What does this Amazon Web Services Solution do?

The IP camera AI SaaS solution aims to empower the security industry by providing artificial intelligence capabilities in the cloud. It helps you reduce the time of work of model training, architecture, and model deployment, from many days to a few minutes. The solution currently provides three AI algorithm functions: face detection, human figure detection, and face comparison. With this solution, you can quickly deploy an end-to-end SaaS services in the Amazon Web Services, and your end users can easily use these AI functions through API calls.

Amazon Web Services Solution Overview

The diagram below presents the architecture you can automatically deploy using the solution's implementation guide and accompanying Amazon CloudFormation template.
Architecture of Serverless Image Handler

Architecture Description

Amazon API Gateway: API Gateway is responsible for routing customers HTTP POST requests and it offers custom domain binding. Meanwhile, API gateway also provide API key configuration to control the requesters' access authority.

Amazon Lambda: Lambda function routes  HTTP POST request which contains input images with base64 format to SageMaker endpoint for inference and it dumps image and final response into S3 bucket for further performance check or data collection.

Amazon S3: S3 is used to store input requests and inferenced responses. The inferenced result can be used for next round of labelling, model training, parameter tuning, to increase the overall model performance.

Amazon SageMaker: SageMaker cluster handles customers inference request, the face detection, human body detection and face comparison models are loaded according deployment configuration. Sagemaker endpoints could be configured to auto-scaling according to requests' pattern to support high-concurrency application scenarios.


Note that the AI algorithms are packaged in Amazon ECR. You can choose the built-in AI algorithms or you could make althorithms of your own and then load , deploy and use them into this solution.

 

IP Camera AI SaaS Solution

Version 1.0.0
Last updated: 05/2021
Author: Amazon Web Services 

Estimated deployment time: 20 min

Source code 

Features

Easy to extend

The solution includes three built-in AI features (face detection, human figure detection, face comparison) and their code samples. Users can customize their own models, package the models into ECR images and integrate with the solution to extend the existing AI features.

Deploy as SaaS

By deploying the SaaS solution, you can use it by calling APIs. The APIs can be provided to downstream systems or be called directly by end-users. It is easy-to-use and cost saving..

Deploy features on demand

All the AI features are independent. You can deploy them seperately. For example, you can choose to deploy only the "face detection" feature.
Standard Product Icons (Features) Squid Ink
Explore all Amazon Web Services Solutions

Browse our portfolio of Amazon Web Services-built solutions to common architectural problems.

Learn more 
Next-Steps-Icon_Find-a-Partner-B
Find a Partner

Find Amazon Web Services certified consulting and technology partners to help you get started.

Learn more 
Standard Product Icons (Start Building) Squid Ink
Start building in the console

Sign-up and start exploring our services.

Get started