Boardcon RK1808 SBC Targets Smart Audio & Computer Vision Applications

RK1808 SBC

Rockchip RK1808 neural network processing unit was initially an IP Block inside RK3399Pro, but the company eventually launched RK1808 Cortex-A35 processor as a standalone solution now providing up to 3.0 TOPS for AI inferencing in modules, USB sticks, and development kits. Boardcon offers another option with EM1808, a Rockchip RK1808 SBC equipped with the processor. The board should be suitable for two main types of AI applications, namely smart audio applications thanks to four audio ports, speaker header, & an onboard 4-mic array, and computer vision with MIPI CSI & DSI interfaces. Boardcon EM1808 board is comprised of a baseboard and CPU module with the following overall specifications: SoC – Rockchip RK1808 dual Cortex-A35 processor up to 1.6GHz with 3.0 TOPS (for INT8) NPU, VPU supporting H.264 1080p60 decode, 1080p30 encode System Memory- 2GB LPDDR3 Storage – 8GB eMMC flash, MicroSD slot, M.2 NVMe SSD interface Display I/F – 26-pin […]

BreadBee is a Tiny Embedded Linux SBC based on MStar MSC313E Camera SoC (Crowdfunding)

BreadBee

There are plenty of tiny and compact Arm Linux SBC on the market from NanoPi NEO to Raspberry Pi Zero or Rock Pi S. But Daniel Palmer has been able to design an even smaller board – BreadBee – based on MStar MSC313E Cortex-A7 SoC since the processor also embeds 64MB RAM, or enough to run embedded Linux.BreadBee specifications: SoC – MStar MSC313E Arm Cortex-A7 processor @ ~1.0 GHz with NEON, FPU, 64MB DDR2 Storage – 16MB SPI NOR flash Networking – 10/100M Ethernet (RJ45) USB – 1x Micro USB 2.0 port Expansion 24-pin dual-row header (2.54mm pitch) with  SPI, I2C, 4x 10-bit ADC, 3x UART, GPIOs 21-pin header (1.27mm pitch) with SD/SDIO, USB 2.0, GPIOs Misc – RTC, Watchdog timer Power Supply – 5V via micro USB port Dimensions – 32 x 30mm Despite MStar MSC313E being a camera processor, the camera interface does not seem exposed in the […]

Grove Beginner Kit for Arduino Features Arduino UNO Compatible Board & Ten Pre-wired Modules

Grove Beginner Kit for Arduino

Arduino boards are great to get started with electronics has they offer an ecosystem of expansion modules and libraries, as well as tutorials, that may it easy to get started with almost any projects. Seeed Studio Grove is a family of standardized modules with 4-pin headers using digital I/O, analog I/O, UART or I2C interfaces and allowing you to easily connect to compatible board such as Seeeduino Lotus board. You still need to connect the Grove module via cables, so Seeed Studio decided to create a big board called Grove Beginner Kit for Arduino that features Seeduino Lotus at the center and ten pre-wired and detachable Grove modules so no cabling is required to get started apart from a USB cable. List of Grove Beginner Kit for Arduino board and modules: Seeeduino Lotus ATmega320p board compatible with Arduino UNO compatible board and featuring 12 Grove connectors 10 pre-wired modules without […]

DragonBoard 845c Android (AOSP) Reference Board Supports Open Source Graphics, Mainline Kernel

Robotics DragonBoard 845c AOSP

Besides the obvious Google Pixel and Nexus devices supported by AOSP (Android Open Source Project), we previously covered some single board computers that were also officially supported by the project with Hikey and Hikey 960 Android reference boards. Linaro Consumer Group (LCG) has just written about Qualcomm Snapdragon 845 based Dragonboard 845c board. It has been now an official Android reference board for a few months now, and it is the first such board with an open-source graphics stack thanks to Freedreno graphics driver and mesa framework. Since no proprietary blobs are required, the board’s full functionality can also be upstreamed into the mainline kernel, and Linaro currently uses the board as a test target for validating the mainline kernel and stable updates. Here’s a reminder of the board’s hardware specifications: SoC – Qualcomm Snapdragon 845 with 8x custom 64-bit ARMv8 CPUs up to 2.8 GHz, Adreno 630 GPU with […]

ESP32-Vaquita-DSPG Board and SDK Support Alexa Integration and AWS IoT Core Cloud Service

