artificial intelligence News - Page 11 of 118 - CNX Software

September 9, 2024September 9, 2024 by Jean-Luc Aufranc (CNXSoft) - 10 Comments

Banana Pi BPI-CM5 Pro – A Rockchip RK3576-powered Raspberry Pi CM4 alternative with up to 16GB RAM, 128GB flash, a 6 TOPS NPU

Banana Pi BPI-CM5 Pro, also called ArmSoM-CM5, is a Rockchip RK3576 system-on-module electrically and mechanically compatible with the Raspberry Pi CM4 while offering up to 16GB LPDDR5 memory, 128GB eMMC flash, and a 6 TOPS AI accelerator embedded into the RK3576 SoC. It comes with a WiFi 6 and Bluetooth 5.3 wireless module, a PMIC for power management, and two 100-pin connectors mostly compatible with the pinout of the Raspberry Pi Compute Module 4. ArmSoM also provides a CM5-IO carrier board to make use of the extra USB 3.0 and PCIe interfaces, and the company told CNX Software they tested the module successfully with the official Raspberry Pi CM4 IO board. Banana Pi BPI-CM5 Pro specifications: SoC – Rockchip RK3576 CPU – 4x Cortex-A72 cores at 2.2GHz, 4x Cortex-A53 cores at 1.8GHz GPU – Arm Mali-G52 MC3 GPU with support for OpenGL ES 1.1, 2.0, and 3.2, OpenCL up to 2.0, […]

September 2, 2024 by Sayantan Nandy - No Comments

Vecow EVS-3000 AI computing systems combine 14th Gen Intel Core CPUs and MXM Graphics for Edge AI applications

Vecow has introduced the EVS-3000 series, a new line of AI computing systems powered by Intel Core i9/i7/i5/i3 (14th Gen) processors with embedded MXM graphics. These systems deliver high computing power, come with multiple PCIe slots for expansion, and support remote monitoring making them ideal for edge AI applications such as autonomous robotics, public security, and machine vision. The EVS-3000 series includes both fan and fanless models: EVS-3100, EVS-3200, EVS-3300, EVS-3400 without fans, and EVS-3100(F), EVS-3200(F), EVS-3300(F), EVS-3400(F) with fans. All systems are powered by Intel R680E chipsets and feature compact NVIDIA or AMD MXM graphics, with support for 2.5GbE LAN, Out-of-Band (OOB) management, and multiple PCIe Gen 4 slots. These systems deliver high performance for AI computing at the edge for applications such as machine vision and robotics. As you may know, we’ve previously covered several Vecow AI computing systems, including the TGS-1000 Series, SPC-9000 fanless embedded system, ECX-3200, […]

August 30, 2024August 30, 2024 by Debashis Das - No Comments

Dusun DSGK-061 – A RK3568-powered VNC Edge AI box for industrial automation and remote management

DSGK 061 Smart VNC Edge Computing Boxjpg

Dusun has recently launched the DSGK-061 Smart VNC Edge Computing AI Box or DSGK-061 Edge AI Box for short. This new Edge AI gateway is powered by a Rockchip RK3568 quad-core processor with a 1 TOPS NPU for edge computing. It has a built-in VNC (Virtual Network Computing) application for remote management and supports various interfaces and communication protocols such as HDMI, USB 3.0, TTL serial, LAN/WAN, and WiFi, making it suitable for applications like industrial automation, smart manufacturing, and more. Previously we have written about similar Edge AI boxes like the Mixtile Edge AI box or Techbase iModGATE-AI, and some very powerful AI boxes with more than 30 TOPS NPU power like the Radxa Fogwise Airbox, the Firefly AIBOX-1684X, the Sipeed MaixBox M4N and more. Feel free to check those out if you are interested in similar products. Dusun DSGK-061 specifications: SoC – Rockchip RK3568 CPU – Quad-core Cortex A55 processor […]

August 27, 2024 by Debashis Das - No Comments

reCamera modular AI camera features SG2002 RISC-V AI SoC, supports interchangeable image sensors and baseboards

Seeed Studio’s reCamera AI camera is a modular RISC-V smart camera system for edge AI applications based on SOPHGO SG2002 SoC. The camera is made up of three boards: the Core board, the Sensor board, and the Baseboard. The Core board includes hosts the processor, storage, and optional Wi-Fi. The Sensor board consists of image choice of image sensors, and the Baseboard provides various connectivity options including USB Type-C, UART, microSD, and optional PoE port and CAN bus connectivity options. At the time of writing the company has released the C1_2002w and C1_2002 core boards. The C1_2002w core board includes eMMC storage, Wi-Fi, and BLE modules, and the C1_2002 features extra SDIO and UART connectivity, but not WiFi. Both boards use the SOPHGO SG2002 tri-core processor and can be paired with various camera sensors for applications such as robotics, healthcare, smart home, as well as buildings and industrial automation. […]

