computer vision News - Page 14 of 22 - CNX Software

June 17, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Modelplace.AI is an app store for OpenCV compatible AI models

OpenCV open-source computer vision library is used in a wide variety of projects and products, and last year, the community also launched the OpenCV AI Kit (OAK) Myriad X-based hardware solution for computer vision. However there’s a learning curve to use the library, especially in combination with artificial intelligence models, and it can be challenging and time-consuming to newcomers. So in order to broaden the reach of the solution, OpenCV has now introduced Modelplace.AI, an app store/marketplace for AI models working with the OpenCV library. The AI model marketplace is a store and try-before-you-buy service for artificial intelligence models, many of which are certified to work with the OpenCV AI Kit. There are currently over 40 models for detection (e.g. person, pedestrian…), classification, segmentation (e.g. extraction of objects from a scene), pose estimation, people counting, text detection, tracking, and more. Right now all models are free, but developers will be […]

May 18, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

OpenMV PureThermal STM32H7 board overlays thermal map on RGB image

We’ve been writing about OpenMV open-source camera boards programmable with MicroPython at least since 2015, with the latest model OpenMV Cam H7 based on STM32H7 Cortex-M7 microcontroller introduced in 2018. But the company has now gone a step further with OpenMV PureThermal board equipped with a more powerful STM32H7 dual-core Arm Cortex-M7/M4microcontroller, and supporting FLIR Lepton 2 to 3.5 thermal imagers, allowing the system to overlay the thermal map on top of the image like an augmented reality app would do. It can do so on the integrated LCD display or on an HDMI display. OpenMV PureThermal features & specifications: MCU – STMicro STM32H7 Arm Cortex-M7 @ 480 MHz) and Cortex-M4 @ 240 MHz microcontroller Memory – 64MB SDRAM Storage – 32 MB of QSPI flash for the firmware, a microSD card slot for saving pictures and machine vision assets Display 800×480 touch Screen LCD DVI out for driving an […]

May 14, 2021May 14, 2021 by Saumitra Jagdale - No Comments

NEON-2000-JNX series AI Camera Features NVIDIA Jetson Xavier NX SOM for AIoT Applications

Machine vision applications highlight the complexity of implementation due to the requirement of interfacing several devices. These devices include image sensor modules, cables, GPU modules, and memory units, thus increasing the time for development and deployment. ADLINK’s NEON-2000-JNX series AI camera aims to simplify the deployment of edge machine vision and AIoT use cases. NEON-2000-JNX series AI camera comes with an inbuilt ADLINK’s new edge vision analytics software known as the EVA SDK. The software reduces the time in designing and creating proofs-of-concept, which leads to quicker deployment of applications. Users get a wide range of options for selecting field-ready “application plug-ins and ADLINK-optimized AI models”. This ensures the quality of vision AI and eases the building of use cases with lesser software code and programs. Additionally, the preview function allows quicker verification of AI Inference flow. We saw the launch of NVIDIA’s Jetson Xavier NX SOM in April 2020 […]

May 5, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Imago “VisionAI” Smart AI Camera supports Tensorflow Lite & AutoML Vision Edge

Imago Technologies GmbH “VisionAI” is a programmable Smart AI camera that combines a quad-core Cortex-A53 processor @ 1.8 GHz together with Google Edge TPU, and designed for embedded image processing applications in the fields of AI, Deep Learning, and Machine Learning. The smart camera supports TensorFlow Lite and AutoML Vision Edge frameworks, and is suited for tasks such as pattern recognition, classification, anomaly or defect detection in inspection applications, code reading, and other machine vision applications. Imago VisionAI (VisionSensor PV3 AI) camera specifications: SoC – Unnamed quad-core Arm Cortex-A53 processor @ 1.8 GHz (likely NXP i.MX 8M Mini) AI Accelerator – Google Edge TPU with up to 4 TOPS of AI processing power System Memory – 2 GB DDR4 RAM Storage – MicroSD card up to 32GB Connectivity – Gigabit Ethernet M12 connector Camera 1/1.8” 5MP mono or color CMOS sensor with 2560 × 1936 pixels resolution, up to 65 […]

April 28, 2021April 28, 2021 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

Xilinx Introduces Kria K26 SoM and vision AI devkit based on Zynq Ultrascale+ XCK26 FPGA MPSoC

