Amazon Rekognition Video is a fully managed machine learning (ML) service that supports both real time streaming video events and stored video analysis.

Amazon Rekognition streaming video events is a low cost, low latency service that can detect objects on video streams from connected cameras. Amazon Rekognition streaming video events returns the object detected such as a person, pet, or package, bounding box coordinates, a zoomed in image of the object detected, and the timestamp. You can deliver timely and actionable alerts when a desired object is detected.

Amazon Rekognition stored video analysis is a service to analyze your videos stored in Amazon S3 and detect objects, scenes, landmarks, celebrities, text, activities, and any inappropriate content. Rekognition Video stored video analysis also provides highly accurate facial analysis and facial search capabilities to detect, analyze, and compare faces, and helps you understand the movement of people in your videos. Each result or detection is paired with a timestamp so that you can easily create an index for detailed video search, or navigate quickly to an interesting part of the video for further analysis. For objects, faces, text, and people, Rekognition Video stored video analysis also returns bounding box coordinates, which is the specific location of the detection in the frame.

Use Cases

Connected Home

Amazon Rekognition Streaming Video Events is a low cost, low latency, and fully managed machine learning service for connected home use cases. This service detects objects such as people, pets, and packages from live video streams. You can deliver timely and actionable alerts when a desired object is detected, and minimize false alerts. You can create elegant automation experiences such as automatically turning on the garage light when a person is detected.

Media asset search and indexing

Using the object, scene, activity, celebrity, text and face analysis metadata generated by Amazon Rekognition Video, you can automatically index large archives of video assets, and make them easily searchable. Your operators can quickly find the assets they need, instead of manually looking through all videos. Using Amazon Rekognition Video, Amazon Transcribe, and end-to-end serverless AWS solutions such as Media2Cloud and Media Insights Engine, you can seamlessly curate, filter and monetize archives across their journey from tape to a Media Asset Management (MAM) system.

Compliance and brand safety

With Amazon Rekognition Video, you can quickly flag when inappropriate or brand-unsafe content appears in thousands of hours of assets. Instead of looking through every second of each asset, your human moderators only need to look at the timestamps flagged by Amazon Rekognition Video. Further, using the detailed hierarchy of moderation labels available, you can address the compliance needs of different international markets. To perform audio moderation, you can use metadata from Amazon Transcribe.

Contextual advertising

Amazon Rekognition Video enables you to serve advertisements that are most relevant to the video content shown. By using the labels, activities or celebrities detected at a certain timestamp, you can boost the effectiveness and returns of the advertisement that will be shown right after that content airs.

Retail store analytics

With Amazon Rekognition Video, you can analyze shopper behavior and density in your retail store by studying the path that each person follows. Using face analysis, you can also understand the average age ranges, gender distribution and emotions expressed by shoppers without identifying them.

Quick response to public safety challenges

Amazon Rekognition Video allows you to create applications that help find missing persons in stored or streaming videos. By searching for their faces against a database of missing persons that you provide, you can accurately flag potential matches and speed up a rescue operation.

Video segment detection

Amazon Rekognition Video enables you to streamline common file-based manual workflows for quality control, ad insertion, and content production. Using the frame-accurate in and out markers for segments such black frames with silence (used to demarcate ad breaks) or credits (used to insert ‘Next Episode’ prompts), human editors can avoid the tedious process of scrubbing a whole video from scratch.

Key features for streaming video events

Label detection

Amazon Rekognition streaming video events is a low cost, low latency, and fully managed service to detect objects such as people, pets, and packages in real-time. Amazon Rekognition streaming video events returns the object detected such as a person, pet, or package, bounding box coordinates, a zoomed in image of the object detected, and the timestamp. You can deliver timely and actionable alerts when a desired object is detected.

Learn More »

Face search

Amazon Rekognition streaming video events can analyze your live video streams in real time to detect and search for faces. By providing a stream from Amazon Kinesis Video Streams as an input to Rekognition Video, you can perform face search against a repository of your own images with very low latency.

Learn more »

Key features for stored video analysis

Object, scene, and activity detection

Amazon Rekognition Video automatically identifies thousands of objects such as vehicles or pets, scenes like a city, beach, or wedding, activities such as delivering a package or dancing, and landmarks. For each label detected, you get a confidence score. For common objects such as 'Person' or 'Car', you also get object bounding boxes to enable counting and object localization. Amazon Rekognition Video relies on motion in the video to accurately identify complex activities, such as “blowing out a candle” or “extinguishing fire”. Using this rich metadata, you can make your content searchable or serve advertisements that best match the context of the content preceding it.

