Posted on by Jean-Luc Aufranc (CNXSoft) - 2 Comments on AAEON BOXER-8220AI Embedded Box PC Features NVIDIA Jetson Nano, 5 Gigabit Ethernet Ports

AAEON BOXER-8220AI Embedded Box PC Features NVIDIA Jetson Nano, 5 Gigabit Ethernet Ports

Jetson Nano Embedded Mini PC

AAEON has launched several AI Boxer-8000 series embedded box PCs based on Intel processors plus AI accelerator, or NVIDIA Jetson TX2. The company has now introduced a new model – BOXER-8220AI – based on NVIDIA Jetson Nano module, and equipped with five Gigabit Ethernet ports. AAEON BOXER-8220AI specifications: SoM (CPU/Memory/Storage) – NVIDIA Jetson Nano with quad-core Arm Cortex-A57 MPCore processor @ 1.43 GHz, 128-core Maxwell GPU. 4GB LPDDR4, 16GB eMMC flash or MicroSD card Video Output – HDMI 2.0 Connectivity – 5x Gigabit Ethernet ports USB – 4x USB 3.0 ports, 1x Micro USB to flash the OS Serial – 2x RS-232 Misc – Power button, recovery button, power LED Power Supply – 10-24V DC via 2-pin terminal block Dimensions – 154 x 101 x 30 mm Weight – 1 kg Temperature Range – Operating: -20°C ~ 60°C, according to IEC60068-2 with 0.5 m/s AirFlow; storage: -45°C ~ 80°C Storage Humidity – 95% @ 40°C, non-condensing Anti-Vibration – 3 Grms/ …

Continue reading… “AAEON BOXER-8220AI Embedded Box PC Features NVIDIA Jetson Nano, 5 Gigabit Ethernet Ports”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Jean-Luc Aufranc (CNXSoft) - 2 Comments on NVIDIA Jetson Nano Review with 52Pi ICE Tower Cooling Fan – Part 1: Unboxing

NVIDIA Jetson Nano Review with 52Pi ICE Tower Cooling Fan – Part 1: Unboxing

Jetson Nano Review with ICE Tower Cooling Fan

If you remember soon after Raspberry Pi 4 launch, there were talks about the SBC overheating under load, and depending on room temperature and workload a heatsink may be needed for the board to perform optimally at all times. This gave birth to “interesting” solutions such as 52Pi ICE Tower Cooling Fan, an oversized cooling solution for Raspberry Pi 4. It does the job however, and it allows me to overclock Raspberry Pi 4 to 2.0 GHz while keeping the CPU temperature under 55°C in a room at 28°C. But the latest Raspberry Pi Foundation board is not the only SBC to suffer from overheating, as at least one user noticed the board would just shutdown under load. The solution was to switch from 10W mode to 5W mode, not an ideal solution since it’s also lowering performance. But 52Pi is coming to the rescue again, as they adapted their ICE tower cooling fan to Jetson Nano SBC. Seeed Studio …

Continue reading… “NVIDIA Jetson Nano Review with 52Pi ICE Tower Cooling Fan – Part 1: Unboxing”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Jean-Luc Aufranc (CNXSoft) - 4 Comments on NVIDIA Jetson Xavier NX SoM Delivers up to 21 TOPS for AI Workloads at the Edge

NVIDIA Jetson Xavier NX SoM Delivers up to 21 TOPS for AI Workloads at the Edge

NVIDIA Jetson Xavier NX

NVIDIA has just announced Jetson Xavier NX system-on-module, with the company claiming it is the “world’s smallest, most powerful AI supercomputer for robotic and embedded computing devices at the edge” with a 70x45mm “Jetson Nano” form factor, and delivering either up to 14 TOPS at 10 Watts or 21 TOPS at 15 Watts. The company expects the module to be used in small commercial robots, drones, intelligent high-resolution sensors for factory logistics and production lines, optical inspection, network video recorders, portable medical devices, and other industrial IoT systems. Jetson Xavier NX specifications: SoC – NVIDIA Xavier with 6-core NVIDIA Carmel ARM v8.2 64-bit CPU, 6MB L2 + 4MB L3 caches, and a 384-core NVIDIA Volta GPU with 48 Tensor Cores, 2x NVDLA deep learning accelerators delivering up to 21 TOPS at 15 Watts System Memory – 8 GB 128-bit LPDDR4x @ 51.2GB/s Storage – 16 GB eMMC 5.1 flash Video Encode 2x464MP/sec 2x 4K @ 30 (HEVC) 6x 1080p @ …

Continue reading… “NVIDIA Jetson Xavier NX SoM Delivers up to 21 TOPS for AI Workloads at the Edge”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Stephen Vicinanza - No Comments on AuverCare is a Predictive AI 24/7 Monitor for Patients and Elderly

AuverCare is a Predictive AI 24/7 Monitor for Patients and Elderly

AI Patient Monitoring System

Information on the Internet for Monitoring Patients and Elderly  If you are in the healthcare field or caring for an elderly or disabled person, you know all about trying to keep them safe. The internet is crowded with camera and audio monitors, wearable fall alert alarms, and the emergency services connected panic button. All these devices have one problem, they only work after there is a problem. What is Predictive AI? There has been a great deal of chatter since the 2016 announcement of a future predicting AI platform.  The article reported on this platform was Predicting the Future – especially use cases such as falls by the elderly. With the advances in the field of AI and object recognition and behavior that is based on data gathered from a variety of sensors, it is not really a stretch to see a predictive healthcare monitor come onto the scene. Predictive Model Used in AuverCare The predictive model is now forming …

