ABOUT THE SPEAKER
Blaise Agüera y Arcas - Software architect
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces.

Why you should listen

Blaise Agüera y Arcas is principal scientist at Google, where he leads a team working on machine intelligence for mobile devices. His group works extensively with deep neural nets for machine perception and distributed learning, and it also investigates so-called "connectomics" research, assessing maps of connections within the brain.

Agüera y Arcas' background is as multidimensional as the visions he helps create. In the 1990s, he authored patents on both video compression and 3D visualization techniques, and in 2001, he made an influential computational discovery that cast doubt on Gutenberg's role as the father of movable type.

He also created Seadragon (acquired by Microsoft in 2006), the visualization technology that gives Photosynth its amazingly smooth digital rendering and zoom capabilities. Photosynth itself is a vastly powerful piece of software capable of taking a wide variety of images, analyzing them for similarities, and grafting them together into an interactive three-dimensional space. This seamless patchwork of images can be viewed via multiple angles and magnifications, allowing us to look around corners or “fly” in for a (much) closer look. Simply put, it could utterly transform the way we experience digital images.

He joined Microsoft when Seadragon was acquired by Live Labs in 2006. Shortly after the acquisition of Seadragon, Agüera y Arcas directed his team in a collaboration with Microsoft Research and the University of Washington, leading to the first public previews of Photosynth several months later. His TED Talk on Seadragon and Photosynth in 2007 is rated one of TED's "most jaw-dropping." He returned to TED in 2010 to demo Bing’s augmented reality maps.

Fun fact: According to the author, Agüera y Arcas is the inspiration for the character Elgin in the 2012 best-selling novel Where'd You Go, Bernadette?

More profile about the speaker
Blaise Agüera y Arcas | Speaker | TED.com
TED2010

Blaise Agüera y Arcas: Augmented-reality maps

Biaise Aguera y Arcas 示範應用增強實境技術的地圖

Filmed:
1,804,381 views

於 TED2010 的演講中,Blaise Aguera y Arcas 令人屏氣地示範了來自於微軟的,新的增強實境地圖技術。
- Software architect
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces. Full bio

Double-click the English transcript below to play the video.

