computer vision News - Page 8 of 25 - CNX Software

January 25, 2024January 26, 2024 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

Vivante NPU (found in Amlogic A311D) gets its open-source driver upstreamed to Mesa

The Teflon project is an open-source TensorFlow Lite delegate that currently supports VeriSilicon Vivante NPU and aims to support several other AI accelerators over time. The project has recently been upstreamed to Mesa meaning AI inference with open-source software will work out of the box in supported hardware once Mesa 24.1 is released in May 2024. Teflon relies on the Etnaviv open-source driver better known for working with Vivante GPUs found, for instance, in NXP i.MX processors, but Tomeu Vizoso also worked on implementing Vivante NPU support since May 2022 thanks to a sponsorship from Libre Computer and documented the development progress on this blog. The VeriSilicon Vivante “VIPNano-QI.7120” 5 TOPS NPU is found in the Amlogic A311D processor, and Tomeu tested Teflon with the Etnaviv NPU drive on both the Libre Computer AML-A311D-CC Alta and Khadas VIM3 single board computers with decent performance although still slower than with the […]

January 19, 2024 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

$16 Grove Vision AI V2 module features WiseEye2 HX6538 Arm Cortex-M55 & Ethos-U55 AI microcontroller

Grove Vision AI V2 XIAO ESP32-C3 OV5647 camera

Seeed Studio’s Grove Vision AI V2 module is based on the HiMax WiseEye2 HX6538 dual-core Cortex-M55 AI microcontroller with an Arm Ethos-U55 microNPU and features a MIPI CSI connector for an OV5647 camera. It is designed for AI computer vision applications using TensorFlow and PyTorch frameworks and connects to hosts such as Raspberry Pi SBCs, ESP32 IoT boards, Arduino, and other maker boards over I2C. We tested the previous generation Grove Vision AI module based on the 400 MHz HX6537-A DSP-based AI accelerator using the SenseCAP K1100 sensor prototype kit with LoRaWAN connectivity, and managed to have the kit perform face detection and send the data over LoRaWAN. The Grove Vision AI V2 builds on that but with a modern Arm MCU core and more powerful AI accelerator that can run models such as Mobilenet V1/V2, Efficientnet-lite, and Yolo v5 & v8 using the SenseCraft low-code/no-code platform. Grove Vision AI […]

January 19, 2024 by Debashis Das - 1 Comment

Firefly CT36L AI Smart Camera Features Rockchip RV1106G2 with 0.5 TOPS NPU, 100Mbps Ethernet with PoE support

Firefly CT36L AI Smart Camera (PoE) features a Rockchip RV1106G2 CPU with 0.5 TOPS NPU, a 5-megapixel ISP, and a 3-megapixel HD lens. It supports 100Mbps Ethernet with PoE and includes advanced image enhancements like HDR, WDR, and noise reduction, all while maintaining low power consumption and high image integration. We’ve previously explored various AI cameras such as Tokay Lite, EDATEC ED-AIC2020, ThinkCore TC-RV1126, Orbbec Persee+, M5Stack UnitV2 among others. Feel free to check them out for more information. Firefly CT36L AI Smart Camera (PoE) specifications: CPU – Rockchip RV1106G2 Arm Cortex-A7 @ 1.2GHz, with Neon and FPU NPU – 0.5 TOPS, supports INT4/INT8/INT16, TensorFlow/MXNet/PyTorch/Caffe/Onnx NN ISP – 5MP high-performance, HDR, WDR, 3DNR, 2DNR, sharpening, defogging, fisheye and gamma correction, feature detection VPU – 3072×1728 (5M) @ 30fps H.265/H.264 encoding, 16M@60FPS JPEG snapshot RAM – 128MB DDR3 built-in Storage – 16MB SPI Flash built-in Camera specifications: Type – Color Camera Image Sensor – SC3336 CMOS Size […]

January 9, 2024 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

ASRock Industrial upgrades mini-ITX, micro-ATX, and ATX motherboards for Intel Core 14th Gen Raptor Lake-S Refresh processors

ASROCK Industrial 14th gen mini-ITX micro-ATX ATX motherboards

ASRock Industrial has just announced 25 (twenty-five!) industrial motherboards powered by 14th gen Intel Core Raptor Lake-S Refresh hybrid processors with up to 24 cores and 32 threads introduced last October, and supporting up to 96GB DDR5 4800/5600 memory. The thin and high-rise mini-ITX, micro-ATX, and ATX industrial motherboards support up to four 4K displays, PCIe Gen5 interfaces, up to three 2.5GbE ports (and 10GbE LAN for the IMB-X1316-10G model), and USB 3.2 Gen2x2 (20 Gbps) ports for factory automation, robotics, machine vision, smart retail, kiosks, digital signage, gaming, security, and more. I would usually list the specifications of the motherboards, but since we have 25 different models, I’ll skip that and provide a summary. One reason ASRock Industrial has so many models is that those are existing motherboards with socketed processors and the company offered 12th and 13th gen CPUs so far, and the company simply updated the BIOS […]

