Microchip SAMA7G54 is a single-core Arm Cortex-A7 microprocessor for low power AI camera & audio applications

SAMA7G54 evaluation kit

Microchip has just announced the 1 GHz SAMA7G54 single-core Arm Cortex-A7 microprocessor (MPU) with MIPI CSI-2 and parallel camera interfaces, as well as up to four I2S, one SPDIF transmitter and receiver, and a 4-stereo channel audio sample rate converter. The company specifically launched a single-core processor to offer a lower power solution for AI camera and audio solutions, and the chip is coupled with the MCP16502 power management IC that has been optimized to provide the best power/performance ratio for the SAMA7G54. Microchip SAMA7G54 specifications: CPU – Arm Cortex-A7 based MPU @ up to 1GHz with 256KB L2 cache Memory – DDR2/DDR3/DDR3L/LPDDR2/LPDDR3 up to 533MHz Storage – Quad SPI, Octal SPI, 3x SD/eMMC Camera I/F – MIPI CSI-2 (2-lane up to 1.5 Gbps each) and 12-bit parallel camera Up to 8 Mpixel @ 30 fps Audio – Up to 4x I2S, PDM, SPDIF (Rx/Tx), 4 stereo channel ASRC Networking […]

Axiomtek AIE900-XNX – A 5G connected fanless Edge AI system for AMR, AGV, and computer vision

Axiomtek AIE900-XNX

Axiomtek AIE900-XNX is a fanless Edge AI computing system powered by NVIDIA Jetson Xavier NX system-on-module designed for autonomous mobile robots (AMR), automated guided vehicles (AGV), and other computer vision applications. The system delivers up to 21 TOPS thanks to the 6-core NVIDIA Carmel ARM v8.2 (64-bit) processor, NVDLA accelerators, and 384-core NVIDIA Volta architecture GPU found in the Jetson Xavier NX module. The AIE900-XNX Edge AI computer also comes with a 5G module for high-speed cellular connectivity and supports SerDes, PoE, and MIPI CSI cameras for video processing. Axiomtek AIE900-XNX specifications: NVIDIA Jetson Xavier NX system-on-module with CPU – 6-core NVIDIA Carmel Armv8.2 64-bit CPU with 6 MB L2 + 4 MB L3 cache GPU – 384-core NVIDIA Volta GPU with 48 Tensor Cores AI Accelerator – 2x NVDLA System Memory – 8GB 128-bit LPDDR4x onboard Storage – 16GB eMMC flash Storage –  M.2 Key M 2280 with PCIe […]

Orbbec Persee+ 3D AI camera runs Ubuntu or Android on Amlogic A311D processor

Orbbec Persee+ 3D AI camera

Orbbec Persee+ is a 3D depth camera running Linux with AI capabilities thanks to Amlogic A311D hexa-core processor equipped with a 5 TOPS NPU (Neural-network Processing Unit). The Persee+ is designed to help researchers, engineers, and hobbyists implement advanced uses for 3D imaging. Orbbec has been around for several years with the first product we covered here being the Orbbec Persee 3D depth camera running Ubuntu or Android on Rockchip RK3288 processor and unveiled in 2015. Last year, the company introduced the Zora P1 Amlogic A311D development board for Orbbec 3D cameras, so in a way, the Orbbec Persee+ is born from the work done on the Persee camera and Zora P1 over the years. Orbbec Persee+ 3D AI camera specifications: SoC – Amlogic A311D hexa-core processor with 4x Cortex-A73 cores, 2x Cortex-A53 cores, Arm Mali-G52MP4 GPU, 5 TOPS NPU System Memory – 4GB RAM Storage – 8GB (specs) / […]

Axzez Interceptor carrier board for RPi CM4 gets 8-port PoE+ board

Raspberry Pi CM4 8-port PoE expansion

The features-rich Axzez Interceptor carrier board for Raspberry Pi CM4 has gotten the Interceptor PoE board with eight PoE+ ports for connecting up to sixteen PoE IP cameras making it usable as a network video recorder. We first wrote about the Interceptor last January noting its impressive I/O capabilities with five SATA ports, four Gigabit Ethernet, two HDMI ports, RS-485 terminal block, and more. It also had two 40-pin FFC connectors “for future expansion”. Those connectors have now found a “meaning to life” with the Interceptor PoE board, as up to two can be connected to the FFC connectors. Some of the features of the new Interceptor PoE Board include: 8x fast PoE+ ethernet ports IEEE 802.3AF-2003 and 802.3AT-2009 compliance Each port has activity/link and status LEDs Input voltage range – 44-57V Optional 48V power boost that can support up to two Interceptor PoE+ boards (Powered from 12V ATX power […]

Qualcomm Edge AI Vision kit combines Qualcomm QCS610 SoC & Sony IMX415 4K ultra low light camera