00:15
About a year and a half ago,
0
0
2000
大約一年半前,
00:17
Stephen斯蒂芬 Lawler勞勒, who also gave a talk
1
2000
3000
Stephen Lawler 在 TED 2007 給了一個
00:20
here at TEDTED in 2007 on Virtual虛擬 Earth地球,
2
5000
2000
關於虛擬地球的演講,
00:22
brought me over to become成為 the architect建築師 of Bing Maps地圖,
3
7000
4000
也是他使我成爲 Bing 地圖的程式設計師,
00:26
which哪一個 is Microsoft's微軟的 online-mapping在線地圖 effort功夫.
4
11000
3000
Bing 地圖是微軟對於線上地圖的一次嘗試。
00:29
In the past過去 two and a half, we've我們已經 been very hard at work
5
14000
2000
過去的兩年半中,我們工作得很努力,
00:31
on redefining重新定義 the way maps地圖 work online線上.
6
16000
4000
我們試圖重新定義線上地圖是如何工作的。
00:35
And we really are seeing眼看 this in very different不同 terms條款
7
20000
2000
我們是真正的將它當作一個完全不同的名詞來看待,
00:37
from the kind of mapping製圖 and direction方向 site現場
8
22000
2000
改變大家過去對於線上地圖只是
00:39
that one is used to.
9
24000
2000
地圖和方向指引網頁的看法。
00:41
So, the first thing that you might威力 notice注意 about the mapping製圖 site現場
10
26000
2000
所以, 這個地圖網頁首先引起你注意的
00:43
is just the fluidity流動性 of the zooming縮放 and the panning搖攝,
11
28000
2000
是流暢的地圖縮放和平移,
00:45
which哪一個, if you're familiar at all with Seadragon海龍,
12
30000
2000
如果你熟悉「海龍」(Seadragon) 技術,
00:47
that's where it comes from.
13
32000
2000
這種流暢度就是來自於那個技術。
00:49
Mapping製圖 is, of course課程,
14
34000
2000
當然,地圖並不僅僅
00:51
not just about cartography製圖,
15
36000
2000
涉及製圖學,
00:53
it's also about imagery意象.
16
38000
2000
它也包含影像。
00:55
So, as we zoom-in放大 beyond a certain某些 level水平
17
40000
3000
所以當我們放大到一定的程度,
00:58
this resolves做出決議 into a kind of Sim City-like市樣
18
43000
3000
它就轉換成了類似遊戲《模擬城市》般
01:01
virtual虛擬 view視圖 at 45 degrees.
19
46000
2000
45 度角的虛擬視野。
01:03
This can be viewed觀看 from any of the cardinal樞機主教 directions方向
20
48000
2000
你可以從任何角度來看它,
01:05
to show顯示 you the 3D structure結構體 of the city, all the facades外牆.
21
50000
3000
它從各個角度向人們展示了城市的立體結構。
01:08
Now, we see this space空間, this three-dimensional三維 environment環境,
22
53000
6000
現在, 我們看到這個空間,這個立體的環境,
01:14
as being存在 a canvas帆布 on which哪一個
23
59000
3000
作爲一塊畫布,
01:17
all sorts排序 of applications應用 can play out,
24
62000
6000
各式各樣的應用程式都可以在上面進行發揮,
01:23
and map's地圖的 directions方向 are really just one of them.
25
68000
3000
而用地圖來指引方向,只是這些應用的其中之一。
01:26
If you click點擊 on this, you'll你會 see
26
71000
3000
如果你點擊這裡,
01:29
some of the ones那些 that we've我們已經 put out, just in the past過去 couple一對 of months個月
27
74000
3000
你可以看見,我們於過去幾個月中,從我們的地圖服務開放以來,
01:32
since以來 we've我們已經 launched推出.
28
77000
2000
所推出的東西。
01:34
So, for example, a couple一對 of days after the disaster災害 in Haiti海地,
29
79000
2000
比如,在海地受災後的幾天內,
01:36
we had an earthquake地震 map地圖 that showed顯示
30
81000
2000
我們的地震地圖就顯示了
01:38
before and after pictures圖片 from the sky天空.
31
83000
2000
震災前後的空拍照片。
01:40
This wonderful精彩 one which哪一個 I don't have time to show顯示 you
32
85000
2000
由於時間的關係,以下這個精彩的應用,我無法示範給你們看,
01:42
is taking服用 hyper-local超本地 blogs博客 in real真實 time
33
87000
3000
它能於第一時間,從該區域的部落格裡提取內容,
01:45
and mapping製圖 those stories故事, those entries
34
90000
2000
將部落格中提到的故事和記錄,
01:47
to the places地方 that are referred簡稱 to on the blogs博客.
35
92000
2000
在地圖上標識出來。
01:49
It's wonderful精彩.
36
94000
3000
這真的很棒!
01:52
But I'm going to show顯示 you some more candy糖果 sort分類 of stuff東東.
37
97000
3000
然而,我要給你們看一些比較吸睛的東西。
01:55
So, we see the imagery意象, of course課程,
38
100000
4000
當然,我們看到圖資,
01:59
not stopping停止 at the sky天空.
39
104000
3000
不僅僅是停留在空中的視角,
02:02