Silicon vendors will usually focus on chip design, and provide an expensive evaluation kit to early customers, leaving the design of cost-optimized boards and system-on-modules to embedded systems companies. But Xilinx has decided to enter the latter market with the Kria portfolio of adaptive system-on-modules (SOMs) and production-ready small form factor embedded boards starting with Kria K26 SoM powered by Zynq UltraScale+ XCK26 FPGA MPSoC with a quad-core Arm Cortex-A53 processor, up to 250 thousand logic cells, and a H.264/265 video codec designed for Edge AI applications, as well as computer vision development kit. Kria K26 System-on-Module Kria K26 module specifications: MPSoC – Xilinx Zynq Ultrascale+ custom-built XCK26 with quad-core Arm Cortex-A53 processor up to 1.5GHz, dual-core Arm Cortex-R5F real-time processor up to 600MHz, Mali-400 MP2 GPU up to 667MHz, 4Kp60 VPU, 26.6Mb On-Chip SRAM, 256K logic cells, 1,248 DSP slices System Memory – 4GB 64-bit DDR4 (non-ECC) Storage – […]

April 13, 2021April 13, 2021 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

Arducam Pico4ML Board – TinyML on Raspberry Pi RP2040 with QVGA Camera & Display

A few months ago, ArduCAM demonstrated person detection on Raspberry Pi Pico with Arducam camera using TensorFlow Lite, and later we noted more work was being performed to bring machine learning to RP2040 platforms, notably with the development of Arducam Pico4ML board with a built-in camera and display. At the time, i..e last month, all we had were some renders of the board, but now Arducam Pico4ML pre-orders have launched for $49.99 on UCTRONICS and Tindie stores. Shipping is scheduled to start at the end of the month, so let’s have a closer look. Arducam Pico4ML TinyML devkit specifications: Microcontroller – Raspberry Pi RP2040 dual-core Cortex-M0+ MCU with 264 KB of embedded SRAM Storage – 2MB SPI flash Display – 0.96-inch LCD SPI Display (ST7735) with 160 x 80 resolution Camera – HiMax HM01B0 QVGA camera (320×240 @ 60fps) Audio – Built-in microphone Sensor – IDK ICM-20948 9-axis IMU (gyroscope, […]

April 9, 2021April 9, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Rugged, fanless quad-camera system brings AI and Machine Vision to rolling stock and automotive applications

quad-camera system automotive AI & machine vision

Eurotech BoltGPU 10-31 is a rugged fanless embedded system powered by NVIDIA Jetson Xavier NX module, equipped with four FAKRA connectors for GMSL camera, and designed to bring Edge AI and machine vision to rolling stock (e.g. trains) and automotive applications. The BoltGPU 10-31 also features 16 GB of eMMC flash, NVMe SSD support, three Gigabit Ethernet interfaces, WiFI 6 and Bluetooth 5.1, two USB3.1 ports, as well as isolated CAN-FD, optoisolated DIO, video out, and GNSS with optional RTK. BoltGPU 10-31 specifications: System-on-Module – NVIDIA Jetson Xavier NX with hexa-core NVIDIA Carmel ARM v8.2 64-bit CPU with 6MB L2 + 4MB L3 cache, 384-core NVIDIA Volt GPU with 48 Tensor Cores (up to 21 TOPS of accelerated computing), 8 GB LPDDR4x RAM, 16GB eMMC 5.1 flash Storage MicroSD card socket Optional 512 GB NVMe SSD on M.2 Key M socket 256 Kbit Serial EEPROM Video Output – 1x Mini […]

April 9, 2021 by Jean-Luc Aufranc (CNXSoft) - 5 Comments

Eyecam open-source webcam will make you feel spied on

Most people will use webcams connected to a computer or integrated into a laptop without thinking about the possibility of being spied on, but Eyecam will certainly raise awareness and make you feel like somebody is truly watching. The open-source webcam is shaped like a human eye and acts like one thanks to a Raspberry Pi camera and an Arduino board controlling six servos for eyeball, eyelids, and eyebrows movements. The project was conducted at Saarland University in Germany, and Eyecam looks amazingly realistic – and creepy – with the eyeball and eyelids moving, especially when face tracking is enabled, and expressions are possible with servos controlling the eyebrows. The webcam is comprised of 3D printed parts, a Raspberry Pi camera connect to Raspberry Pi Zero recognized as a USB webcam from the host, and an Arduino Leonardo Pro Micro to control the 6 servo motors. On the software side, […]