Arducam OCam, whose name stands for Object Camera, is an AI camera with 3 TOPS of AI performance and designed to work with OStream‘s PhysicO Edge AI media platform that adds context to MP4 video streams in real-time.
The camera supports resolutions from QVGA to 2K, takes USB or PoE power, comes with a drag-and-drop AI pipeline for easy programming/configuration, and is also compatible with common AI tools such as TensorFlow, PyTorch, Edge Impulse, and others.
Arducam OCam specifications:
- Resolution – QVGA up to 2K
- Frame Rate – Up to 60 fps
- FoV – 80°
- Audio – Dual beamforming
- AI processing power – Up to 3 TOPS
- Power Supply
- 5V via USB
- PoE
- Power Consumption – Up to 5 Watts
- Dimensions – 10 cm Φ x 3 cm
- Weight – 400 grams
As I understand it, the AI pipeline – named ObjectAgent – runs on the camera itself, and adds context (e.g. results from object detection like cars, persons, etc…) directly into the MP4 stream’s object data along with the audio and video. So the videos become searchable in the PhysicO dashboard in a way similar to Google Image Search. The best way to understand how it works is to check out the video below should a driveaway detection demo that can be further customized into a “is dad a home?” solution.
Something similar can be achieved with DIY solutions using NVIDIA Jetson Nano and Arducam’s other cameras, and open-source frameworks such as Gstreams and OpenCV, but Arducam describes the OCam as a DFY solution (done for you) that works out of the box. I could not find clear documentation, with just an overview of the solution, but I understand you’ll get tutorials and documentation after logging in to https://app.ostream.com and registering your camera. We’ll try to get a camera for testing and review.
The Arducam OCam is available for pre-order now for $125, and after the pre-order period is over, the price will go up to $160. Shipping is scheduled to start in March 2023. As a side note, OStream also sells the battery-powered Percept-WOCam long-distance (“not WiFi”) camera for $250, but it seems to be another type of solution, as the bitrate rate is under 2 Mbps and they crop the objects of interest.
Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress
