OStream’s PipeRunner is an edge AI media platform for converting video into an event-driven dataset. This solution provides real-time pattern detection to enable automated IoT workflows across applications from smart agriculture to smart cities. PipeRunner uses AI to detect and track context to accelerate media decoding while embedding useful insights into the video. OStream’s design can be clustered into an 8-device rack to form a scalable and cost-effective edge AI hardware platform, using the following board.
Built by OKdo, OStream’s PipeRunner-NVAI serves as a carrier board for inserting your own NVIDIA Jetson Orin NX or Orin Nano SoM for 20 to 100 TOPs AI processing; the operating system for this board is Ubuntu 20.04 LTS. With the NVIDIA device in place, this 96 x 76 mm board features GigE and Bluetooth 4.0 connectivity, 1x 4-lane MIPI camera and 3x USB 2.0 high-speed interfaces, and 128 GB NVMe SSD external storage. PipeRunner-NVAI can be powered using a 20 V supply at 3 A and has an operating temperature from 0°C to +85°C.
For a ready-to-go platform with 3 TOPS AI processing at full frame rate, consider OStream’s PipeRunner-RKAI Edge AI Media Board, which comes preconfigured with the Rockchip 1808 SoC.
OStream’s PipeRunner boards come preloaded with Physico software to make graphical AI pipeline building easy. They also leverage a pre-integrated set of AI computer vision stacks, GStreamer, and OpenCV to automatically run your elements on the right hardware accelerators for the task. In conjunction with Physico, this board detects and tracks context within your MP4 video stream to enable triggering of real-time action with other devices and systems, while simultaneously embedding useful metadata into your video stream.
OStream’s platform streamlines real-time pattern detection and simplifies development of automated AIoT workflows. It also enables users to search their media streams in a similar way to Google Images™ as objects are recognised and categorised.
Learn more about PipeRunner-NVAI in this datasheet. If you want to evaluate this technology for use in a commercial application, and have access to NVIDIA Orin SoMs, use the form below to apply for a sample, and ipXchange will put you in touch with OStream for further discussion.