DepthAI Brings AI plus Depth to the Raspberry Pi (Crowdfunding)

DepthAI Embedded Platform

Edge computing on the Raspberry PI has been a bit of ups and downs, especially with everyone gearing for AI in everything. The Raspberry Pi, on its own, isn’t really capable of any reliable AI applications. Typical object detection on the Raspberry Pi would get you something around 1 – 2 fps depending on the nature of your model and this because all those processing is done on the CPU. To address this poor performance of AI applications on the Raspberry Pi, AI Accelerators came to the rescue. The Intel Neural Compute Stick 2 is one such accelerator capable of somewhere around 8 – 15 fps depending on your application. The NCS2, which is based on the Myriad X VPU technology, offers so much more than the compute stick delivers, and this is something that the team behind DepthAI has exploited to create a powerful AI module for edge computing called DepthAI. It is one thing to do object detection. …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Olimex OSHW Allwinner S3 IP Camera Board in the Works – Feedback & Suggestions Welcomed

OSHW IP Camera Board

Allwinner S3 Arm Cortex-A7 processor is designed for dual-camera systems and embeds 128MB RAM. It looks to be an evolution of the older Allwinner V3s chip that came with 64MB RAM and is software-compatible with the older camera SoC. We reported about the new processor and an Allwinner S3 development board last year, but Olimex has started working on an open-source hardware IP camera board based on the processor and is asking for feedback from customers and the community at large. Preliminary specifications: SoC – Allwinner S3 Cortex-A7 @ 1.2GHz with 128MB DDR3 RAM at 1333 MHz Storage -MicroSD card slot, configuration EEPROM, optional NAND/eMMC/SPI Flash on socket Camera I/F MIPI camera connector with RPi pinout Parallel CSI camera connector Display – LCD connector for LCD-OLinuXino 4.3″ to 15.6″ displays Audio – Audio in and out via 3.5mm audio jacks Connectivity Fast Ethernet with PoE option WiFi / BT module with RTL8723BS Expansion – UEXT connector Misc – Buttons Power Supply …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Lixil AI-based Toilet Analyzes Shape & Size of Feces with Camera and LEDs

Earlier this year, we wrote about machine learning & image processing in embedded systems using pasta type classification as an example. Lixil Group, a Japanese company manufacturing housing equipment, is working on a concept using similar technology, but instead of classifying pasta, they implemented the technology into an AI-based toilet that checks the shape and size of feces of people living in elderly facilities. Lixil’s toilet was unveiled at the 46th International Home Care & Rehabilitation Exhibition (HCR 2019) in Tokyo at the end of last month. The system relies on a camera and two LED’s placed on the back of the seat, which turn on when the user sits on the seat. Once the job is done, images of the feces are taken automatically and classified into seven categories as specified by the Bristol stool chart. Classification happens within a few seconds, and results can be check by staff members using a computer or tablet. The goal is probably …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

STEEReoCAM is a 3D Stereo Camera for NVIDIA Jetson Nano, TX2, & AGX Xavier Dev Kits

STEEReoCam 2MP 3D Stereo Camera The latest e-con systems camera added to the lineup is the STEEReoCam. A 2MP 3D MIPI compliant stereo camera that works with the NVIDIA Jetson Nano, AGX Xavier, and Jetson TX2 development kits.   Improved Overall Function The camera has greater accuracy and depth range, with an OmniVision 1/2.9″ OV2311 global shutter CMOS sensor.  And the STEEReoCam comes bundled with CUDA the proprietary accelerated stereo SDK, that uses the GPU in the NVIDIA Tegra processors. AI and IoT Applications The camera is targeted towards depth sensing, AVG, robotics, face and gesture recognition, drones, medical procedure robots, and embedded visions. Software Development Kit e-Con Systems provides a Software Development Kit (SDK) package for the camera designed to work with NVIDIA Jetson development boards. The SDK is built on OpenCV 3.4.2 and CUDA Compute Capability 5.3/7.2/6.2. Sample Linux applications, some of which are shown in the video above, include TaraXL Parallel Viewer, TaraXL Studio Application, Save DepthMap …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

