英文:
In AWS Rekognition is it possible to identify an person in a video from an Image?
问题
对于我的当前使用情况,我关注两个方面。一个是一个人的视频。另一个是这个人的照片。AWS Rekognition能帮我检测视频中的人是否与照片中的人是同一个吗?
英文:
For my current use case, I'm looking at 2 things. 1 is a video of a person. And 1 is a photo of this same person. Can AWS Rekognition help me to detect if the person in the video is the same one in the photo?
答案1
得分: 0
来自 使用Amazon Rekognition进行存储视频分析 - Amazon Rekognition:
> Amazon Rekognition Video是一个可以用来分析视频的API。使用Amazon Rekognition Video,您可以在存储在Amazon Simple Storage Service(Amazon S3)存储桶中的视频中检测标签、面部、人物、名人以及成人(暗示性和明确性)内容。您可以在媒体/娱乐和公共安全等领域中使用Amazon Rekognition Video。以前,扫描视频中的物体或人物需要一个人类观众花费很多小时,而且容易出错。Amazon Rekognition Video自动化了物体的检测以及它们在视频中出现的时间。
Rekognition允许创建一个面部集合,基本上是从照片中学到的一组面部。因此,您需要:
- 创建一个空的面部集合
- 提供一张照片并使用
IndexFaces()
将来自照片的面部加载到面部集合中 - 然后 搜索存储的视频以查找面部 - Amazon Rekognition
输出是一个包含视频中发现的面部集合中面部的时间的JSON列表(精确到毫秒)。
这里有一个示例:使用您作为主角的自动化视频编辑! | AWS Machine Learning Blog
英文:
From Working with stored video analysis - Amazon Rekognition:
> Amazon Rekognition Video is an API that you can use to analyze videos. With Amazon Rekognition Video, you can detect labels, faces, people, celebrities, and adult (suggestive and explicit) content in videos that are stored in an Amazon Simple Storage Service (Amazon S3) bucket. You can use Amazon Rekognition Video in categories such as media/entertainment and public safety. Previously, scanning videos for objects or people would have taken many hours of error-prone viewing by a human being. Amazon Rekognition Video automates the detection of items and when they occur throughout a video.
Rekognition allows the creation of a Face Collection, which is basically a set of faces learned from photos. So, you would need to:
- Create an empty Face Collection
- Provide a photo and use
IndexFaces()
to load the face from the photo into the Face Collection - Then Search stored videos for faces - Amazon Rekognition
The output is a big JSON list of times in the video when faces from the Face Collection are found in the video (down to the millisecond).
Here's an example: Automated video editing with YOU as the star! | AWS Machine Learning Blog
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库,让每个人都能够通过互相帮助和分享经验来进步。
评论