These little green綠色 bubbles泡泡 represent代表
40
107000
3000
這些綠色的小泡泡代表了
02:05
photosynthsphotosynths that users用戶 have made製作.
41
110000
2000
用戶群的像片合成的結果,
02:07
I'm not going to dive潛水 into them either, but photosynthsphotosynths are integrated集成 into the map地圖.
42
112000
3000
關於像片合成 (photosynths) 以及其與地圖的整合,我也就不深入探究了,
02:10
Everything that's cased套管 in blue藍色
43
115000
2000
所有的藍色地帶
02:12
is an area where we've我們已經 taken採取 imagery意象 on the ground地面 as well.
44
117000
5000
都是我們在地面上拍過照的地方,
02:17
And so, when you fly down --
45
122000
2000
因此, 當你往下飛 —
02:19
(Applause掌聲)
46
124000
2000
(掌聲)
02:21
Thank you. When you fly down to the ground地面,
47
126000
2000
謝謝, 當你飛到地表的時候,
02:23
and you see this kind of panoramic全景 imagery意象,
48
128000
3000
你便可以看見類似的全景圖像,
02:26
the first thing that you might威力 notice注意 is that it's not just a picture圖片,
49
131000
4000
你第一個會注意到的是,這並不僅是一張照片,
02:30
there's just as much three-dimensional三維 understanding理解 of this environment環境
50
135000
3000
它能了解這個立體的環境,
02:33
as there is of the three-dimensional三維 city from above以上,
51
138000
3000
就跟從空中俯瞰的立體城市一樣,
02:36
so if I click點擊 on something to get a closer接近 view視圖 of it,
52
141000
4000
所以當我點擊目標,靠近觀察,
02:40
then, the fact事實 that that transition過渡 looks容貌 as it does,
53
145000
3000
事實上,你可看到那個轉換的過程,
02:43
is a function功能 of all of that geometry幾何,
54
148000
2000
都是這個地圖背後對於幾何
02:45
all of that 3D understanding理解 behind背後 this model模型.
55
150000
4000
以及立體環境的了解在發生作用。
02:49
Now, I'll show顯示 you a fun開玩笑 app應用
56
154000
3000
現在,我要爲你們示範一個有趣的程式,
02:52
that -- we've我們已經 been working加工 on a collaboration合作 with our friends朋友 at FlickrFlickr的.
57
157000
7000
這是我們協同在 Flicker 的朋友一起開發的。
02:59
This takes FlickrFlickr的, georegisteredgeoregistered imagery意象
58
164000
3000
這個程式將 Flickr 裡有地理位置標籤的圖資,
03:02
and uses使用 photosynth-likePhotosynth的樣 processes流程
59
167000
3000
使用類似「像片合成」的程序,
03:05
to connect that imagery意象 to our imagery意象, so --
60
170000
4000
將那些圖資跟我們的圖資連結。
03:09
I'm not sure if that's the one I actually其實 meant意味著 to pull up, but --
61
174000
3000
我不確定這是我想要找的東西,
03:12
(Laughter笑聲)
62
177000
3000
(笑聲)
03:15
But notice注意 -- this is, of course課程, a popular流行 tourist遊客 site現場,
63
180000
4000
但是,你們可以看到, 這是一個熱門的觀光景點,
03:19
and there are lots of photos相片 around here,
64
184000
2000
這附近有很多照片,
03:21
and these photos相片 are all taken採取 at different不同 times.
65
186000
3000
這些照片是於不同時間拍的,
03:24
So this one was taken採取 around five.
66
189000
2000
這張是早上 5 點拍的,
03:26
So that's the FlickrFlickr的 photo照片,
67
191000
2000
那是 Flickr 的照片,
03:28
that's our imagery意象.
68
193000
2000
這是我們的照片。
03:30
So you really see how this kind of crowd-sourced眾包 imagery意象
69
195000
3000
這樣你可以知道,這種由網路社群提供的圖資
03:33
is integrating整合, in a very deep way, into the map地圖 itself本身.
70
198000
3000
是如何深層的與地圖本身整合在一起。
03:36
(Applause掌聲)
71
201000
2000
(掌聲)
03:38
Thank you.
72
203000
2000
謝謝。
03:40
(Applause掌聲)
73
205000
2000
(掌聲)
03:42
There are several一些 reasons原因 why this is interesting有趣
74
207000
2000
這之所以很有趣,有幾個原因
03:44
and one of them, of course課程, is time travel旅行.
75
209000
2000
其中之一,當然,是時光旅行,
03:46
And I'm not going to show顯示 you some of the wonderful精彩 historic歷史性 imagery意象 in here,
76
211000
2000
我就不示範這些精彩的歷史圖資了,
03:48
but there are some with horses馬匹 and carriages車廂 and so on as well.
77
213000
3000
但是在那些圖資裡面有馬車之類的東西。
03:51
But what's cool about this is that, not only is it augmenting增廣
