NVIDIA Jetson Nano based AI camera devkit enables rapid computer vision prototyping

AI Camera Devkit

ADLINK “AI Camera Dev Kit” is a pocket-sized NVIDIA Jetson Nano devkit with an 8MP image sensor, industrial digital inputs & outputs, and designed for rapid AI vision prototyping. The kit also features a Gigabit Ethernet port, a USB-C port for power, data, and video output up to 1080p30, a microSD card with Linux (Ubuntu 18.04), and a micro USB port to flash the firmware. As we’ll see further below it also comes with drivers and software to quickly get started with AI-accelerated computer vision applications. AI Camera Dev Kit specifications: System-on-Module –  NVIDIA Jetson Nano with CPU – Quad-core Arm Cortex-A57 processor GPU – NVIDIA Maxwell architecture with 128 NVIDIA cores System Memory – 4 GB 64-bit LPDDR4 Storage – 16 GB eMMC Storage – MicroSD card socket ADLINK NEON-series camera module Sony IMX179 color sensor with rolling shutter Resolution – 8MP (3280 x 2464) Frame Rate (fps) – […]

Renesas RZ/V2MA microprocessor embeds AI & OpenCV accelerators for image processing

Renesas RZ/V2MA AI OpenCV accelerator

Renesas has launched the RZ/V2MA dual-core Arm Cortex-A53 microprocessor with a low-power (1TOPS/W) DRP-AI accelerator and one OpenCV accelerator for rule-based image processing enabling vision AI applications. The MPU also supports H.265 and H.264 video decoding and encoding, offers LPDDR4 memory and eMMC flash interfaces, as well as Gigabit Ethernet, a USB 3.1 interface, PCIe Gen 2, and more. The RZ/V2MA microprocessor targets applications ranging from AI-equipped gateways to video servers, security gates, POS terminals, and robotic arms. Renesas RZ/V2MA specifications: CPU – 2x Arm Cortex-A53 up to 1.0GHz Memory – 32-bit LPDDR4-3200 Storage – 1x eMMC 4.5.1 flash interface Vision and Artificial Intelligence accelerator DRP-AI at 1.0 TOPS/W class OpenCV Accelerator (DRP) Video H.265/H.264 Multi Codec Encoding: h.265 up to 2160p, h.264 up to 1080p Decoding: h.265 up to 2160p, h.264 up to 1080p Networking – 1x Gigabit Ethernet USB – 1x USB 3.1 Gen1 host/peripheral up to 5 […]

TI Sitara AM623 & AM625 Cortex-A53 SoCs offer low-power AI for HMI and IoT applications

Sitara AM62 Starter Kit

Texas Instruments has just launched the new Sitara AM62 family with AM623 and AM625 single to quad-core Cortex-A53 processors designed to provide IoT gateways and HMI applications with AI processing at low power, in some cases with up to 50% reduction in power consumption. The AM623 processor specifically targets Internet of Things (IoT) applications and gateways that may benefit from object and gesture recognition, while the AM625, equipped with a 3D GPU, should power HMI applications with edge AI and up to two full-HD displays. Sitara AM623 and AM625 processors Sitara AM623/AM625 key features and specifications: CPU – Single, dual, or quad-core Arm Cortex-A53 processor @ up to 1,400 MHz with 512KB L2 shared cache, plus 32KB I+D cache per core Co-processor – 1x Arm Cortex-M4F real-time core at up to 400 MHz with 256KB SRAM with SECDED ECC GPU (AM625 only) – Unnamed 3D GPU with support for OpenGL […]

Inforce 68A1 SoM supports up to seven 4Kp120 cameras, dual 4Kp120 video encoding/decoding

Inforce 68A1 QCS8250 module

SMART Wireless Computing has announced the Inforce 68A1, a compact system-on-module based on Qualcomm QCS8250 IoT processor with support for up to seven concurrent 4Kp120 camera inputs, and decode/encode two 4Kp120 video streams simultaneously. Equipped with 8GB PoP DDR5 memory, 64GB UFS storage, a wireless module supporting 802.11ax Wi-Fi 6E and Bluetooth 5.1, the module is designed for high-end IoT applications such as smart cameras, video collaboration, AI hubs, connected healthcare, and smart retail. Inforce 68A1 specifications: SoC – Qualcomm QCS8250 octa-core Kryo 585 processor up to 2.84 GHz (high-performance cores) or 1.8 GHz (low power cores) with Adreno 650 GPU, Adreno 665 VPU, Adreno 995 DPU, Hexagon DSP with quad HVX, NPU230 neural processing unit, Spectra 480 ISP; 15 TOPS AI processing power System Memory – 8GB LPDDR5 (PoP) Storage – 64GB UFS flash Wireless – Qualcomm QCA6391 with 802.11 a/b/g/n/ac/ax Wi-Fi 6 2×2 MIMO, Bluetooth 5.1 Audio – […]