Continue reading… “AuverCare is a Predictive AI 24/7 Monitor for Patients and Elderly”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Jean-Luc Aufranc (CNXSoft) - 17 Comments on NVIDIA Launches Upgraded Shield TV with Tegra X1+ Processor

NVIDIA Launches Upgraded Shield TV with Tegra X1+ Processor

Shield TV 2019 vs Shield TV Pro 2019

Ever since NVIDIA launched the Shield TV in 2015 it features in lists of best Android TV boxes in the $200 budget range, although it can raise to close to $300 if you do not live in a country where the Shield TV is not officially sold. The company launched a more compact version in 2017, and NVIDIA just officially announced upgraded Shield TV and Shield TV Pro 2019 models with a more powerful Tegra X1+ Processor delivering a 25% boost, as well as  Dolby Atmos and Dolby Vision support. As you can see from the photo above the Shield TV now has a completely different cylindrical design, while the Shield TV Pro keeps the traditional design of the box. However, both share many of the same specifications: SoC – NVIDIA Tegra X1+ processor with a 256-core NVIDIA GPU Memory & Storage Shield: 2 GB RAM; 8GB eMMC flash; MicroSD card slot Shield Pro: 3GB RAM; 16GB eMMC flash; MicroSD card …

Continue reading… “NVIDIA Launches Upgraded Shield TV with Tegra X1+ Processor”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Stephen Vicinanza - 2 Comments on STEEReoCAM is a 3D Stereo Camera for NVIDIA Jetson Nano, TX2, & AGX Xavier Dev Kits

STEEReoCAM is a 3D Stereo Camera for NVIDIA Jetson Nano, TX2, & AGX Xavier Dev Kits

STEEReoCam 2MP 3D Stereo Camera The latest e-con systems camera added to the lineup is the STEEReoCam. A 2MP 3D MIPI compliant stereo camera that works with the NVIDIA Jetson Nano, AGX Xavier, and Jetson TX2 development kits.   Improved Overall Function The camera has greater accuracy and depth range, with an OmniVision 1/2.9″ OV2311 global shutter CMOS sensor.  And the STEEReoCam comes bundled with CUDA the proprietary accelerated stereo SDK, that uses the GPU in the NVIDIA Tegra processors. AI and IoT Applications The camera is targeted towards depth sensing, AVG, robotics, face and gesture recognition, drones, medical procedure robots, and embedded visions. Software Development Kit e-Con Systems provides a Software Development Kit (SDK) package for the camera designed to work with NVIDIA Jetson development boards. The SDK is built on OpenCV 3.4.2 and CUDA Compute Capability 5.3/7.2/6.2. Sample Linux applications, some of which are shown in the video above, include TaraXL Parallel Viewer, TaraXL Studio Application, Save DepthMap …

Continue reading… “STEEReoCAM is a 3D Stereo Camera for NVIDIA Jetson Nano, TX2, & AGX Xavier Dev Kits”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Jean-Luc Aufranc (CNXSoft) - 33 Comments on TensorFlow Lite for Microcontrollers Benchmarked on Linux SBCs

TensorFlow Lite for Microcontrollers Benchmarked on Linux SBCs

TensorFlow Lite microcontrollers benchmark linux SBC

Dimitris Tassopoulos (Dimtass) decided to learn more about machine learning for embedded systems now that the technology is more mature, and wrote a series of five posts documenting his experience with low-end hardware such as STM32 Bluepill board, Arduino UNO, or ESP8266-12E module starting with simple NN examples, before moving to TensorFlow Lite for microcontrollers. Dimitris recently followed up his latest “stupid project” (that’s the name of his blog, not being demeaning here :)) by running and benchmarking TensorFlow Lite for microcontrollers on various Linux SBC. But why? you might ask. Dimitris tried to build tflite C++ API designed for Linux, but found it was hard to build, and no pre-built binary are available except for x86_64. He had no such issues with tflite-micro API, even though it’s really meant for baremetal MCU platforms. Let’s get straight to the results which also include a Ryzen platform, probably a laptop, for reference: SBC Average for 1000 runs  (ms) Ryzen 2700X (this …

Continue reading… “TensorFlow Lite for Microcontrollers Benchmarked on Linux SBCs”

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Posted on by Jean-Luc Aufranc (CNXSoft) - 2 Comments on Waveshare Jetbot AI Kit for NVIDIA Jetson Nano Board Sells for $100 and Up

Waveshare Jetbot AI Kit for NVIDIA Jetson Nano Board Sells for $100 and Up

NVIDIA Jetbot

NVIDIA Jetson Nano developer kit was launched for $99 last March with impressive specifications for the price including one module with four Arm Cortex-A57 cores, a 128-core Maxwell GPU, and 4GB LPDDR4 RAM. The company also introduced Jetbot robot based on the new board, with all instructions available on Github, but until now you had to put some efforts to build it up as the fairly long list of parts had to be purchased or 3D printed separately. It’s now become easier, as Waveshare has started selling their Jetbot AI kit on Amazon for $122.99 without Jetson Nano, and $259.99 with, meaning you may be better off purchasing NVIDIA board separately for around $100, or you may purchase the complete kit directly on Waveshare website for $215.99 plus shipping, or $99.99 without the SBC. Jetbot AI kit content: Optional NVIDIA Jetson Nano SBC 64GB micro SD Card Metal box Camera holder Acrylic piece Jetbot expansion board with battery holder, motor …

Continue reading… “Waveshare Jetbot AI Kit for NVIDIA Jetson Nano Board Sells for $100 and Up”

Support CNX Software – Donate via PayPal or become a Patron on Patreon