Amazon Rekognition allows you to easily add image and video analysis capabilities to your application. You only need to provide images or videos to the Rekognition API, and the service can identify objects, people, text, scenes, and activities, and detect any inappropriate content. Amazon Rekognition also provides highly accurate facial analysis and facial recognition functions for the images and videos you provide. You can detect, analyze, and compare faces in a variety of use cases, including user verification, people counting, and public safety.
Amazon Rekognition is based on mature and highly scalable deep learning technology also developed by Amazon computer vision scientists. It can analyze billions of images and videos every day without using any machine learning expertise. Amazon Rekognition is an easy-to-use API that can quickly analyze any image or video file stored in Amazon S3. Amazon Rekognition always learns from new data, and we will continue to add new tags and face recognition capabilities to this service.
https://docs.aws.amazon.com/zh_cn/rekognition/index.html
What is Amazon Rekognition Video?
Amazon Rekognition Video is a deep learning-based video analysis service that can detect activities, understand the movement of people in the screen, and identify you stored in Amazon S3 People, objects, celebrities, and inappropriate content in’s videos. The analysis results are equipped with corresponding timestamps, allowing you to easily create an index for extremely detailed video searches. When recognizing people and faces, Rekognition Video will also return the bounding box coordinates to indicate the specific location of the person or face in the screen.
In addition, Amazon Rekognition Video can also monitor the live video stream you create through Amazon Kinesis Video Steams to detect and recognize faces based on the face data you provide.
Amazon Rekognition Video can be real-time Analyze your live video stream to detect and recognize faces. You only need to input streaming video from Amazon Kinesis Video Streams into Rekognition Video, and you can perform face recognition based on a collection of tens of millions of faces you provide with very low latency. For batch processing use cases, Amazon Rekognition Video can also analyze previously recorded video data stored in Amazon S3.
Amazon Rekognition Video is a deep learning-based video analysis service that can detect activities, understand the movement of people in the screen, and recognize you People, objects, celebrities, and inappropriate content in videos stored in Amazon S3. The analysis results are equipped with corresponding timestamps, allowing you to easily create an index for extremely detailed video searches. When recognizing people and faces, Rekognition Video will also return the bounding box coordinates to indicate the specific location of the person or face in the screen.
In addition, Amazon Rekognition Video can also monitor the live video stream you create through Amazon Kinesis Video Steams to detect and recognize faces based on the face data you provide.
Amazon Rekognition Video can be real-time Analyze your live video stream to detect and recognize faces. You only need to input streaming video from Amazon Kinesis Video Streams into Rekognition Video, and you can perform face recognition based on a collection of tens of millions of faces you provide with very low latency. For batch processing use cases, Amazon Rekognition Video can also analyze previously recorded video data stored in Amazon S3.
Analyze streaming video in real time
Amazon Rekognition Video can analyze your live video stream in real time to detect and recognize faces. You only need to input streaming video from Amazon Kinesis Video Streams into Rekognition Video, and you can perform face recognition based on a collection of tens of millions of faces you provide with very low latency. For batch processing use cases, Amazon Rekognition Video can also analyze previously recorded video data stored in Amazon S3.