Computer vision

Enhance smart cities with AI-enabled applications leveraging computer vision technology.

To achieve better understanding of and safety for its citizens, public sector organizations want to turn anonymized images and videos of people, places, and things into valuable insights and reduce the time spent analyzing large volumes of content. Computer vision technology allows public sector organizations to automate contextual tagging of images and videos. Customizable tagging can include image location, probable demographic information, and facial, vehicle, and brand matches. This enables city planners to understand gender, age, population, and traffic patterns and law enforcement to ensure safety and security in the community.


Deep Vision AI, Inc.

Deep Vision AI, Inc. provides intelligent image and video analysis and offers an API running on Amazon Web Services (AWS), can process images and video content in real time to provide location coordinates of the detected faces, classify them by age and gender, and identify subjects of interest. Your own gallery of face images can be added to a private gallery hosted on AWS, and the Deep Vision API will start recognizing custom faces immediately. Additionally, the facial analysis can be complemented with Deep Vision’s Visual Context model, which provides thousands of general concepts, such as tattoo presence or known hair color.

 Common applications:

  • Curate and organize your visual data with automated image tagging
  • Search and recommend products with visual search
  • Optional custom computer vision models tuned to your needs

Deep Vision API allows the processing of images and video on a frame-by-frame basis as illustrated below. When an image is uploaded into Amazon Simple Storage Service (Amazon S3), an AWS Lambda function will call the computer vision API, and results will be pushed to Amazon Elasticsearch Service (Amazon ES). Viewer applications can leverage the indexed results to get access to the image.

Deep Vision AP diagram
Global Emancipation Network

Global Emancipation Network (GEN) fights human trafficking

The deployment of Deep Vision’s visual recognition tools provides the ability to gain real-time insight into image sets and video feeds. As a result, GEN has referred 989 suspected traffickers and victims to law enforcement. Using Deep Vision, GEN has already processed 10 million images with striking results.

Quotes icon
Deep Vision’s system that recognizes and identifies visual clues, identifies facial matches, and categorizes visual data, is empowering GEN’s users to prioritize leads and facilitate the identification of persons of interest. These AI-powered visual tools are significantly speeding up the outreach and response time, two critical components to find victims of human trafficking.
- Sherrie Caltagirone, Global Emancipation Network Executive Director
AWS Marketplace

AWS Marketplace is a digital catalog with thousands of software listings from independent software vendors that make it easy to find, test, buy, and deploy software that runs on AWS.

Have questions? Have tips?

We're here to help you get started with AWS Marketplace. Ask for or give advice on the AWS Marketplace discussion forum.

Have questions? Have tips?

We're here to help you get started with AWS Marketplace. Ask for or give advice on the AWS Marketplace discussion forum.