The mission to create a searchable database of Earth's surface | Will Marshall

翻译人员: Tianji (Homer) Li 校对人员: Yolanda Zhang

Four years ago, here at TED,

4年前，就在TED的讲台上，

I announced Planet's Mission 1:

我公布了地球任务1号：

to launch a fleet of satellites

一个为了每天拍摄地球全貌

that would image the entire Earth, every day,

而发射一系列卫星的任务，

and to democratize access to it.

并让大众能获得这些信息。

The problem we were trying to solve was simple.

我们要解决的问题很简单，

Satellite imagery you find online is old, typically years old,

网上你能找到的卫星 图片很旧，甚至早就过时了，

yet human activity was happening on days and weeks and months,

但是人类活动每天、 每周、每月都在发生，

and you can't fix what you can't see.

我们不能解决自己看不见的问题。

We wanted to give people the tools to see that change and take action.

我们想要给人们工具去 看见变化，并且采取行动。

The beautiful Blue Marble image, taken by the Apollo 17 astronauts in 1972

阿波罗17号的宇航员在1972年 照下了美丽的蓝色星球图片，

had helped humanity become aware that we're on a fragile planet.

帮助人们了解到，我们生活在 一个脆弱的星球上。

And we wanted to take it to the next level,

我们想要继续这项事业，

to give people the tools to take action, to take care of it.

为人们提供保护地球的工具。

Well, after many Apollo projects of our own,

在完成了多个我们自己的阿波罗任务，

launching the largest fleet of satellites in human history,

发射了人类历史上数量 最多的一组卫星后，

we have reached our target.

我们完成了既定目标。

Today, Planet images the entire Earth, every single day.

今天，Planet每天都在 记录着地球的全貌。

Mission accomplished.

任务完成。

（掌声）

(Applause)

Thank you.

谢谢。

It's taken 21 rocket launches --

这个任务经历了21次火箭发射——

this animation makes it look really simple -- it was not.

这个动画让整个过程看起来 很轻松——但事实并非如此。

And we now have over 200 satellites in orbit,

现在我们有超过200个卫星 在轨道上环绕运行，

downlinking their data to 31 ground stations we built around the planet.

将搜集到的数据发送到31个全球站点。

In total, we get 1.5 million 29-megapixel images of the Earth down each day.

每天，我们总计得到150万张 29兆像素的地球表面图片。

And on any one location of the Earth's surface,

并且，在地球表面任意一点，

we now have on average more than 500 images.

我们现在拥有平均超过500张图片。

A deep stack of data, documenting immense change.

一组巨大的数据， 记录着巨大的改变。

And lots of people are using this imagery.

很多人在使用这些图片。

Agricultural companies are using it to improve farmers' crop yields.

农业企业用他们来提高农民的产量。

Consumer-mapping companies are using it to improve the maps you find online.

商业地图公司用他们来 提高地图的精度。

Governments are using it for border security

政府用他们来监管边疆安全，

or helping with disaster response after floods and fires and earthquakes.

或是应对自然灾害， 比如洪水、火灾或地震。

And lots of NGOs are using it.

很多非政府组织也在用它们

So, for tracking and stopping deforestation.

去追踪并阻止森林砍伐，

Or helping to find the refugees fleeing Myanmar.

帮助找到逃离缅甸的难民，

Or to track all the activities in the ongoing crisis in Syria,

或追踪叙利亚危机中的活动，

holding all sides accountable.

以令各方势力负责。

And today, I'm pleased to announce Planet stories.

今天，我有幸能够宣布 Planet stories的上线。

Anyone can go online to planet.com

任何人都可以登陆planet.com，

open an account and see all of our imagery online.

创建一个账户，就能 在网上看到所有的图片。

It's a bit like Google Earth, except it's up-to-date imagery,

这是一个实时版的 Google Earth，

and you can see back through time.

你还可以看到历史数据。

You can compare any two days

你可以比较任何两天，

and see the dramatic changes that happen around our planet.

然后发现我们的星球 发生的巨大改变。

Or you can create a time lapse through the 500 images that we have

或者你可以用这500张照片 创造一个延时视频，

and see that change dramatically over time.

去显示该地点随着时间 发生的巨大变化，

And you can share these over social media.

你还可以把它们 分享到社交网络上。

It's pretty cool.

很强大的工具。

(Applause)

（掌声）

谢谢。

Thank you.

We initially created this tool for news journalists,

我们最初为新闻工作者 创造了这个工具，

who wanted to get unbiased information about world events.

因为他们想得到对于世界 不带偏见的信息。

But now we've opened it up for anyone to use,

但现在我们把它向公众开放，

for nonprofit or personal uses.

作为非盈利或个人用途。

And we hope it will give people the tools to find and see the changes on the planet

我们希望这个工具能够让人们 发现地球发生的变化，

and take action.