Qualcomm Edge AI Vision kit

e-con Systems has recently launched the qSmartAI80_CUQ610, a Qualcomm Edge AI vision kit based on Qualcomm QCS610 octa-core Cortex-A76/A55 processor and featuring a camera module based on Sony STARVIS IMX415 4K ultra low light sensor. The kit is comprised of a QCS610 module with 4GB RAM and 16GB eMMC flash and carrier board designed by VVDN Technologies, as well as e-con Systems 4K camera module, and designed to run vision machine learning and deep learning models at the edge. qSmartAI80_CUQ610 “Qualcomm Edge AI Vision kit” specifications: System-on-Module SoC – Qualcomm QCS610 octa-core processor with 2x Kryo 460 Gold cores @ 2.2 GHz (Cortex-A76 class), and 6x Kryo 430 Silver low-power cores @ 1.8GHz (Cortex-A55 class), Adreno 612 GPU @ 845 MHz, with OpenGL ES 3.2, Vulkan 1.1, OpenCL 2.0, Hexagon DSP with Hexagon Vector eXtensions (HVX),  Spectra 250L ISP, 4Kp30 VPU H.265 encode/decode; Note: Qualcomm QCS410 SoC is available upon […]

Maple Eye ESP32-S3 board offers 2MP camera, microphone, and two LCD displays

Maple Eye ESP32-S3 camera displays

AnalogLamb Maple Eye ESP32-S3 is a WiFi and Bluetooth connected board based on ESP32-S3 dual-core Xtensa LX7 microcontroller and equipped with one 2MP camera, one microphone, and two LCD displays placed on each side of the board. Those features, plus 8MB of flash and an 8 MB Octal PSRAM, allow the board to make good use of ESP32-S3 AI instructions through the ESP-DL library found in ESP-WHO framework in order to speed up face detection and recognition algorithms, or for audio processing. Maple Eye ESP32-S3 specifications: Wireless module – ESP32-S3-WROOM-1 module with ESP32-S3 dual-core Xtensa LX7 processor @ up to 240 MHz integrating vector instructions  for AI acceleration, 512 KB SRAM, 8MB PSRAM & 8MB Octal SPI Flash Storage – MicroSD card interface Displays – 2x 1.3-inch TFT LCD displays, selectable by switch Camera – 2MP OV2640 camera Audio – Digital microphone for VAD (voice activity detection) & ASR (automatic […]

Arducam Pi Hawk-eye is a 64MP camera for Raspberry Pi 4/CM4

64MP camera raspberry pi

Arducam Pi Hawk-eye is a 64MP “ultra-high resolution” camera for Raspberry Pi 4 or CM4 with built-in autofocus following the company’s 16MP autofocus camera introduced at the end of last year. The new camera module will allow you to take still images at up to 9152 x 6944 resolution, but videos will still be limited to 1080p30 on the Raspberry Pi 4. The Pi Hawk-eye is also compatible with the official Raspberry Pi v1/v2 cameras, meaning you can reuse your enclosures/mounts, and keep on using the same software, for instance, libcamera. Arducam Pi Hawk-eye specifications: Sensor – Sensor with 9152 x 6944 pixels resolution Still resolution – 64MP Video modes On Raspberry Pi – 1080p30, 720p60, and 640×480 @ 60/90fps Camera module – 1280×720 @ 120 fps, 1080p60, 2312×1736 @ 30 fps, 3840×2160 @ 20 fps, 4624×3472 @ 10 fps, 9152×6944 @ 2.7 fps Optical size – 9.25mm diagonal (7.4×5.5mm) […]

Morse Micro MM6104, MM6108 Wi-Fi HaLow SoCs support up to 32.5 Mbps data rate

Morse Micro MM61xx

Australian company Morse Micro MM6104 and MM6108 Wi-Fi HaLow SoCs should offer some competition to the Newracom NRC chips found in all 802.11ah WiFi HaLow boards and devices released so far. Both MM610x chips have similar features, but the MM6104 SoC supports 1/2/4 MHz channel bandwidth for up to 15 Mbps data rate – just like the Newracom NRC7292 chip – while the more powerful MM6108 can handle a data rate of up to 32.5 Mbps thanks to 1/2/4/8 MHz channel bandwidth. MM6104/MM6108 specifications: Optional 32-bit RISC-V Host Applications Processor (HAP) Single-Chip IEEE802.11ah Wi-Fi HaLow transceiver for low-power, long-reach IoT applications Worldwide Sub-1 GHz frequency bands (850MHz to 950MHz) On-chip power amplifier with support for external PA option MM6104 – 1/2/4 MHz channel bandwidth for up to 15 Mbps data rate (Note: the datasheet reads “single-stream max data rate up to 40 Mbps”, but it appears to be a mistake […]