artificial intelligence

Posted on by Jean-Luc Aufranc (CNXSoft) - 3 Comments on Odyssey Blue mini PC bundle ships with Frigate open-source NVR, Coral USB AI accelerator

Odyssey Blue mini PC bundle ships with Frigate open-source NVR, Coral USB AI accelerator

Frigate NVR Odyssey Blue mini PC

Odyssey Blue mini PC based on the ODYSSEY-X86J4125 SBC is now offered as part of a bundle with Frigate open-source NVR platform with support for real-time local object detection, and an Coral USB AI accelerator. The Odyssey Blue mini PC is equipped with an Intel Celeron J4125 quad-core Gemini Lake Refresh processor, 8GB RAM, and a 128GB SSD preloaded with an unnamed Linux OS (probably Debian 11) and Frigate Docker container. The solution can run over object detection at 100+ FPS when equipped with a Coral USB accelerator. Since the hardware is not exactly new, and we’ve covered it in detail in the past, even reviewing the earlier generation SBC with Celeron J4105 processor and Re_Computer enclosure, I’ll focus on the software, namely Frigate NVR in this post. Frigate is an open-source NVR program designed for Home Assistant with AI-powered object detection that runs as a Docker container and uses […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on NVIDIA Jetson Xavier NX fanless embedded box PC features four HDMI input ports

NVIDIA Jetson Xavier NX fanless embedded box PC features four HDMI input ports

NVIDIA Xavier NX embedded box pc four HDMI inputs

AAEON BOXER-8256AI is a fanless embedded box PC equipped with an NVIDIA Jetson Xavier NX system-on-module, offering four HDMI input ports – two Full HD, two 4K capable -, as well as two HDMI outputs for smart healthcare equipment, digital signage, and entertainment. The embedded computer comes with 8GB RAM and a 16GB flash provided by the NVIDIA module, supports M.2 NVMe and SATA storage, Gigabit Ethernet, plus optional WiFI, 4G, and 5G cellular connectivity through M.2 sockets.   BOXER-8256AI specifications: SoM – NVIDIA Jetson Xavier NX with CPU – 6-core NVIDIA Carmel Armv8.2 64-bit CPU GPU – 384-core NVIDIA Volta GPU with 48 Tensor Cores AI accelerator – 2x NVDLA deep learning accelerators AI performance – Up to 21 TOPS at 15 Watts System Memory – 8GB LPDDR4x Storage – 16GB eMMC flash Storage – MicroSD Slot, M.2 NVMe SSD socket, SATA III port Display Interfaces – 2x HDMI […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on Intel Loihi 2 high-efficiency neuromorphic chip works with the Lava open-source framework

Intel Loihi 2 high-efficiency neuromorphic chip works with the Lava open-source framework

Intel Loihi 2

Neuromorphic AI accelerator chips relying on spiking neural networks (SNN), which we’ve seen from companies such as Innatera or Brainchip, will be used more and more in the future as they provide much higher efficiency compared to traditional deep neural networks (DNN) solutions. Intel is also working on SNN, and recently announced the Loihi 2 second-generation neuromorphic research chip with up to 1 million neurons (the human brain has 86 billion of those on average) that delivers up to 175x lower energy to learn a new object instance with similar or better speed and accuracy compared to conventional methods running on a central processing unit (CPU). The new Loihi 2 neuromorphic chip offers the following improvement over the first generation Loihi: Up to 10x faster processing capability (2x for simple neuron state, 5x for synaptic operations, 10x for spike generation) Up to 60x more inter-chip bandwidth achieved through a combination […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on $7 Lolin S3 ESP32-S3 board ships with MicroPython firmware

$7 Lolin S3 ESP32-S3 board ships with MicroPython firmware

Lolin S3 ESP32-S3 board

Lolin S3 is the first ESP32-S3 board from the company, but instead of using the more compact D1 mini form factor, the board features a longer design with two rows of 20 pins offering up to 31 GPIOs. Based on ESP32-S3-WROOM-1 module, the board features 16MB QSPI flash, 8MB SPRAM, two USB Type-C OTG and UART ports, a Lolin I2C port, an RGB LED, as well as Reset and user buttons. Lolin S3 specifications: Wireless module – ESP32-S3-WROOM-1 module with: Espressif Systems ESP32-S3 dual-core Tensilica LX7 @ up to 240 MHz with vector instructions for AI acceleration, 512KB RAM, 2.4 GHz WiFi 4 and Bluetooth 5.0 LE with support for long-range, up to 2Mbps data rate, mesh networking 16MB QSPI flash 8MB PSRAM PCB antenna USB – 2x USB Type-C ports, one OTG port, one UART port for programming and debugging Expansion 2x 20-pin headers with up to 31x GPIO, […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on LeapFive NB2 quad-core RISC-V processor comes with GPU, NPU, and DSP