78
216000
3000
這之所以很酷, 並不僅僅是因爲
03:54
this visual視覺 representation表示 of the world世界
79
219000
2000
它從使用者身上蒐集了取多東西,
03:56
with things that are coming未來 in from users用戶,
80
221000
3000
並以之充實了對大千世界的視覺呈現。
03:59
but it also is the foundation基礎 for augmented增強 reality現實,
81
224000
4000
但同時, 這也是增強實境的基礎,
04:03
and that's something that I'll be showing展示 you more of in just a moment時刻.
82
228000
3000
過一會兒,我將更詳細地向你們介紹這項功能,
04:06
Now I just made製作 a transition過渡 indoors在室內. That's also interesting有趣.
83
231000
4000
現在我,正在轉換進入室內,這也很有趣,
04:10
OK, notice注意 there's now a roof屋頂 above以上 us.
84
235000
2000
請注意,現在有屋頂在我們的頭上方了。
04:12
We're inside the Pike梭子魚 Place地點 Market市場.
85
237000
3000
我們現在是在派克市場裡面,
04:15
And this is something that we're able能夠 to do with a backpack背包 camera相機,
86
240000
2000
這些圖資是我們使用背負式攝影機所拍攝的。
04:17
so, we're now not only imaging成像 in the street
87
242000
4000
所以, 我們不光是在街上
04:21
with this camera相機 on tops上衣 of cars汽車,
88
246000
2000
使用架設在汽車頂上的攝影機拍攝圖資,
04:23
but we're also imaging成像 inside.
89
248000
4000
我們同時也在室內拍攝。
04:27
And from here, we're able能夠 to do the same相同 sorts排序 of registration註冊,
90
252000
5000
從這裡, 我們可以使用各種東西來成像,
04:32
not only of still images圖片, but also of video視頻.
91
257000
4000
不只是用靜態的圖片,也可以用影片。
04:36
So this is something that we're now going to try
92
261000
2000
我們現在就來試驗一下,
04:38
for the first time, live生活,
93
263000
2000
這是我們第一次做直播測試。
04:40
and this is really, truly, very frightening可怕的.
94
265000
3000
這真是,真的,非常可怕。
04:43
(Laughter笑聲)
95
268000
2000
(笑聲)
04:46
OK.
96
271000
2000
04:48
(Ringing鈴聲)
97
273000
2000
(電話鈴聲)
04:50
All right, guys, are you there?
98
275000
2000
好了,夥計們, 你們在嗎?
04:52
(Noise噪聲)
99
277000
2000
(噪音)
04:54
All right. I'm hitting it. I'm punching沖孔 play.
100
279000
2000
好,我上線了,正式開始。
04:56
I'm live生活. All right. There we go.
101
281000
2000
直播開始了,好的,開始。
04:58
So, these are our friends朋友 in Pike梭子魚 Place地點 Market市場, the lab實驗室.
102
283000
5000
這是我們現在正位於派克市場的朋友們,我們實驗室的成員。
05:03
(Applause掌聲)
103
288000
8000
(掌聲)
05:12
So they're broadcasting廣播 this live生活.
104
297000
2000
他們現在在現場直播。
05:14
OK, George喬治, can you pan back over to the corner market市場?
105
299000
4000
好吧,喬治,你能把鏡頭移到市場的角落嗎?
05:18
Because I want to show顯示 points of interest利益.
106
303000
4000
因爲我想示範一下資訊熱點功能。
05:22
No, no. The other way.
107
307000
3000
不,不,另外一個方向。
05:25
Yeah, yeah, back to the corner, back to the corner.
108
310000
2000
對了,對了,回到角落,回到角落
05:27
I don't want to see you guys yet然而.
109
312000
3000
我還不想看見你們呢。
05:31
OK, OK, back to the corner, back to the corner, back to the corner.
110
316000
6000
好吧,好吧,回到角落,回到角落,回到角落。
05:37
OK, never mind心神.
111
322000
2000
好吧, 算了。
05:40
What I wanted to show顯示 you was these points of interest利益
112
325000
2000
我本來想要示範給你們看的是這些資訊熱點
05:42
over here on top最佳 of the image圖片
113
327000
2000
會層疊在這個圖資上方。
05:44
because what that gives you a sense of is the way,
114
329000
2000
因爲這會讓你感覺,
05:46
if you're actually其實 on the spot,
115
331000
2000
彷彿身歷其境 ...
05:48
you can think about this --
116
333000
2000
你可以這樣想:
05:50
this is taking服用 a step in addition加成 to augmented增強 reality現實.
117
335000
3000
這是在增強實境的基礎上又邁進了一步,
05:53
What the hell地獄 are you guys -- oh, sorry.
118
338000
2000
你們這些傢伙在幹什麼啊?噢,對不起
05:55
(Laughter笑聲)
119
340000
3000
(笑聲)
05:58
We're doing two different不同 --
120
343000
3000
我們正在做兩件不同的事情,
06:01
OK, I'm hanging up now.
121
