Allwinner V3LP gets low voltage RAM, should replace Allwinner V3S dual camera SoC

Allwinner V3LP

Allwinner V3LP is a single-core Cortex-A7 processor for dual-camera systems with the exact same specifications as the Allwinner V3S processor introduced in 2016, except it should be more power efficient with a lower DDR operating voltage of 1.5V instead of 1.8V. Sochip explains that procuring the integrated DDR2 in the Allwinner V3s design is challenging, so Allwinner has replaced the memory in the pin-to-pin compatible Allwinner V3LP with more broadly available and lower power RAM. Allwinner V3LP specifications: CPU – ARM Cortex-A7 @ up to 1.2 GHz Memory – Integrated 64MB DDR2 DRAM @ 1.5 V Storage I/F – SD 2.0, eMMC 4.41, SPI NAND flash, SPI NOR flash Audio Codec – 92dB audio codec supporting 2x ADC channels and 2x DAC channels, 1x low-noise analog microphone bias output, 1x microphone input and 1x stereo microphone output Video Processing Unit Encoding – 1080p@40fps or 1080p@30fps + VGA@30fps H.264 Decoding – […]

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) – […]

Giveaway Week – e-con Systems e-CAM20_CURB camera

e-CAM20_CURB LEGO mount

Today, we’re giving away the e-con Systems e-CAM20_CURB is a 2.3MP color camera with a global shutter that is designed to work with Raspberry Pi 4 SBC. The camera is based on ON Semiconductor AR0234CS CMOS sensor and supports uncompressed video at 1920 x 1200 (2.3MP) up to 60 fps,  1920 x 1080 (Full HD) up to 65 fps, and 1280 x 720 (HD) up to 120 fps. I just completed the e-CAM20_CURB camera review with Raspberry Pi 4 last weekend and found the video smoothness and quality to be much better than most cameras I’ve tried when there is motion, even in relatively dark scenes, since motion blur and artifacts are reduced. The company provides Yocto Linux and Raspbian/Raspberry Pi OS images with V4L2 drivers and Gstreamer tools, and the camera was fairly easy to use with the Yocto image thanks to the useful documentation provided with the kit. […]

Getting started with e-CAM20_CURB camera for Raspberry Pi 4

eCAM20_CURB night scene

e-con Systems e-CAM20_CURB is a 2.3 MP fixed focus global shutter color camera designed for the Raspberry Pi 4, and the company has sent us a sample for evaluation and review. We’ll start by providing specifications, before checking out the package content, connecting the camera to the Raspberry Pi 4 with a DIY LEGO mount, showing how to access the resources for the camera, and trying tools provided in the Raspberry Pi OS or Yocto Linux image. e-CAM20_CURB specifications The camera is comprised of two boards with the following specifications: eCAM217_CUMI0234_MOD full HD color camera with 4-lane MIPI CSI-2 interface ON Semiconductor AR0234CS CMOS sensor with 1/2.6″ optical form-factor Global Shutter Onboard ISPimage sensor from ON Semiconductor Uncompressed UYVY streaming HD (1280 x 720) up to 120 fps Full HD (1920 x 1080) up to 65 fps 2.3 MP (1920 x 1200) up to 60 fps External Hardware Trigger Input […]

TinyML-CAM pipeline enables 80 FPS image recognition on ESP32 using just 1 KB RAM

TinyML-CAM image recognition microcontroller boards

The challenge with TinyML is to extract the maximum performance/efficiency at the lowest footprint for AI workloads on microcontroller-class hardware. The TinyML-CAM pipeline, developed by a team of machine learning researchers in Europe, demonstrates what’s possible to achieve on relatively low-end hardware with a camera. Most specifically, they managed to reach over 80 FPS image recognition on the sub-$10 ESP32-CAM board with the open-source TinyML-CAM pipeline taking just about 1KB of RAM. It should work on other MCU boards with a camera, and training does not seem complex since we are told it takes around 30 minutes to implement a customized task. The researchers note that solutions like TensorFlow Lite for Microcontrollers and Edge Impulse already enable the execution of ML workloads, onMCU boards, using Neural Networks (NNs). However, those usually take quite a lot of memory, between 50 and 500 kB of RAM, and take 100 to 600 ms […]

SONOFF NSPanel Pro control panel review with Zigbee modules, CAM Slim WiFi camera

SONOFF NSPanel Pro Zigbee Devices Added

ITEAD has sent us a Smart Home kit for review including the SONOFF NSPanel Pro Android control panel and Zigbee gateway, an enclosure stand, the CAM Slim WiFi camera, and four Zigbee modules, namely the SNZB-01 wireless switch, the SNZB-02 temperature & humidity sensor, the SNZB-03 motion sensor, and the SNZB-04 door/window sensor. In this review, we’ll configure the NSPanel Pro controller with the eWelink app in Android, show how to add the WiFi camera and Zigbee devices directly to NSPanel Pro, and go back to the eWelink app for more advanced features such as scenes with triggers and actions. Sonoff NSPanel Pro kit unboxing Let’s get started by having a closer look at the SONOFF NSPanel Pro controller. As previously noted, the device is based on Rockchip PX30 quad-core Cortex-A35 processor and runs Android 8.1. It acts both as a control panel and a WiFi to Zigbee 3.0 gateway. The […]

Easily add face detection to your project with the Person Sensor module

Person Sensor

It’s now much easier to AI features to your project thanks to better tools, but as we’ve experienced when trying out Edge Impulse machine learning platform on the XIAO BLE Sense board, it still requires some effort and the learning curve may be higher than some expect. But for common tasks like face detection, there’s no reason for the solution to be hard-to-use or expensive, and Pete Warden (Useful Sensors) has designed the $10 Person Sensor fitted with a camera module pre-programmed with algorithms that detect nearby faces and reports the results over an I2C interface.   Person Sensor specifications: ASIC – Himax HX6537-A ultra-low-power AI accelerator @ 400 MHz with 2MB SRAM, 2MB flash Camera Image Sensor – 110 degrees FOV Image scan rate – 7Hz with no facial recognition Image scan rate – 5Hz with facial recognition active Host interface Qwiic connector for the I2C interface up to […]

Innodisk releases USB camera modules for AI applications

Innodisk EV2U-RMR2 camera module

Innodisk, better known for its industrial storage solutions and embedded peripherals, has recently announced a shift towards the AI industry, and the first products for this market are three USB 2.0 camera modules with 1920×1080 resolution. All three camera modules are fixed focus. Innodisk EV2U-RMR2 offers HDR support, the EV2U-SGR1 is more compact, offers wider angles, and is optimized for low light conditions, while the EV2U-RMR1 supports HDR in a longer, but much thinner and narrower form factor and is equipped with an M5 lens, instead of an M12 lens for the other models. Innodisk EV2U-RMR2 camera module specifications: Resolution – 1920×1080 @ 30fps Sensor Size – 1/4” Pixel Size – 2 um Lens type – Fixed focus (M12) Lens D/H/V FoV – 86°/72°/38° HDR support Output I/F – USB 2.0 Power consumption – Around 1 Watt Dimensions – 58 x 25 x 22 mm Temperature Range – -20°C ~ […]