SolidRun ClearFog GTR A385 NVR Platforms Feature Up to 8 Gigabit Ethernet PoE Ports

SolidRun ClearFog GTR A385 NVR

A Networking Video Recorder (NVR) is designed to record and playback videos from multiple IP cameras usually connected over Ethernet, and in many cases powered over Ethernet (PoE). The main purpose is for security applications allowing caretakers to monitor multiple cameras at the same time on a mosaic screen. There are plenty of turnkey NVR solutions on the market, but SoliRun, an embedded systems company known for its modules and single board computers, recently introduced the ClearFog GTR A385 family that supports up to eight PoE/PoE+ Gigabit Ethernet Ports. The ClearFog GTR A385 family currently includes two modules with GTR S4 supporting up to four cameras, and GTR L8 up to eight cameras. Specifications: SoC – Marvell ARMADA A385 dual-core Armv7 (Cortex A9 class) up to 1.3Ghz System Memory – Up to 2GB on-board DDR3L Storage – 8GB eMMC flash (default),  2x 7 pin SATA (optional replacement for 2 x mPCIe slots) Connectivity 1x 1GbE WAN supporting up to 802.3bt …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

TIL: The Android Camera App Supports QR Code Scanning (in Some Phones)

Android Camera QR Code

QR Code are pretty common, and until today I used a third-party app to scan the codes and get the embedded information such as a webpage. But I’ve just read in LinkedIn that the default camera app can read QR codes. No need to install any third-party app, no need to reach any menu, just point for two or three seconds and it will work as shown in the short video below.  I’m always running out of space on with Xiaomi Mi A2 phone since it only has 32GB flash, and no MicroSD card slot.  So if beside saving some time while scanning QR code, I can get rid of one app that’s always a plus. Except it does not work on my phone. Instead I had to tap on the right of the camera app to switch to Google Lens (or launch Google Lens manually), and the QR code will automatically be detected. It’s not ideal. but it …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Tiny USB WiFi Camera Supports Motion and AI Human Detection

USB WiFi Camera

When I first saw U21 HD camera it reminded me of SOOCOO G1 is action camera with a flexible stick, since the camera also comes with a flexible hose which allows you to orient it as you please. But it’s a different bear, as U21 is a surveillance camera powered over USB and featuring WiFi connectivity. I can’t see any motion detection, so it may have some dose of “AI” since it claims to support motion and human detection so you only get relevant alerts. It is currently sold (pre-orders) on Banggood for $33.65 including shipping with order starting to be processed on October 30th. U21 USB WIFI camera key features and specifications: MCU / WiSoC – No information (yet) Storage – MicroSD card slot up to 128GB for up to one month of recording (8GB = 2 days); Cloud storage via third party (paid) Camera – 14mm lens, HD resolution Alerts – Motion detection, AI human detection (provided and …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Atomic Pi x86 SBC Meets Intel Neural Compute Stick 2 in $99 Neural Computing DevKit (Crowdfunding)

Atomic Pi Neural Computing Development Kit

IoT Team launched the $34 Atomic Pi SBC powered by an Intel Atom x5-Z8350 processor via a Kickstarter campaign last December. At the time, it only ships to the US, and looked too good to be true. But the thing is real coming from a failed robotics project, and the low-cost x86 board went back for sale via Amazon and other channels with worldwide availability last spring. The price has even gone a bit lower as you’ll find it for $32.95 on Amazon. Note that it requires some technical skills to get started and with 16GB eMMC flash it only supports Liux distributions such as Ubuntu 18.04, and installing Windows 10 is possible, but you’ll be seriously limited. Atomic Pi is back in the news, as IoT Team has now launched another Kickstarter campaign for the board, except it’s not sold standalone, but instead as part of a $99 neural computing development kit that combines Atomic Pi SBC with 2GB …

Support CNX Software – Donate via PayPal or become a Patron on Patreon