346000
3000
好吧,我要掛了。
06:04
We're doing two different不同 things here.
122
349000
2000
我們正在做兩件不一樣的事情,
06:06
One of them is to take that real真實 ...
123
351000
2000
他們中的一個正要去拿那個真的......
06:08
(Laughter笑聲)
124
353000
7000
(笑聲)
06:15
All right, let me just take a moment時刻 and thank the team球隊.
125
360000
3000
好吧, 讓我們停下來感謝我們的小組成員,
06:18
They've他們已經 doneDONE a fantastic奇妙 job工作 of pulling this together一起.
126
363000
2000
他們出色地完成了這個實驗。
06:20
(Applause掌聲)
127
365000
2000
(掌聲)
06:22
I'm going to abandon放棄 them now and walk步行 back outside.
128
367000
3000
我現在要拋棄他們了,接下來我往外走,
06:25
And while I walk步行 outside, I'll just mention提到 that
129
370000
3000
在我往外走的時候,我得提一下的是,
06:28
here we're using運用 this for telepresence網真,
130
373000
2000
剛剛,我們將這個工具作為遠端視訊會議,
06:30
but you can equally一樣 well use this
131
375000
2000
但是,你同時也可以在當地,
06:32
on the spot, for augmented增強 reality現實.
132
377000
2000
把這個當做增強實境的工具。
06:34
When you use it on the spot, it means手段 that
133
379000
2000
當你在景點現場使用的時候,
06:36
you're able能夠 to bring帶來 all of that metadata元數據
134
381000
2000
你就可以把所有世界上的原始數據
06:38
and information信息 about the world世界 to you.
135
383000
2000
和資訊都帶到你的所在地。
06:40
So here, we're taking服用 the extra額外 step of also broadcasting廣播 it.
136
385000
2000
而這邊,我們更進一步地把這些東西轉播出去。
06:42
That was being存在 broadcast廣播, by the way, on a 4G network網絡
137
387000
3000
順便說一下,這是在第四代行動通訊 (4G) 網絡上,
06:45
from the market市場.
138
390000
3000
從市場直接轉播的。
06:48
All right, and now there's one last TEDTED talk
139
393000
3000
好,現在你們看到的是微軟的一場 TED 演講,
06:51
that Microsoft微軟 has given特定 in the past過去 several一些 years年份.
140
396000
2000
這是微軟官方在過去幾年裡所給的最後一場 TED 演講。
06:53
And that's Curtis柯蒂斯 Wong, WorldWide全世界 Telescope望遠鏡.
141
398000
3000
那是 Curtis Wong,全球望遠鏡 (WorldWide Telescope)
06:56
So, we're going to head over to the dumpsters垃圾箱,
142
401000
2000
我們現在朝垃圾場走去,
06:58
where it's traditional傳統, after a long day at the market市場,
143
403000
3000
這也是在市場工作一整天結束時的傳統,
07:01
to go out for a break打破, but also stare up at the sky天空.
144
406000
4000
到外面去小歇片刻, 然後注視著天空,
07:05
This is the integration積分
145
410000
2000
這是將全球望遠鏡
07:07
of WorldWide全世界 Telescope望遠鏡 into our maps地圖.
146
412000
3000
整合到我們的地圖中。
07:10
(Applause掌聲)
147
415000
2000
(掌聲)
07:12
This is the current當前 -- thank you --
148
417000
3000
這是現在, 謝謝,
07:15
this is the current當前 time. If we scrub擦洗 the time,
149
420000
2000
這是現在,但是如果我們轉移時間,
07:17
then we can see how the sky天空 will look at different不同 times,
150
422000
3000
我們就可以看見天空在不同的時間是如何變化的
07:20
and we can get all of this very detailed詳細
151
425000
2000
我們可以得到非常詳細的
07:22
information信息 about different不同 times, different不同 dates日期:
152
427000
4000
不同時間,不同日期的資訊,
07:27
Let's move移動 the moon月亮 a little higher更高 in the sky天空,
153
432000
2000
讓我們把月亮在天空中移得高一點,
07:29
maybe change更改 the date日期.
154
434000
4000
也許更動日期可以做到。
07:33
I would like to kind of zoom放大 in on the moon月亮.
155
438000
3000
我想將月亮放大,
07:39
So, this is an astronomically天文數字 complete完成
156
444000
2000
所以這是將天空中完整的
07:41
representation表示 of the sky天空
157
446000
3000
天文資訊
07:44
integrated集成 right into the Earth地球.
158
449000
2000
整合呈現在地球中。
07:46
All right now, I've overrun氾濫 my time,
159
451000
2000
好,我的時間到了,
07:48
so I've got to stop.
160
453000
2000
我必須要停下了。
07:50
Thank you all very much.
161
455000
2000
非常感謝。
07:52
(Applause掌聲)
162
457000
12000
(掌聲)
Translated by Jenny Yang
Reviewed by Bill Hsiung