ESP32-Vaquita-DSPG

Espressif Systems has just announced another ESP32 board, namely ESP32-Vaquita-DSPG development kit together with an SDK that supports AVS (Alexa Voice Service) integration with AWS IoT cloud connectivity. ESP32-Vaquita-DSPG specifications: Wireless Module – ESP32-WROVER-E with ESP32-D0WD-V3 WiFi + Bluetooth SoC , 64 Mbit SPI flash and 64 Mbit PSRAM Audio DSP – DSPG DBMD5P Audio SoC with far-field voice recognition using the company’s HDClear algorithms. Power Amplifier for external speakers up to 8W Codec – ES8311 I2S audio codec Speaker connector 3.5mm audio jack 2-mic array on MIC board Debugging – USB-UART port Misc- Mainboard – Power LED, boot & reset buttons MIC board – 5x RGB LEDs, 2x function buttons Power Supply 5V input via USB Power Port 5V-to-3.3V regulator. ESP32-Vaquita-DSPG board needs an external 4-ohm speaker or a pair of headphones for audio output, two USB cables for power and debugging, and a computer running Windows, Linux, or […]

Widora TINY200 Allwinner F1C200s ARM9 Development Board Supports DVP Camera, Up to 512MB SD NAND Flash

Allwinner F1C200s ARM9 Development Board

Widora TINY200 is a tiny ARM9 development board equipped with Allwinner F1C200s with a DVP camera interface compatible with OV2640 / 5640 sensor, an audio amplifier, and various storage options from a 16MB SPI flash to a  512MB SD NAND flash. I first heard about the processor when I wrote about Microchip SAM9X60 ARM9 SoC last month, and some people noted there were other fairly new ARM9 SoCs around such as Allwinner F1C200s that also includes 64MB RAM so you can run Linux without having to connect external memory chips. Widora TINY200 V2 specifications: SoC – Allwinner F1C200s ARM926EJS processor @ 400-600 MHz (Overclockable to 900 MHz) with 64MB DDR1 RAM Storage – 16MB SPI NOR flash or 128MB NAND flash and MicroSD card slot or 512MB SD NAND flash. Display I/F – 40-pin RGB FPC cable for resistive touch screens; additional 6-pin FPC cable for capacitive touch support Camera […]

ESP32-S2-Saola-1 Development Board is Now Available for $8

ESP32-S2-Saola-1 Board

Espressif ESP32-S2 WiFi SoC mass production started at the end of February 2020,  and soon enough we started to find ESP32-S2 SoC and modules for $1 to $2 on sites like Digikey, but so far we had not seen ESP32-S2 development boards for sale. The good news is the breadboard-friendly ESP32-S2-Saola-1 development board has started to show up for $8 on resellers such as Mouser and Digikey albeit with a lead time of 8 to 12 weeks. ESP32-S2-Saola-1 specifications: Supported modules – ESP32-S2-WROOM(-I) & ESP32-S2-WROVER(-I) with 4 MB SPI flash and for ESP32-S2-WROVER modules only, 2 MB PSRAM USB – 1x Micro USB port for power and programming / debugging via USB-to-UART bridge Expansion – 2x 20-pin I/O headers with SPI, I2S, UART, I2C, touch sensors, PWM, etc… Misc – Boot and reset buttons, RGB LED, 3.3V power on LED Power Supply (3 methods) 5V via Micro USB port (default) […]

Edgeless EAI-Series Dual Arm Cortex-M4 MCU Features a 300 GOPS CNN-NPU

Edgeless EAI80 Development Board

Microcontrollers will have an important role to play in AIoT (AI + IoT) applications as they provide the lowest cost and power consumption. Performance is limited but we start seeing MCUs with AI accelerators such as GreenWaves GAP9 multi-core RISC-V microcontroller or Kendryte K210 RISC-V MCU with a KPU AI accelerator. Another option is by Edgeless Semiconductor Co. Ltd (零边界集成电路有限公司) based in Zhuhai, China, and more specifically its Edgeless EAI-Series dual-core Arm Cortex-M4 microcontrollers equipped with a 300 GOPS CNN NPU. Edgeless EAI specifications: CPU – Dual Arm Cortex-M4F @ up to 200Mhz, with DSP instructions, I/D cache for high performance; 500DMIPS/1.25DMIPS/MHz (Dhrystone2.1) AI Accelerator – CNN-NPU clocked at up to 300MHz with 300 GOPS peak throughput; 144MAC/cycle, EER up to 1TOPS/W, for image recognition scenario. Support major CNN Models including Resnet-18, Resnet-34, Vgg16, GoogleNet, Lenet, etc.. Support Convolutional kernel size 1~7 Support Channel/Feature No. up to 512 Support Max/Average […]