If you ever wanted to have computer vision, artificial intelligence in your product without the huge learning and development effort, here is a chance with megaAI Board.
Brandon Gilles from Luxonis has launched megaAI board which is a complete Computer Vision solution in a tiny, low power board.
It comes packed with 4K Resolution, 60FPS Camera along with Intels Madrid X AI accelerator chip.
It’s not only good for hobbyists, researchers but also for the OEMs. It is compatible with our DepthAI ecosystem, and is therefore easy to use.
See a small introduction video, which gives a good overview.
Hardware Features
- High Compute Capacity: 4 Trillion Operations Per Second(TOPS) using Intel’s Madrid X AI Accelerator Chip.
- Onboard Camera: 12 MP 4056×3040 Auto-Focus (8cm-∞) 81-Deg. Horizontal Field of View (HFOV)
- RAW Output Specs: 4K @ 60FPS or 12MP @ 30FPS with USB3.1 Gen2 Host
- Hardware Image Encoding: 12 MP JPEG encoding
- Hardware Video Encoding: 4K H.265 encoding at 30 FPS
- Low Power Draw: 2.5 W max.
- Lightweight: 2 oz.
- Compact Size: 45 mm x 30 mm
- Flexible Design Usage: built for ease of prototyping AND integration into new products
- Fast Connectivity: USB3 Type-C 3.1 Gen1 (5 Gbps)
- Open Source: MIT Licensed hardware, software, and documentation
Super Simple Object Detection
The megaAI make difficult computer vision tasks like real-time object detection and tracking as simple as plugging in a USB cable and running a Python script.
You need to just use the DepthAI git repository and run python depthai.py to see a live demonstration of MobileNetSSD being run on your host system. You can even record live 4K, 30 FPS video of everything the camera looks at.
Object Detection & Tracking
Object detection is the capability to segment each object from the scene and then identify what it is. megaAI claim to have successful in object detection and tracking at crazy 30 FPS on Raspberry Pi board without any load on the CPU.
megaAI example Image shows Object detected and labeled.
Computer Vision along with AI is changing the way we see the world, super complex problems are getting solved easily. The future is really interesting.
There are so many Hardware available these day for your on the edge AI experiments. See some of the popular AI hardware platforms listed here.
I hope you have enjoyed reading the post. You can share your thoughts below in the comments section.
News Source.
You can read my other blogs or interesting embedded system articles here where I share some of the practical tips for embedded system design.
I help embedded engineers and start ups build reliable and successful embedded products and providing professional services as embedded system design consultant. If you need any help please let me know here.
Happy Learning to you!