artificial intelligence

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on NVIDIA Jetson Nano Powered Edge AI System Supports one PoE Camera, Operates in -30 to +60°C Temperature Range

NVIDIA Jetson Nano Powered Edge AI System Supports one PoE Camera, Operates in -30 to +60°C Temperature Range

NVIDIA Jetson Nano PoE Camera edge AI system

Axiomtek AIE100-903-FL is a fanless edge AI System powered by NVIDIA Jetson Nano system-on-module and designed to connect a single 15W PoE camera for AI computing, edge computing, smart retail, smart city, and more. The solution can operate in a wide range of temperatures from -30°C to +60°C and comes with an optional IP42-rated waterproof cover kit that makes it suitable for use in moist places and “semi-outdoor environments”  including freezers and under eaves (edges of the roof which overhang the face of a wall) and other outdoor locations with some protection against rain. Axiomtek AIE100-903-FL specifications: SoM – NVIDIA Jetson Nano with quad-core Arm Cortex-A57 processors, 128 CUDA core NVIDIA Maxwell GPU, 4GB 64-bit LPDDR4 and 16GB eMMC flash Storage – 1x M.2 Key M 2280 with PCIe x4 NVMe SSD slot, 1x Micro SD slot Video Output – 1x HDMI 2.0 up to 4K2K @ 60 Hz Connectivity […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 2 Comments on ROScube Pico SBC Runs Ubuntu & ROS on Intel Atom or Rockchip PX30 Processor

ROScube Pico SBC Runs Ubuntu & ROS on Intel Atom or Rockchip PX30 Processor

RoScube Pico SBC Devkit

ADLINK has launched ROScube Pico SBC designed for robotics projects and powered by either an Intel Atom x5 Apollo Lake processor or a Rockchip PX30 Arm Cortex-A35 processor via their SMARC-compliant system-on-modules namely LEC-AL and as LEC-PX30. Both models run Ubuntu and ROS/ROS-2 operating systems simultaneously, and the company also provides NeuronBot robotics development and demo kit based on the SBC. ROScube Pico SBC and Devkit If ROScube Pico looks similar it’s because it appears to be based entirely on ADLINK previously announced ADLINK Industrial-Pi (I-Pi) SMARC Development Kit based on Rockchip PX30, and Vizi-AI development starter kit based on Atom x5-E3940 SoC and Movidius Myriad X VPU. Those are the specifications listed for ROScube Pico: SMARC Module For ROScube Pico NPS-1 – LEC-AL with Intel Atom processor, Intel Movidius Myriad X AI accelerator, 8GB LPDDR4 RAM, 32GB eMMC For ROScube Pico NPS-4 – LEC-PX30 with Rockchip PX-30 quad-core Cortex-A35 […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on TTGO T-Watch K210 / K210 AIOT Watches Perform Face Detection with Kendryte K210 RISC-V Processor, ESP32 WiSoC

TTGO T-Watch K210 / K210 AIOT Watches Perform Face Detection with Kendryte K210 RISC-V Processor, ESP32 WiSoC

TTGO-Watch-K210

After covering ESP32 based TTGO T-Watch-2020 programmable watch last month, I noticed LilyGO launched “TTGO T-Watch K210 AIOT” watch with Kendryte K210 RISC-V AI SoC and a camera for face detection and recognition, and while searching for information, I discovered another apparently similar “TTGO T-Watch K210“. But let’s look into the specifications to find out what the differences are. I first came across TTGO T-Watch K210 AIOT, so let’s have a look at some preliminary specifications for this model: AI Processor – Kendryte K210 RISC-V Dualcore 64bit with FPU with 8MB SRAM Storage – 16MB QSPI flash, MicroSD card socket Display I/F – FPC connect for external display (not included) Camera – 2MP OV2640 sensor Audio – MAX98357A Audio codec; CVSD & SBC audio encoding Connectivity – 2.4 GHz 802.11b/g/n WiFi 4 up to 150 Mbps, Bluetooth 4.2 BR/EDR and BLE Debugging – USB-C port via CP2104 Expansion UART, SPI, […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 5 Comments on Samsung Exynos 880 SoC Targets Mid-Range 5G Smartphones