并做出改变。

OK, so humanity now has this database of information about the planet,

那么人类现在有了这个不断变化的

changing over time.

地球数据库。

What's our next mission, what's Mission 2?

我们的下一个任务是什么呢？

In short, it's space plus AI.

简而言之， 就是空间加上人工智能。

What we're doing with artificial intelligence

我们利用人工智能

is finding the objects in all the satellite images.

检索卫星图片中的事物。

The same AI tools that are used to find cats in videos online

网上用来在视频中标记猫狗的AI工具，

can also be used to find information on our pictures.

同样可以用来处理我们的照片。

So, imagine if you can say, this is a ship, this is a tree,

想象这里有艘船，这里有棵树，

this is a car, this is a road, this is a building, this is a truck.

这是辆车，这是条路， 这是个大楼，这是个卡车。

And if you could do that for all of the millions of images

如果你能够对 每天产生的几百万张图片

coming down per day,

这样处理，

就基本上创造出了一个数据库，

then you basically create a database

包含了地球上每天存在的有形事物。

of all the sizable objects on the planet, every day.

And that database is searchable.

并且这个数据库是可以被搜索的。

So that's exactly what we're doing.

这就是我们在做的事。

Here's a prototype, working on our API.

这是一个使用了我们API的原型。

This is Beijing.

这是北京。

So, imagine if we wanted to count the planes in the airport.

如果我们想要统计机场的飞机数量，

We select the airport,

只需要选择机场，

and it finds the planes in today's image,

程序就会检索出今天照片中的飞机，

and finds the planes in the whole stack of images before it,

和以前所有照片中的飞机，

and then outputs this graph of all the planes in Beijing airport over time.

然后它生成了这张标记了 北京机场飞机的统计图。

Of course, you could do this for all the airports around the world.

当然，你可以对世界上 任何一个机场这样操作。

And let's look here in the port of Vancouver.

让我们来看看温哥华的一个港口。

So, we would do the same, but this time we would look for vessels.

我们用同样的流程来统计船只。

So, we zoom in on Vancouver, we select the area,

放大并选中温和华，搜索这片区域，

然后我们搜索船只，

and we search for ships.

And it outputs where all the ships are.

就会得到船只的情况。

想象一下这将为负责 追踪并组织非法捕鱼的

Now, imagine how useful this would be to people in coast guards

who are trying to track and stop illegal fishing.

海岸保卫人员提供多么大的帮助。

合法的捕鱼船只

See, legal fishing vessels

transmit their locations using AIS beacons.

用AIS灯塔传达他们的位置，

But we frequently find ships that are not doing that.

但我们经常发现违反规则的船只。

The pictures don't lie.

图片不会撒谎。

And so, coast guards could use that

所以，海岸保卫人员可以利用这个信息

and go and find those illegal fishing vessels.

来发现非法船只。

And soon we'll add not just ships and planes

我们将会很快加入不局限于

飞机船只的其他对象，

but all the other objects,

and we can output data feeds

并且我们可以生成这些地点的

of those locations of all these objects over time

对象数据流，

that can be integrated digitally from people's work flows.

从人们的工作流程中 进行数字化集成。

In time, we could get more sophisticated browsers

未来我们还可以建立一个 更复杂的浏览器，

that people pull in from different sources.

让人们放入不同来源的信息。

But ultimately, I can imagine us abstracting out the imagery entirely

但是最终，我们可以把图像完全抽象化，

and just having a queryable interface to the Earth.

产生一个可检索的地球表面界面。

Imagine if we could just ask,

想象一下我们可以这样问，

"Hey, how many houses are there in Pakistan?

“巴基斯坦有多少栋楼房？

Give me a plot of that versus time."

对时间做个统计图。”

"How many trees are there in the Amazon

“亚马逊有多少树？

and can you tell me the locations of the trees that have been felled

还有从上周到这周

between this week and last week?"

倒下的树的地点？”

Wouldn't that be great?

这不是很棒吗？

Well, that's what we're trying to go towards,

这就是我们想要达到的目标，

and we call it "Queryable Earth."

我们叫它“可检索地球”。

So, Planet's Mission 1 was to image the whole planet every day

地球任务1号负责 每天记录地球表面的图像，

and make it accessible.

并对大众开放。

Planet's Mission 2 is to index all the objects on the planet over time

地球任务2号负责 对地球上所有事物编码，

and make it queryable.

生成检索信息。

Let me leave you with an analogy.

不妨这样类比，

Google indexed what's on the internet and made it searchable.

Google把互联网上的事物编码， 建立了搜索引擎，

Well, we're indexing what's on the Earth and making it searchable.

我们要将地球上所有事物编码， 同样方便大家查询。

Thank you very much.

非常感谢！

(Applause)

（掌声）