The smart street lighting project was implemented by Innodisk in Taipei City, the capital of Taiwan, together with the Project Management Office located there. The solution consists of lighting, safety alerts, traffic assessments, parking detection, and environmental detection by incorporating air quality sensors.

One challenge in implementing the project was the latency in automatic license plate recognition (ALPR). This is where the Aetina Edge AI platform came into play. It achieves high-resolution image recognition in real time. Then, various environmental indicators need to be captured simultaneously via multiple sensors. Sysinno’s iAeris3 outdoor air quality detector provides environmental reports including temperature, humidity, volatile organic compounds, formaldehyde, ozone, sulfur dioxide and nitrogen dioxide. The user can select up to nine air factors at a time. Another task was to integrate external components, such as cameras, that require power. The Aetina Mini Series M2 is equipped with PoE (Power over Ethernet). This palm-sized device has high performance with low power consumption. The storage used is Innodisk M.2 (P42) 3TE6 SSD – DRAM-less SSD with PCIe interface and industrial 3D TLC NAND flash.

Aetina’s M2 mini-series with two PoE-powered cameras, together with Innodisk’s DRAM and flash memory and Sysinno’s outdoor air detector, is a complete intelligent street lighting solution. It provides safety alerts, traffic assessments, parking detection, and environmental information.

Factory automation using AI – Automated optical inspection with real-time inference.

Printed electronic component manufacturing involves roll-to-roll (R2R), trimming, surface optical inspection, and defect marking.

Of critical importance is a fast and highly accurate print defect inspection system to detect and prevent damage and defects during the various production steps. Without AI, employees must manually inspect each product. This inspection takes an average of three seconds. In addition, the accuracy of the manual inspection can vary widely per inspector. To make this process more efficient and reduce inaccuracies, Innodisk developed an AI solution for automated optical inspection (AOI).

It had to take into account that setting up cameras, sensors and AI computing platforms is typically very time-consuming and unmanned systems often crash. Technicians who are then deployed on site are usually very costly in the process. Innodisk’s total solution brings together all aspects of AI computing platforms in a simple way, and the InnoAgent out-of-band remote management module allows systems to be restarted from any location.

Innodisk’s solution combines the benefits of the EXOU-X261 FPGA Machine Vision Solution Kit and the InnoAgent out-of-band module to achieve automated machine vision inspection with out-of-band remote management. The system uses Deep Learning to detect and flag assembly defects. In addition, the system can be deployed and managed on a large scale, enabling fully autonomous inspection in any factory. Thanks to the integrated InnoAgent module, the system is highly available and can be restarted remotely from any location if the operating system experiences problems such as a blue screen or the primary network connection fails. The InnoAgent out-of-band module also enables system statistics to be monitored globally via Innodisk’s iCAP platform.

ASIC solution in transportation with traffic flow calculation and vehicle detection.

Traffic management is critical to ensuring road mobility and traffic flow. Real-time control and prediction are the first steps towards smarter traffic management. Innodisk’s AI department was tasked with developing a total solution that ensures high performance and near 100% availability. Real-time control and prediction requires high-performance AI computers, and safety-critical systems require high availability and 24/7 remote access.

The Innodisk AOSI-020 fanless AI system with Hailo-8TM Edge AI processor, which offers up to 8Tera operations per second, was used. Innodisk InnoAgent OOB remote management module enables out-of-band remote management of systems even when they have crashed. The Innodisk SATADOM-SH 3TE7 supports multiple industrial features, including TRIM, NCQ and S.M.A.R.T.

The components form a high-performance traffic management system. This has nearly 100 percent uptime because the system can be managed from any location using InnoAgent’s out-of-band remote management capabilities. In addition to high availability, the InnoAgent module can be used to send remote commands to the system, such as restart and power on/off.

Über Innodisk Europe B.V.

Aetina’s M2 mini series with two PoE-powered cameras, together with Innodisk’s DRAM and flash memory and Sysinno’s outdoor air detector, is a complete intelligent street lighting solution. It provides safety alerts, traffic assessments, parking detection and environmental information.

Innodisk’s printed electronic device manufacturing solution combines the benefits of the EXOU-X261 FPGA Machine Vision Solution Kit and the InnoAgent out-of-band module to achieve automated machine vision inspection with out-of-band remote management. Thanks to the integrated InnoAgent module, the system is highly available and can be restarted remotely. The InnoAgent out-of-band module enables system statistics to be monitored globally via the iCAP platform.

Inndodisk’s ASIC solution in transportation with traffic flow calculation and vehicle detection uses the Innodisk AOSI-020 fanless AI system with Hailo-8TM Edge AI processor, which provides up to 8Tera operations per second. The Innodisk InnoAgent OOB remote management module enables out-of-band remote management of systems, even when they have crashed. The Innodisk SATADOM-SH 3TE7 supports several industrial features, including TRIM, NCQ and S.M.A.R.T.

#Innodisk #Edge #AI #GPU

Firmenkontakt und Herausgeber der Meldung:

Innodisk Europe B.V.
Pisanostraat 57
NL5623CB Eindhoven
Telefon: +49 (152) 5100 6027
http://www.innodisk.com/

Ansprechpartner:
Patrik Stocks
Innodisk Europe B.V.
Telefon: +49 (152) 5100-6027
E-Mail: Patrik_stocks@innodisk.com
Für die oben stehende Pressemitteilung ist allein der jeweils angegebene Herausgeber (siehe Firmenkontakt oben) verantwortlich. Dieser ist in der Regel auch Urheber des Pressetextes, sowie der angehängten Bild-, Ton-, Video-, Medien- und Informationsmaterialien. Die United News Network GmbH übernimmt keine Haftung für die Korrektheit oder Vollständigkeit der dargestellten Meldung. Auch bei Übertragungsfehlern oder anderen Störungen haftet sie nur im Fall von Vorsatz oder grober Fahrlässigkeit. Die Nutzung von hier archivierten Informationen zur Eigeninformation und redaktionellen Weiterverarbeitung ist in der Regel kostenfrei. Bitte klären Sie vor einer Weiterverwendung urheberrechtliche Fragen mit dem angegebenen Herausgeber. Eine systematische Speicherung dieser Daten sowie die Verwendung auch von Teilen dieses Datenbankwerks sind nur mit schriftlicher Genehmigung durch die United News Network GmbH gestattet.

counterpixel