This Guidance demonstrates how to use annotated data to train machine learning (ML) models that help with transportation and logistics yard management. Transportation and logistics yards are complex environments that involve time-consuming manual tracking and monitoring activities. This architecture uses data from these environments to generate ML-powered insights to improve yard management.
Recorded videos are used as input to create annotated data. The data is stored in a file system for later use.
A computer vision (CV) model is trained in the ML training module using annotated data.
In the ML training module, Amazon SageMaker infrastructure is critical for training custom CV models. The models are trained to detect physical assets using optical recognition.
The trained model and business logic application is deployed to the AWS Panorama Appliance. Live internet protocol (IP) cameras send a feed to this appliance. Feeds are used for inference at the edge and are not recorded.
The output from the AWS Panorama Appliance is used to create a web application hosted on an Amazon Elastic Compute Cloud (Amazon EC2) instance.
End users access this web application through Amazon CloudFront. The web application presents a view of assets in the facility and a dashboard interface powered by Amazon QuickSight.
Optional: Amazon Virtual Private Cloud (Amazon VPC) peering connects data to other external yard systems for enhanced functionality of asset tracking and monitoring.
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
This architecture displays information on working statistics through services that allow for quick feedback, recovery, and refactoring.
Data is encrypted in transit and at rest. The architecture uses the principle of least privilege and enforced login to protect access to data. Each layer of the application is secured and monitored for traceability.
The architecture distributes workloads to avoid a single point of failure. It uses tracking key performance indicators (KPIs) to monitor reliability for production workloads.
The architecture uses serverless functions (such as AWS Lambda) where possible in addition to a data driven approach.
Customers pay only for resources used. Monitoring services check that applications are using resources efficiently so that customers do not pay for more resources than they actually need.
Serverless and managed services match instance size and usage to avoid wasted compute power. This architecture maximizes energy efficiency by adopting and aligning to a mature deployment approach using key AWS services, such as SageMaker, Amazon EC2, and AWS Glue.
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.