. "We are looking forward to seeing what our community members are able to achieve using the power of the Raspberry Pi AI camera." The AI camera is compatible with all Raspberry Pi single-board computers and combines the company's RP2040 microcontroller chip with Sony's IMX500 image sensor, the latter responsible for AI processing. The combination eliminates the need for additional components such as accelerators or a graphics processing unit (GPU), which are usually necessary for camera modules to handle large-scale visual data. The Raspberry Pi AI Camera, with 12.3 megapixels, can capture images at 10 frames per second in 4056 x 3040, or at 40 fps in 2028 x 1520. It also has a manually adjustable focus, a 76-degree field of view, and measures 25 x 24 x 11.9 mm, making it almost identical in size to the Camera Module 3 that Raspberry Pi released last year.

Raspberry Pi AI Camera Review: AI for the masses

It may not come as a big surprise. After all, the $70 Raspberry Pi AI Camera was spotted at Embedded World 2024, but the news of a new AI-enabled camera for the Raspberry Pi is a welcome addition to Raspberry Pi's new range of AI products, starting with the Raspberry Pi AI Kit back in June. The Raspberry Pi AI Camera kit is a capable AI device which has another Raspberry Pi at its heart. Just underneath the sensor lies an RP2040. The same SoC as found in the Raspberry Pi Pico. It may not be as powerful as the RP2350 found in the Raspberry Pi Pico 2, but it has enough computational power to run basic inference models. This is where it gets interesting. The RP2040 is doing all of the computational work for the AI model. The Raspberry Pi's CPU is sitting idle. This means that power consumption is much lower than using the Pi's CPU. Put this AI camera in a low power Raspberry Pi Zero 2 W board, and we have a potent cocktail for embedded AI projects. At Embedded World, the Raspberry Pi AI Camera was being run on a Raspberry Pi Zero 2W and showed a steady 30fps while tracking people at the convention booth. Is the Raspberry Pi AI Camera worth your $70, or should you pony up the cash and buy into the Raspberry Pi AI Kit instead? Let's find out! Put the new Raspberry Pi AI Camera against the Raspberry Pi Camera Module V3 and you can see the family resemblance. At a casual glance they look the same, but the new AI camera has a larger plastic shroud around the sensor, and hidden under it is an RP2040. The AI camera has the same mounting holes to secure the camera into a holder. My 3D printed holder worked well, but the extra size around the sensor means that it won't fit every camera mount, just like the V3. This is Raspberry Pi's first AI camera, born from a partnership with Sony, which also manufactures our favorite single board computer. This may be the first AI camera from Raspberry Pi, but it can also be used as a typical camera. I managed to take images and video at the maximum resolution of 4056 x 3040. For video I would drop this down to 1080p though as the highest resolution will drop the FPS considerably. Installation was a breeze. Plug in, power up and update the software. Because this was a review unit, I did have to follow a few extra steps that consumers will not. To start with, our review unit didn't work as expected, it turns out that I needed to update the firmware to the latest version. With that out of the way, I was able to test the camera. If you have ever used a Raspberry Pi camera, or the latest AI kit, then you are right at home. To put it simply, the AI camera behaves in a similar manner to the AI kit. It has TensorFlow support, and comes with models to identify some objects and human poses, and all of this is done inside the RP2040. Yes, the Raspberry Pi 5's Arm based SoC is left idle while the AI camera does all of the work. This leaves the Raspberry Pi 5 to handle other, more CPU intensive tasks while the AI camera does all the AI. While running our tests we kept an htop (terminal application to monitor system resources) session open. We could see that all four of the CPU cores were running at less than 10%! I tested the AI camera with two models, a mobilenet object detection model and a posenet model that is used to detect a human pose. Both of the models worked at 640 x 480 pixels and kept to a steady 30 fps, even during my "thrilling" moments of "animated pose detection" testing. Using the rpicam-hello object detection demo script I was able to see the AI camera detect a person, me, in the shot with a high percentage of confidence. I then reached for a series of props, a water bottle and a 3D printed banana for scale. All of these objects were detected, once the image was in focus. We've got to remember that this is a 20 cm to infinity lens, so getting too close will cause the image to blur, and the AI model will fail to detect the object. I then moved on to pose detection, and performing what can only be described as an amateur dramatic level rendition of Michael Jackson's Thriller, I could see the AI model detect my pose as a wireframe across my shoulders and arms. These demos are great, but can we use the Raspberry Pi AI Camera in a project? Yes we can! Using the Picamera2 library we can bring the power of the AI camera into a Python project. Pose detection can be used to control a motor, trigger a sound effect or anything really. At a fun level we could use this to trigger magic effects in a video, at a more serious level this could be used for gesture control as a life enhancing tool. The Sony IMX500 has a tool to convert PyTorch or TensorFlow models into something that the Sony IMX500 understands. These can be installed from the terminal using pip. You'll need to install the modules into a virtual environment, as per PEP668 guidance. Ok, the Raspberry Pi AI Kit has a much more powerful NPU. The $70 Raspberry Pi AI Kit comes with the Hailo-8L NPU as an M.2 2242 package. Using the M.2 HAT+ board, the Hailo-8L connects to the PCIe bus and provides around 13 TOPS (Tera-Operations Per Second) of performance with TensorFlow, TensorFlow Lite, Keras, PyTorch & ONNX. But if we want to use a camera, then we need to pay an additional $25. If we want to use a hard drive, then we are out of luck because the Hailo-8L is occupying the only spot. The Raspberry Pi AI Camera may not have the same performance as the Hailo-8L; we've not been able to confirm the performance, but we can hazard a guess that the Hailo-8L is more performant than the RP2040. We'd love to see how the RP2350 performs, but that is the subject of another story. If you crave the ultimate AI performance for your Raspberry Pi, then the Raspberry Pi AI Kit is for you. But for the majority of us, the Raspberry Pi AI Camera does a great job. Because this is an "all-in-one" device, we can see the AI camera being used in schools and for light AI projects in an industrial setting. For robotics projects, the Raspberry Pi AI Camera will be superb, offering enough smarts for obstacle detection, without forcing you to redesign your chassis. The RP2040 brains in the camera are good enough to get the job done, heck we'd say that they are more than good enough for 99% of users. Power AI users will want a little more muscle, and for that the Raspberry Pi AI kit should be your first port of call. You can still connect a Camera Module v3 and use the Hailo-8L NPU with Python to create a powerful AI based project. But if you are dipping your toe into AI, then the AI camera could be a great deal for $70. At $70, this is an expensive camera for the Raspberry Pi, but this isn't "just a camera". We get AI baked into the camera, an AI that we can use with our PyTorch or TensorFlow models thanks to Picamera2 integration. It just works. Even our review unit with its pre-release software, just worked once we got the process down. This is a great value AI kit for those of us who want to start using AI with cameras.