December 22, 2023November 2, 2024 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

Orbbec Femto Mega 3D depth camera review – Part 1: Unboxing, teardown, and first try

Orbbec sent us a Femto Mega 4K RGB and 3D depth and camera for review. The camera is powered by an NVIDIA Jetson Nano module, features Microsoft ToF technology, and outputs RGB, TOF, and IR data through a USB-C port or a gigabit Ethernet port. I’ll start the two-part with an unboxing, a teardown, and a quick try with the OrbbecViewer program on Ubuntu 22.04 in the first part of the review because checking out the software and SDK in more detail in the second part later on. Femto Mega depth and RGB camera unboxing I received the camera in a cardboard package showing the camera model and key features: “ORBBEC Femto Mega DEPTH+RGB CAMERA”. The package’s content is comprised of a USB-C cable to connect to the host, the camera, and a 12V/2A power adapter. The front side of the camera features the RGB camera sensor, the TOF (Time-of-Flight) […]

December 12, 2023December 11, 2023 by Jean-Luc Aufranc (CNXSoft) - No Comments

STMicro VD55G1 – A small, low-power global shutter I3C camera sensor for computer vision

STMicro VD55G1 global shutter camera sensor

STMicro VD55G1 is a new global shutter I3C camera sensor with a small die size of 2.7 x 2.2 mm, 804 x 704 pixels native resolution, and consuming about 1mW in its ‘always-on’ autonomous mode to wake up the host when motion is detected. Camera sensors are available with rolling or global shutter, with most from the former type, but as we’ve seen in our reviews of the e-Con Systems See3CAM_24CUG (USB 3.1) and the Raspberry Pi Global Shutter (MIPI CSI) global shutter cameras, the latter is much better we capturing moving objects clearly at high frame rates with fewer artifacts than with rolling cameras. The VD55G1 global shutter sensor will also benefit from the same advantage but is offered in a smaller package working over MIPI CSI and/or I3C, making it suitable for devices with small batteries used in applications such as eye tracking or motion estimation. STMicro VD55G1 […]

December 7, 2023 by Jean-Luc Aufranc (CNXSoft) - No Comments

Tokay Lite – A battery-powered no-code AI camera based on ESP32-S3 WiSoC (Crowdfunding)

Maxlab’s Tokay Lite is an OHSWA-certified AI camera based on ESP32-S3 WiFI and Bluetooth SoC that can be used for computer vision (e.g. facial recognition & detection) and robotics applications without the need to know programming languages since a web interface is used for configuration. The WiFi and Bluetooth AI camera also features night vision with four IR LEDs, an IR cut filter, light and PIR motion sensors, a 20-pin expansion connector with SPI and UART, support for an external RTC, and can take power from USB-C or a LiPo battery. Tokay Lite specifications: Wireless module ESP32-S3-WROOM-1 MCU – ESP32-S3 dual-core LX7 microprocessor @ up to 240 MHz with Vector extension for machine learning, 512 KB SRAM Memory – 8MB PSRAM Storage – 8MB SPI flash Connectivity – WiFi 4 and Bluetooth 5 with LE/Mesh PCB antenna Certifications – FCC/CE certification Camera OV2640 camera sensor (replaceable) via DVP interface Image Capabilities: […]

December 3, 2023 by Debashis Das - No Comments

OpenMV CAM RT1062 camera for machine vision is programmable with MicroPython

Following the success of the OpenMV Cam H7 and the original OpenMV VGA Camera, OpenMV recently launched the OpenMV CAM RT1062 powered by NXP’s RT1060 processor. This new camera module integrates a range of features, including a high-speed USB-C (480Mbps) interface, an accelerometer, and a LiPo connector for portability. Similar to its predecessor, this camera module also features a removable camera system, and it is built around the OV5640 image sensor which is more powerful in terms of resolution and versatility. However, the previous Omnivision OV7725 sensor, used in the OpenMV Cam H7 has a far superior frame rate and low-light performance. OpenMV provides a Generic Python Interface Library for USB and WiFi Comms and an Arduino Interface Library for I2C, SPI, CAN, and UART Comms which can be used to interface your OpenMV Cam to other systems. To program the board, you can use MicroPython 3 with OpenMV IDE, […]