reServer Jetson-50-1-H4 is an AI Edge server powered by NVIDIA Jetson AGX Orin 64GB

Jetson AGX Orin 64GB AI inference server

reServer Jetson-50-1-H4 is an AI inference edge server powered by Jetson AGX Orin 64GB with up to 275 TOPS of AI performance, and based on the same form factor as Seeed Studio’s reServer 2-bay multimedia NAS introduced last year with an Intel Core Tiger Lake single board computer. The 12-core Arm server comes with 32GB LPDDR5, a 256GB NVMe SSD pre-loaded with the Jetpack SDK and the open-source Triton Inference server, two SATA bays for 2.5-inch and 3.5-inch drives, up to 10 Gbps Ethernet, dual 8K video output via HDMI and DisplayPort, USB 3.2 ports, and more. reServer Jetson-50-1-H4 (preliminary) specifications: SoM – Jetson AGX Orin module with CPU – 12-core Arm Cortex-A78AE v8.2 64-bit processor with 3MB L2 + 6MB L3 cache GPU / AI accelerators NVIDIA Ampere architecture with 2048 NVIDIA CUDA cores and 64 Tensor Cores @ 1.3 GHz DL Accelerator – 2x NVDLA v2.0 Vision Accelerator […]

OpenNCC Nighthawk – A face blurring AI camera based on Myriad X VPU

We’ve just written about OpenCV Ai Kit Lite computer vision camera based on Intel Myriad X VPU, and OpenNCC Nighthawk is another such programmable camera based on the Intel AI accelerator, but with an IR filter for night vision, and working with OpenNCC-SDK notably supporting real-time face blurring for enhanced privacy. OpenNCC Nighthawk specifications: VPU – Intel Movidius Myriad X MA2085 up to 4 TOPS RAM – 8 Gbits (1GB) LPDDR4 Camera 2MP camera up to 1920 x 1080 @ up to 30fps ~114° Field of View (DFOV) 2.2mm focal length Lens TTL (through the lense) – 24mm Mount – M12 x 0.5mm thread size Day&Night IR Filter – Solenoid excitation type, automatically switch between 0.1~2 lux IR LED – 850nm up to 5m Output Data format – YUV420, YUV422, MJPG, H.264 Misc – Reset, GPIO Host Interface – USB 3.1 TYPE-C port Temperature Range – 0°- 50° The camera […]

OpenCV AI Kit Lite – A compact 4K Tri-camera kit for computer vision applications (Crowdfunding)

The OpenCV AI Kit “OAK-D” now has a little brother with the OpenCV AI Kit Lite equipped with the same Intel Myriad X-based DepthAI solution with three cameras, but in a much compact form factor and a price slashed to as low as $79 and up. Like its predecessor, the OpenCV AI Kit leverage the Myriad X AI accelerator’s capabilities to provide a wide range of real-time computer vision applications, and can be programmed with C++ or Python APIs, as well as graphical user interfaces. OpenCV AI Kit Lite (OAK-D Lite) specifications: Intel Myriad X-based DepthAI with 4 TOPS of AI performance Cameras (made by ArduCam) Color Camera IMX214 (PLCC) with 4208×3120 resolution,  1.348:1 aspect ratio 1/3.1 inch Lens size 81.3 degrees DFOV Focus range 8cm – ∞ Stereo Camera specifications: Omnivision OV07251-G04A-1E (COB) with  640 x 480 resolution, 1.333:1 aspect ratio 1/7.5 inch lens size DFOV: 85.6,HFOV: 72.9, VFOV: […]

UP Squared Pro SBC gets more I/Os, 3x M.2 sockets, TPM 2.0 security chip

UP Squared Apollo Lake SBC was launched in 2016 via a crowdfunding campaign with a price starting at just 89 Euros for the model with 2GB RAM 16GB storage, and a dual-core Intel Celeron N3350 processor. AAEON has now announced an update simply called UP Squared Pro with many of the same features, but greater expandability and I/O features, for example, to add 5G modules and AI accelerators through one of the three M.2 sockets, as well as improved security via a TPM 2.0 chip. UP Squared Pro (UPN-APL01) specifications with highlights in bold or strikethrough in comparison to the UP Squared specifications (in 2016): SoC (one or the other) Intel Celeron N3350 dual-core “Apollo Lake” processor @ 1.1 GHz / 2.4 GHz with 12 EU Intel HD graphics 500 @ 200 MHz / 650 MHz (6W TDP) Intel Pentium N4200 quad-core “Apollo Lake” processor @ 1.1 GHz / 2.5 […]

