当社はデータインフラストラクチャの将来を開拓しています。

製品
会社情報
サポート

October 17th, 2018

マーベルは Arm TechCon 2018 で AWS Greengrass によるエッジコンピューティングを実証します

By Maen Suleiman, Senior Software Product Line Manager, Marvell

and Gorka Garcia, Senior Lead Engineer, Marvell Semiconductor, Inc.

Thanks to the respective merits of its ARMADA® and OCTEON TX® multi-core processor offerings, Marvell is in a prime position to address a broad spectrum of demanding applications situated at the edge of the network. These applications can serve a multitude of markets that include small business, industrial and enterprise, and will require special technologies like efficient packet processing, machine learning and connectivity to the cloud. As part of its collaboration with Amazon Web Services® (AWS), Marvell will be illustrating the capabilities of edge computing applications through an exciting new demo that will be shown to attendees at Arm TechCon – which is being held at the San Jose Convention Center, October 16th-18th.

This demo takes the form of an automated parking lot. An ARMADA processor-based Marvell MACCHIATObin® community board, which integrates the AWS Greengrass® software, is used to serve as an edge compute node. The Marvell edge compute node receives video streams from two cameras that are placed at the entry gate and exit of the parking lot. The ARMADA processor-based compute node runs AWS Greengrass Core; executes two Lambda functions to process the incoming video streams and identify the vehicles entering the garage through their license plates; and subsequently checks whether the vehicles are authorized or unauthorized to enter the parking lot.

最初のLambda関数は、自動ナンバープレート認識(OpenALPR)ソフトウェアを実行します。そして、ナンバープレート番号を取得し、それをゲートID(Entry / Exit)とともに、 DynamoDB® データベースにアクセスするAWS®クラウドで実行されているLambda関数に渡します。 クラウドのLambda関数は、DynamoDBホワイトリストデータベースの読み取りを担当し、ナンバープレートが認可された車に属しているかどうかを判断します。この情報は、MACCHIATObinボード上のネットワークの端にある2番目のLambda関数に返送され、駐車場の容量の管理とゲートの開閉を担当します。このLambda関数は、エッジのアクティビティをAWS CloudElasticsearch®サービスに記録します。これは、オープンソースのデータ視覚化エンジンである Kibana®,のバックエンドとして機能します。 Kibanaを使用すると、遠隔地の操作員が駐車場の混雑具合、入口ゲートのステータス、出口ゲートのステータスに関する情報に直接アクセスできます。さらに、AWS Cognitoサービスは、Kibanaへのアクセスのためにユーザーを認証します。

 

 

After the AWS Cloud Lambda function sends the verdict (allowed/denied) to the second Lambda function running on the MACCHIATObin board, this MACCHIATObin Lambda function will be responsible for communicating with the gate controller, which is comprised of a Marvell ESPRESSObin® board, and is used to open/close the gateway as required.

The ESPRESSObin board runs as an AWS Greengrass IoT device that will be responsible for opening the gate according to the information received from the MACCHIATObin board’s second Lambda function.

This demo showcases the capabilities to run a machine learning algorithm using AWS Lambda at the edge to make the identification process extremely fast. This is possible through the high performance, low-power Marvell OCTEON TX and ARMADA multi-core processors. Marvell infrastructure processors’ capabilities have the potential to cover a range of higher-end networking and security applications that can benefit from the maturity of the Arm® ecosystem and the ability to run machine learning in a multi-core environment at the edge of the network.

Those visiting the Arm Infrastructure Pavilion (Booth# 216) at Arm TechCon (San Jose Convention Center, October 16th-18th) will be able to see the Marvell Edge Computing demo powered by AWS Greengrass.

For information on how to enable AWS Greengrass on Marvell MACCHIATObin and Marvell ESPRESSObin community boards, please visit http://wiki.macchiatobin.net/tiki-index.php?page=AWS+Greengrass+on+MACCHIATObin and http://wiki.espressobin.net/tiki-index.php?page=AWS+Greengrass+on+ESPRESSObin.

 

 

Tags:

コメントは現在使用できません。