August 25, 2024August 25, 2024 by Jean-Luc Aufranc (CNXSoft) - 6 Comments

Review of Napcat wireless NVR with solar-powered security cameras

Napcat solar-powered wireless NVR review

After I reviewed the NapCat smart video doorbell last June, the company asked me to review a wireless NVR with solar-powered security cameras and I understood I would receive a kit with four solar-powered cameras and an NVR with storage preinstalled. In this review, I’ll go through an unboxing, a quick teardown of the NVR, the installation process, and my experience with the Napcat NVR user interfaces (connected to HDMI) and the Napcat Life Android app which I also used with the video doorbell. Napcat wireless NVR N1S22 kit unboxing The package I’ve received reads “N1S22” model of a “Solar-powered Security Camera System” and is quite smaller than I expected. One reason for the small size is that my kit only comes with two cameras instead of four, and the company also did a good job of making everything take as little space as possible. On the net, you’ll see […]

August 22, 2024August 23, 2024 by Jean-Luc Aufranc (CNXSoft) - 22 Comments

ODROID-M2 low-profile SBC features Rockchip RK3588S2 SoC, up to 16GB LPDDR5, 128GB eMMC flash

Hardkernel has just launched the ODROID-M2 low-profile SBC based on a Rockchip RK3588S2 octa-core Cortex-A76/A55 AI SoC with up to 16GB LPDDR5, 64GB eMMC flash, an M.2 PCIe socket, support for three displays through HDMI, USB-C, and MIPI DSI interfaces, gigabit Ethernet, and more. The ODROID-M2 follows the ODROID-M1 and ODROID-M1S single board computers based on respectively Rockchip RK3568 and RK3566 quad-core Cortex-A55 processors, but a significantly more powerful Rockchip RK3588S2 processor, and a larger 90x90mm form factor to accomodate for extra features and interfaces. ODROID-M2 specifications: SoC – Rockchip RK3588S2 CPU – Octa-core processor with 4x Cortex-A76 cores @ up to 2.3 GHz (+/- 0.1Ghz), 4x Cortex-A55 cores @ up to 1.8 GHz GPU – Arm Mali-G610 MP4 GPU @ 1 GHz compatible with OpenGL ES 3.2, OpenCL 2.2, and Vulkan 1.2 APIs VPU – 8Kp60 video decoder for H.265/AVS2/VP9/H.264/AV1 codecs, 8Kp30 H.265/H.264 video encoder AI accelerator – 6 […]

August 20, 2024August 20, 2024 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

NanoPi M6 – A Rockchip RK3588S SBC and fanless HMI solution with an integrated 3.5-inch touchscreen display

NanoPi M6 is a Rockchip RK3588S SBC (single board computer) that is also offered as a complete fanless HMI solution with a metal case and a 3.5-inch capacitive touchscreen display with 800×480 resolution. The M6 is offered with 4GB to 32GB LPDDR5 memory, supports microSD, eMMC flash module, and M.2 NVMe SSD bootable storage, features one HDMI 2.1 port, two MIPI DSI connectors, two MIPI CSI camera connectors, gigabit Ethernet, an M.2 E-Key socket for WiFi and Bluetooth, and a 30-pin GPIO header for expansion among a few other ports and features. NanoPi M6 specifications: SoC – Rockchip RK3588S CPU – Octa-core processor with 4x Cortex-A76 cores @ up to 2.4 GHz, 4x Cortex-A55 cores @ up to 1.8 GHz GPU – Arm Mali-G610 MP4 GPU compatible with OpenGL ES 3.2, OpenCL 2.2, and Vulkan 1.2 APIs VPU – 8Kp60 video decoder for H.265/AVS2/VP9/H.264/AV1 codecs, 8Kp30 H.265/H.264 video encoder AI […]

August 15, 2024August 15, 2024 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

Firefly EC-R3576PC FD is an Embedded Large-Model Computer based on Rockchip RK3576 processor

Firefly RK3576 Embedded Large Model Computer

Firefly EC-R3576PC FD is described as an “Embedded Large-Model Computer” powered by a Rockchip RK3576 octa-core Cortex-A72/A53 processor with a 6 TOPS NPU and supporting large language models (LLMs) such as Gemma-2B, LlaMa2-7B, ChatGLM3-6B, or Qwen1.5-1.8B. It looks to be based on the ROC-RK3576-PC SBC we covered a few weeks ago, and also designed for LLM. But the EC-R3576PC FD is a turnkey solution that will work out of the box and should deliver decent performance now that the RKLLM toolkit has been released with NPU acceleration. However, note there are some caveats doing that on RK3576 instead of RK3588 that we’ll discuss below. Firefly EC-R3576PC FD specifications: SoC – Rockchip RK3576 CPU 4x Cortex-A72 cores at 2.2GHz, four Cortex-A53 cores at 1.8GHz Arm Cortex-M0 MCU at 400MHz GPU – ARM Mali-G52 MC3 GPU clocked at 1GHz with support for OpenGL ES 1.1, 2.0, and 3.2, OpenCL up to 2.0, and […]