Video: Tips for Getting Started with Video AI Platforms

了解更多有关人工智能平台的信息流媒体的下一个事件.

阅读这段录音的完整文本:

小君海德: If you don’t have developers in-house at your organization, a lot of these vendors offer demo versions of their platforms that you can play around with. The free version of Microsoft Azure Video Indexer, for example, is quite robust. You can actually take widgets and embed them into your own systems. Of the four platforms we discuss in this article, Video Indexer is the most complete product that you can access without having to go through contract negotiations.

Google Cloud and AWS offer demos on their pages, but they don’t really expose them to the degree that you can embed them into your own system. 有人工智能平台, “嵌入”本质上意味着获取代码, 把I-Frame放进你的系统, 并在你的系统中加载他们的页面. The online demo versions of Google Cloud and AWS don’t allow that, 但是你可以上传你自己的视频, 等待应用程序处理它们, and see how well the service will work with your video.

IBM sells several Watson products, such as Video Enrichment (top right in Figure 1). 它们是api优先的. 从理论上讲, 你可以购买他们的付费产品, and communicate between your system and theirs to pull metadata into your system.

This is one of the big use cases for AI: You have this media asset manager (MAM) that houses all this metadata about all the assets being stored there. Wouldn’t it be great to have the computer generate some of that metadata for you, so that in addition to the title and the season and the episode name, 比如“车祸”,”“豹,和“小女婴。,或任何适用于你的内容的术语, that you can actually search and discover your content much more easily? The first thing your developers are going to want to learn about is, what’s the learning curve? What software development kit is available for each of these platforms?

AWS有一个客户端SDK, which basically acts as an accelerator so your developers don’t have to write all the code from scratch. They can build their code on top of the boilerplate AWS provides, with SDKs for Android, iOS, Java, .净等. My team of developers has played around with this SDK, 他们发现这本书包罗万象, 而且比谷歌云少得多.

One important step in choosing a video AI platform is to let your developers test whatever demo version is available and listen to their feedback, because your team is going to be more productive if they feel that they don’t have to spend as much time trying to grok how to work with the software. Like AWS, the Google Cloud platform has a good number of client SDKs: C#, node.js, Go, Java等. 但是从开发者的角度来看, 他们的API文档非常冗长, and it takes a lot of clicks to get to what you need. If I just want to know how to send my video up to their service, rather than seeing the signature of the payload that I want to upload, I have to wade through 3-4 paragraphs on every single data point within that signature.

IBM Cloud’s API reference lives behind a pay wall. You talk to the IBM Watson media people, and you say, “This is my use case. I want to play around with your system, because I think I’m going to buy it.“然后你可能会签一些合同. In my case, as an IBM partner, they were kind enough to share API documentation with me. 看起来很简单.

Azure Microsoft Video Indexer has a client SDK for .网只. 如果你没有 .NET developers in your shop, Video Indexer might not be the right solution for you. Amazon and Google have things like Java, Android, iOS, Ruby, and so on. Your developers might be able to build something faster on those platforms. Video Indexer文档非常出色. It’s well laid-out, and you can inline-test it as long as you have an active account.