megaAI 4K AI Camera Board Features Movidius Myriad X VPU (Crowdfunding)

megaAI 4K AI camera board reminds me of Kendryte K210 based boards such as Maixduino used for computer vision for tasks such as object tracking or face recognition, but instead of just handling QVGA at around 15 to 18 fps, megaAI can supports inference at 4K resolution up to 30 fps. The tiny board can achieve this feat by leveraging the 4 TOPS of AI processing power delivered by Intel Movidius Myriad X VPU (Vision Processing Unit) while consuming only around 2.5 Watts. megaAI board specifications: AI Accelerator – Intel Movidius Myriad X VPU delivering up to 4 TOPS (Trillion Operations Per Second) Camera – 12 MP 4056×3040 Auto-Focus (8cm-∞) camera with 81 degrees  horizontal Field of View (HFOV) Video RAW Output – 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 […]

ADLink Launches Vizi-AI Development Starter Kit for Industrial Machine Vision & Artificial Intelligence

ADLINK has recently launched Vizi-AI development starter kit for industrial machine vision and artificial intelligence (AI) at the edge in collaboration with Intel and Arrow Electronics. Vizi-AI is comprised of a carrier board that looks to be the same as used in the company’s I-Pi SMARC development kit equipped with an Intel Movidius Myriad X VPU and combined with LEC-AL Intel Atom Apollo Lake SMARC computer module. Vizi-AI SBC Let’s have a look at the hardware features and specifications of Vizi-AI SBC (aka VIZI-AI LEC-AL-E3940-AI-4G-32G): SoC – Intel Atom x5-E3940 quad-core Apollo Lake-I processor @ up to 1.6 / 1.8 GHz (Turbo) with 12EU Intel HD Graphics 500; 9.5W TDP System Memory – 4GB LPDDR4 (Option up to 8GB) Storage – 1x MicroSD card slot AI Accelerator – Intel Movidius Myriad-X VPU (Vision Processing Unit) Video – 1x HDMI port, single-channel LVDS/eDP interface via flat cable Audio – On-carrier audio […]

Gen 3 Intel Movidius “Keem Bay” VPU Introduced at 2019 Intel AI Summit

Intel made announcements about upcoming AI solutions at 2019 Intel AI Summit. Those include Intel Nervana Neural Network Processors (NNP) for training (NNP-T1000) and inference (NNP-I1000) for cloud and data center customers, as well as Gen 3 Intel Movidis “Keem Bay” VPU. We’ll focus on the latter in this post with Intel claiming similar performance as NVIDIA Jetson AGX Xavier at much lower power consumption with claims of up to 4.7 times more power efficiency when using ResNet-50 benchmark inference measurement using INT8 with a batch size of 1. Considering Jetson Xavier AGX has a ~30W power budget, that would mean Movidius “Keem Bay” consumes around 6 Watts.  Compared to Myriad X MA2085, the new Gen3 VPU is said to have more than 10 times the inference performance. Intel did not provide any TOPS figure, but considering the company announced 1 TOPS of neural compute performance for Myriad X, one […]

Atomic Pi x86 SBC Meets Intel Neural Compute Stick 2 in $99 Neural Computing DevKit (Crowdfunding)

IoT Team launched the $34 Atomic Pi SBC powered by an Intel Atom x5-Z8350 processor via a Kickstarter campaign last December. At the time, it only ships to the US, and looked too good to be true. But the thing is real coming from a failed robotics project, and the low-cost x86 board went back for sale via Amazon and other channels with worldwide availability last spring. The price has even gone a bit lower as you’ll find it for $32.95 on Amazon. Note that it requires some technical skills to get started and with 16GB eMMC flash it only supports Liux distributions such as Ubuntu 18.04, and installing Windows 10 is possible, but you’ll be seriously limited. Atomic Pi is back in the news, as IoT Team has now launched another Kickstarter campaign for the board, except it’s not sold standalone, but instead as part of a $99 neural […]