▲Back to top

ABOUT THE SPEAKER
Blaise Agüera y Arcas - Software architect
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces.

Why you should listen

Blaise Agüera y Arcas is principal scientist at Google, where he leads a team working on machine intelligence for mobile devices. His group works extensively with deep neural nets for machine perception and distributed learning, and it also investigates so-called "connectomics" research, assessing maps of connections within the brain.

Agüera y Arcas' background is as multidimensional as the visions he helps create. In the 1990s, he authored patents on both video compression and 3D visualization techniques, and in 2001, he made an influential computational discovery that cast doubt on Gutenberg's role as the father of movable type.

He also created Seadragon (acquired by Microsoft in 2006), the visualization technology that gives Photosynth its amazingly smooth digital rendering and zoom capabilities. Photosynth itself is a vastly powerful piece of software capable of taking a wide variety of images, analyzing them for similarities, and grafting them together into an interactive three-dimensional space. This seamless patchwork of images can be viewed via multiple angles and magnifications, allowing us to look around corners or “fly” in for a (much) closer look. Simply put, it could utterly transform the way we experience digital images.

He joined Microsoft when Seadragon was acquired by Live Labs in 2006. Shortly after the acquisition of Seadragon, Agüera y Arcas directed his team in a collaboration with Microsoft Research and the University of Washington, leading to the first public previews of Photosynth several months later. His TED Talk on Seadragon and Photosynth in 2007 is rated one of TED's "most jaw-dropping." He returned to TED in 2010 to demo Bing’s augmented reality maps.

Fun fact: According to the author, Agüera y Arcas is the inspiration for the character Elgin in the 2012 best-selling novel Where'd You Go, Bernadette?

More profile about the speaker
Blaise Agüera y Arcas | Speaker | TED.com