Learn More »

Content moderation

Amazon Rekognition Video automatically detects inappropriate content such as nudity, violence or weapons in videos, and provides timestamps for each detection. You also get a hierarchical list of labels with confidence scores, describing sub-categories of unsafe content. For example, 'Graphic Female Nudity' is a sub-category of 'Explicit Nudity'. Confidence scores and detailed labels allow you to set up varied business rules to serve the compliance needs of different markets and geographies.

Learn More »

Text detection

Amazon Rekognition Video automatically detect and read text in videos, and provides the detection confidence, location bounding box, as well as the timestamp for each text detection. In addition, you get convenient options to filter out words by regions of interest (ROIs), word bounding box size, and word confidence score. For example, you may only want to detect text in the bottom third region for on-screen graphics or only the top left corner for reading scoreboards in a soccer game.

Learn More »

Celebrity recognition

With Amazon Rekognition Video, you can detect and recognize when and where well known persons appear in a video. The time-coded output includes the name and unique id of the celebrity, and URLs pointing to related content for the celebrity, for example, the celebrity's IMDB link.

Learn more »

Face detection and analysis

Amazon Rekognition Video can detect up to 100 faces in a video frame, and return the bounding box location. For each detected face, you can also get additional attributes such as gender, emotions, estimated age range, and whether the person is smiling, along with timestamps for each detection.

Learn More »

Face search

Amazon Rekognition Video can identify known people in a video by searching against a private repository of face images. You get a similarity score for each match, and timestamps for each instance where the same person is identified during the video. Amazon Rekognition Video can also cluster all unknown people in a video who don’t have any matches in the repository, and return timestamps with unique identifiers for each such person.

Learn more »

Person pathing

With Amazon Rekognition Video you can capture where, when and how each person is moving in your video. Amazon Rekognition also provides a unique index for each person found, allowing you to count the number of people in the video.

Learn more »



Abode Systems (Abode) offers homeowners a comprehensive suite of do-it-yourself home security solutions that sets up simply in minutes and enables homeowners to keep their families and property safe. Since the company’s launch in 2015, camera sensors have played an essential part in Abode’s solution, enabling customers to visually monitor their homes from anywhere.

"We are always focused on making technology choices that provide value to our customers and enable rapid growth while keeping costs low. With Amazon Rekognition Streaming Video Events, we could launch person, pet and package detection at a fraction of the cost of developing everything ourselves. For us it was a no-brainer, we didn’t want to create and maintain a custom computer vision service. We turned to the experts on the Rekognition team. Amazon Rekognition’s streaming video events APIs are accurate, scalable and easy to incorporate into our systems. The integration powers our smart notification features, so instead of a customer receiving 100 notifications a day, every time the motion sensor is triggered, they receive just 2 or 3 smart notifications when there is an event of interest present in the video stream."

Scott Beck, Chief Technology Officer - Abode Systems

VidMob is a technology platform that connects marketers with a global network of expert editors, animators, and motion graphic designers.

“Performance data isn’t a problem, but understanding why certain creative assets work better than others, and then having the ability to act on that information is. By building VidMob’s Agile Creative Suite™ on top of Amazon Rekognition, we are addressing two of the most significant marketer pain points. To date, our Agile Creative Suite has analyzed over 40,000 creative assets with Rekognition. The granularity of the data from Rekognition allows us to surface incredible insights for our clients, and enables them to see their content in a whole new way.”

Alex Collmer, CEO & Founder - VidMob

Pattern89 is the world's first data science coaching platform for paid social.

“Pattern89 uses Amazon Rekognition to provide our customers with deep data analysis including creative coaching to improve ad performance on Facebook and Instagram. Our customers have been able to implement our recommendations to reduce their ad spend, increase revenue, and improve efficiency metrics. We chose Amazon Rekognition because of its simple API, support for multiple media types, and its best-in-class labeling and face detection.”

Matt Brown, CTO - Pattern89

Learn more about Amazon Rekognition pricing

Visit the pricing page
Ready to build?
Get started with Amazon Rekognition Video
Have more questions?
Contact us