Samsung Exynos 880 SoC Targets Mid-Range 5G Smartphones

Samsung Exynos 880

5G used to be reserved for premium smartphones, but with processors such as Qualcomm Snapdragon 765G and Huawei/Hisilicon Kirin 820, 5G cellular connectivity is also coming to mid-range smartphones. Samsung Exynos 880 brings another option to the mid-range 5G handsets market. The octa-core Cortex-A77/A55 mobile processor comes with a Mali-G76 GPU, an NPU and a DSP for on-chip AI acceleration, and supports 5G downloads up to 3.55 Gbps, uploads up to 1.38 Gbps. Samsung Exynos 880 specification: CPU – Dual-core Cortex-A77 processor @ 2.0GHz, hexa-core Cortex-A55 processor @ 1.8 GHz GPU – Arm Mali-G76 MP5 On-Device AI – Neural processing unit (NPU) and digital signal processor (DSP) System Memory Type – LPDDR4x Storage I/F – UFS 2.1, eMMC 5.1 Display – Up to Full HD+ (2520×1080) resolution Camera – Single-camera up to 64MP, Dual-camera up to 20MP+20MP Video – 4K UHD 30fps encoding and decoding with HEVC/H.265, H.264, and VP9 […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 18 Comments on Arm Announces Cortex-A78 CPU, Mali-G78 GPU, Ethos-N78 NPU and Custom Cortex-X1 Core

Arm Announces Cortex-A78 CPU, Mali-G78 GPU, Ethos-N78 NPU and Custom Cortex-X1 Core

Arm Cortex A78

Arm has just announced its 2020 Arm Mobile IP portfolio with no less than five IP blocks including Arm Cortex-A78 CPU, Arm Mali-G78 and G68 GPUs, Arm Ethos-N78 neural processing unit, and the custom Cortex-X program starting with Cortex-X1, the most powerful Arm core to date. Arm Cortex-A78 CPU Cortex-A78 highlights: Architecture –  Armv8-A (Harvard) Extensions – Armv8.1, Armv8.2, Cryptography, and RAS; Armv8.3 (LDAPR instructions only) ISA support – A64, A32, and T32 (at EL0 only) Microarchitecture Pipeline – Out of order Superscalar Neon / Floating Point Unit Optional cryptography Unit Max number of CPUs in cluster – 4 Physical Addressing (PA) – 40-bit Memory system and external interfaces 32KB to 64KB L1 I-Cache / D-Cache 256KB to 512KB L2 Cache Optional 512KB to 4MB L3 Cache ECC and LPAE support Trustzone security Cortex-A78 delivers 20% extra performance compared to Cortex-A77 at the same power budget (one Watt), but peak […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on UP Xtreme Smart Surveillance Combines Whiskey Lake SBC, Myriad X VPUs, and Video Management & Analytics Software

UP Xtreme Smart Surveillance Combines Whiskey Lake SBC, Myriad X VPUs, and Video Management & Analytics Software

UP Xtreme Smart Surveillance

We’re seeing more and more computer vision products with built-in artificial intelligence accelerated features like face recognition or object detection including AI cameras, facial recognition systems, and AI NVR systems. It’s great as a consumer because of less frequent and more accurate alerts in security camera systems but more worrying as a citizen due to mass surveillance. But the trend is here to stay, and AAEON has just announced the UP Xtreme Smart Surveillance solutions powered by UP Extreme Whiskey Lake SBC with either an Intel Core i5-8365UE or Intel Core i7-8665UE processor, as well as two Intel Movidius Myriad X VPUs using OpenVINO SDK. The system also leverages Milestone video management software (VMS) and SAIMOS video analytics software. Based on the photo above, the hardware looks to be UPX-Edge Embedded Computer which we previously covered in details at launch last December. Instead of hardware, the focus of Up Xtreme […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on megaAI 4K AI Camera Board Features Movidius Myriad X VPU (Crowdfunding)

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

megaAI Myriad X board

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 […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 33 Comments on iWave Systems i.MX8M Mini Devkit Targets Low-cost Facial Recognition Systems

iWave Systems i.MX8M Mini Devkit Targets Low-cost Facial Recognition Systems

iwave systems imx8m mini devkit

iWave Systems i.MX8M Mini Board is a development platform based on an update versions of the company’s iW-RainboW-G34M-SM i.MX 8M Mini system-on-module and designed specifically for low-cost facial recognition systems thanks to NXP eIQ ML software, and MIPI display and camera. iWave Systems i.MX8M Mini (aka iW-RainboW-G34D) specifications: SoM SoC – NXP i.MX8M Mini Q/QL/D/DL/S/SL with up to 4x Cortex-A53 cores,  1x Cortex-M4F real-time core, Vivante 3D and 2D GPUs System Memory – 1GB LPDDR4 (Expandable up to 4GB) Storage – 8GB eMMC Flash (Expandable), optional 2MB QSPI Flash optional Micro SD slot Wireless – Dual-band 802.11a/b/g/n/ac WiFi 5 and Bluetooth 5.0. PMIC – BD71847AMWV i.MX8M SODIMM Carrier Board Storage – MicroSD slot Display I/F – MIPI DSI display connector Camera I/F – MIPI CSI camera connector Audio – Audio codec, 3.5mm Line In/Out jack Networking – Up to 2x Gigabit Ethernet ports (One is Optional) USB – 2x USB […]