Mini Pupper – Raspberry Pi 4-based robot dog teaches ROS, SLAM, navigation, computer vision (Crowdfunding)

Mini Pupper Raspberry Pi 4 Robot Dog

Mini Pupper is a Raspberry Pi 4 powered robot dog inspired by Stanford Pupper open-source quadruped robot, and designed in “light collaboration” with Nathan Kau, the original creator of Stanford Pupper. Just like the original design, MangDang’s Mini Pupper is open-source, based on Ubuntu and ROS (Robot Operating System), and designed for robotics education in schools, homeschool families, enthusiasts and others, with notably students being able to learn out to use ROS, SLAM, navigation, and OpenCV computer vision through online courses that will come with the robot. Mini Pupper key features and specifications: SBC – Raspberry Pi 4 Model B with 2GB RAM Storage – 2GB microSD card Display – 320×240 LCD for facial animation Camera – Support for OpenCV AI Kit Lite 12 DOF via MangDang’s custom servos Optional Lidar module for SLAM (Simultaneous localization and mapping) Battery – 800 mAh Charger – Input voltage – 100-240V AC 50/60Hz, […]

OpenCV AI Kit Lite – A compact 4K Tri-camera kit for computer vision applications (Crowdfunding)

OpenCV AI Kit LIte

The OpenCV AI Kit “OAK-D” now has a little brother with the OpenCV AI Kit Lite equipped with the same Intel Myriad X-based DepthAI solution with three cameras, but in a much compact form factor and a price slashed to as low as $79 and up. Like its predecessor, the OpenCV AI Kit leverage the Myriad X AI accelerator’s capabilities to provide a wide range of real-time computer vision applications, and can be programmed with C++ or Python APIs, as well as graphical user interfaces. OpenCV AI Kit Lite (OAK-D Lite) specifications: Intel Myriad X-based DepthAI with 4 TOPS of AI performance Cameras (made by ArduCam) Color Camera IMX214 (PLCC) with 4208×3120 resolution,  1.348:1 aspect ratio 1/3.1 inch Lens size 81.3 degrees DFOV Focus range 8cm – ∞ Stereo Camera specifications: Omnivision OV07251-G04A-1E (COB) with  640 x 480 resolution, 1.333:1 aspect ratio 1/7.5 inch lens size DFOV: 85.6,HFOV: 72.9, VFOV: […]

Qualcomm Flight RB5 5G Platform is a high-end drone reference design with 7 cameras

Qualcomm Flight RB5 5G Platform

Leveraging its involvement in the Ingenuity Mars helicopter, Qualcomm has introduced the Qualcomm Flight RB5 5G platform, a high-end drone reference design with 5G and WIFi 6 connectivity, seven cameras up to 8K resolution, and 15 TOPS of AI performance. The platform is based on Qualcomm QRB5165 octa-core processor, a variant of Snapdragon 865 for robotics, also found in Qualcomm Robotics RB5 Platform with support for Intel RealSense D435i (that should reach end-of-life soon), and provides an upgrade to the company’s Flight Pro drone based on Qualcomm Snapdragon 820 platform. Qualcomm Flight RB5 5G Platform key features and specifications: SoC – Qualcomm QRB5165 with eight Kryo 585 cores up to 2.84 GHz, GPU Adreno 650 GPU with support for Open GL ES and OpenCL, Hexagon 698 DSP with HVX, Hexagon Tensor Accelerator, Qualcomm Spectra 480 ISP with dual 14-bit image signal processing Memory – LPDDR5 up to 2750 MHz, LPDDR4x up […]

Jevois Pro small AI camera with Amlogic A311D SoC offers up to 13 TOPS (Crowdfunding)

JeVois Pro

Jevois-A33 smart camera was a tiny Linux camera with Allwinner A33 processor designed for computer vision applications and announced in 2016. I had the opportunity to review the computer vision camera the following year, and it was fun to use to learn about computer vision with many examples, but since it relied on the CPU for processing, it would not have been suitable for all projects due to the lag, as for example, object detection took 500ms and Yolo V3 around 3 seconds per inference. But time has passed, and great progress has been made in the computer vision and AI fields with the tasks now usually handled by a built-in NPU, or an AI accelerator card. So JeVois Pro deep learning camera has just been launched with an Amlogic A311D processor featuring a 5 TOPS NPU, and support for up to 13 TOPS via a Myriad X or Google […]