Sony Semiconductor Solutions and Raspberry Pi Launch the Raspberry Pi AI Camera By Investing.com

Accelerating the development of edge AI solutions ATSUGI, and , /PRNewswire/ -- Sony (NYSE:SONY) Semiconductor Solutions Corporation (SSS) and Raspberry Pi (LON:RPI) Ltd today announced that they are launching a jointly developed AI camera. The Raspberry Pi AI Camera, which is compatible with Raspberry Pi's range of single-board computers, will accelerate the development of AI solutions which process visual data at the edge. Starting from , the product will be available for purchase from Raspberry Pi's network of Approved Resellers, for a suggested retail price of . Not including any applicable local taxes. In , it was announced that SSS would make a minority investment in Raspberry Pi Ltd. Since then, the companies have been working to develop an edge AI platform for the community of Raspberry Pi developers, based on SSS technology. The AI Camera is powered by SSS's IMX500 intelligent vision sensor, which is capable of on-chip AI image processing and enables Raspberry Pi users around the world to easily and efficiently develop edge AI solutions that process visual data. "SSS and Raspberry Pi Ltd aim to provide Raspberry Pi users and the development community with a unique development experience," said , General Manager, System Solutions Division, Sony Semiconductor Solutions Corporation. "I'm very excited to share SSS edge AI sensing technology with the world's largest development community as the first fruits of our strategic partnership. We look forward to further collaboration with Raspberry Pi using our AITRIOS™ edge AI solution development and operations platform. We aim to make the most of AI cameras equipped with our image sensors in our collaborative efforts with Raspberry Pi." "AI-based image processing is becoming an attractive tool for developers around the world," said , CEO, Raspberry Pi Ltd. "Together with our longstanding image sensor partner Sony Semiconductor Solutions, we have developed the Raspberry Pi AI Camera, incorporating Sony's image sensor expertise. We look forward to seeing what our community members are able to achieve using the power of the Raspberry Pi AI Camera." Specifications About Sony Semiconductor Solutions Corporation Sony Semiconductor Solutions Corporation is a wholly owned subsidiary of Sony Group Corporation and the global leader in image sensors. It operates in the semiconductor business, which includes image sensors and other products. The company strives to provide advanced imaging technologies that bring greater convenience and fun. In addition, it also works to develop and bring to market new kinds of sensing technologies with the aim of offering various solutions that will take the visual and recognition capabilities of both human and machines to greater heights. For more information, please visit https://www.sony-semicon.com/en/index.html. About Raspberry Pi Ltd Raspberry Pi is on a mission to put high-performance, low-cost, general-purpose computing platforms in the hands of enthusiasts and engineers all over the world. Since 2012, we've been designing single-board and modular computers, built on the Arm architecture, and running the Linux operating system. Whether you're an educator looking to excite the next generation of computer scientists; an enthusiast searching for inspiration for your next project; or an OEM who needs a proven rock-solid foundation for your next generation of smart products, there's a Raspberry Pi computer for you.