LeapFive NB2 quad-core RISC-V processor comes with GPU, NPU, and DSP

LeapFive NB2 quad-core RISC-V processor

After SiFive and StarFive, here comes LeapFive RISC-V silicon vendor offering the NB2 quad-core 64-bit RISC-V application processor with GPU, NPU, and vision and audio DSPs capable of running Linux. LeapFive NB2 processor is equipped with MIPI DSI and LVDS display interface, dual GbE, USB 3.2/2.0 interfaces, and other peripheral interfaces that make it well-suited to a wide range of applications including Smart Home applications, robotics, industrial gateways, drones, building automation, smart cities, digital signage, medical equipment and more. LeapFive NB2 specifications: CPU – Quad-core SiFive U74 64-bit RISC-V processor @ 1.8 GHz delivering 2.5 DMIPS/MHz Cache – 32KB I-cache, 32KB D-cache, 2MB level 2 cache GPU – “High-performance graphics processor” @ 850 MHz DSP – Dedicated vision DSP, audio DSP NPU – Independent AI engine delivering up to 4 TOPS @ 1.4 GHz VPU – 4Kp60 H.264/H.265 Video encoding and decoding, JPEG image codec System Memory – Up to […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on AI, computer vision meet LoRaWAN with SenseCAP K1100 sensor prototype kit

AI, computer vision meet LoRaWAN with SenseCAP K1100 sensor prototype kit

Wio Terminal Grove Vision AI LoRaWAN module

CNXSoft: This is another tutorial using SenseCAP K1100 sensor prototype kit translated from CNX Software Thai. This post shows how computer vision/AI vision can be combined with LoRaWAN using the Arduino-programmable Wio Terminal, a Grove camera module, and LoRa-E5 module connecting to a private LoRaWAN network using open-source tools such as Node-RED and InfluxDB. In the first part of SenseCAP K1100 review/tutorial we connected various sensors to the Wio Terminal board and transmitted the data wirelessly through the LoRa-E5 LoRaWAN module after setting the frequency band for Thailand (AS923). In the second part, we’ll connect the Grove Vision AI module part of the SenseCAP K1100 sensor prototype kit to the Wio Terminal in order to train models to capture faces and display the results from the camera on the computer. and evaluate the results of how accurate the Face detection Model is. Finally, we’ll send the data (e.g. confidence) using […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 4 Comments on NVIDIA Jetpack 5.0.2 release supports Ubuntu 20.04, Jetson AGX Orin

NVIDIA Jetpack 5.0.2 release supports Ubuntu 20.04, Jetson AGX Orin

NVIDIA Jetpack 5.0.2 Ubuntu 20.04

The NVIDIA Jetpack 5.0.2 production release is out with Ubuntu 20.04, the Jetson Linux 35.1 BSP 1 with Linux Kernel 5.10, an UEFI-based bootloader, support for Jetson AGX Orin module and developer kit, as new as updated packages such as CUDA 11.4, TensorRT 8.4.1, cuDNN 8.4.1. NVIDIA Jetson modules and developer kits are nice little pieces of hardware for AI workloads, but the associated NVIDIA Jetpack SDK was based on the older Ubuntu 18.04 which was not suitable for some projects. But the good news is that Ubuntu 20.04 was being worked on and initially available through the Jetpack 5.0.0/5.0.1 developer previews, and NVIDIA Jetpack 5.0.2 SDK is the first production release with support for Ubuntu 20.04. Besides the upgrade to Ubuntu 20.04, the Jetpack 5.0.2 SDK also adds support for both the Jetson AGX Orin Developer Kit and the newly-available Jetson AGX Orin 32 GB production module. It still […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 7 Comments on AMD Ryzen Embedded 5000 Series CPUs show up in Micro-ATX motherboard

AMD Ryzen Embedded 5000 Series CPUs show up in Micro-ATX motherboard

AMD Ryzen Embedded 5000 Series motherboard

Advantech has announced the AIMB-522 industrial Micro-ATX motherboard with AMD Ryzen Embedded 5000 Series Zen3 processors for AI image processing in automation and surveillance applications. I had never heard about “Ryzen Embedded 5000 Series” processors, but that motherboard comes with a choice of new SKUs such as the 12-core Ryzen 5950E, the 10-core Ryzen 5900E, the 8-core Ryzen 5800E, and the 6-core Ryzen 5600E, as well as existing Ryzen 5000 desktop processors. AIMB-522 Micro-ATX motherboard specifications: Processor (one or the other) Ryzen 5950E 12-core processor @ up to 3.4 GHz with 64MB L3 cache; TDP: 105W Ryzen 5900E 10-core processor @ up to 3.7 GHz with 64MB L3 cache; TDP: 105W Ryzen 5800E 8-core processor @ up to 3.7 GHz with 32MB L3 cache; TDP: 100W Ryzen 5600E 6-core processor @ up to 3.6 GHz with 32MB L3 cache; TDP: 65W Ryzen 5950X 16-core processor @ up to 3.4 GHz […]