Abe Davis: New video technology that reveals an object's hidden properties

204,153 views ・ 2015-05-05

TED


请双击下面的英文字幕来播放视频。

翻译人员: Hong Li 校对人员: Li Li
00:13
Most of us think of motion as a very visual thing.
0
13373
3349
大部分人认为 动作是明显可见的。
00:17
If I walk across this stage or gesture with my hands while I speak,
1
17889
5088
比如我走过这个舞台, 或者边做手势边说话,
00:22
that motion is something that you can see.
2
22977
2261
这些动作都能被大家看到。
00:26
But there's a world of important motion that's too subtle for the human eye,
3
26255
5482
但还有很多重要的动作 肉眼很难察觉到,
00:31
and over the past few years,
4
31737
2041
在过去几年中,
00:33
we've started to find that cameras
5
33778
1997
我们致力于寻找某种摄像机
00:35
can often see this motion even when humans can't.
6
35775
3410
可以捕捉到人眼看不到的运动。
00:40
So let me show you what I mean.
7
40305
1551
请看大屏幕。
00:42
On the left here, you see video of a person's wrist,
8
42717
3622
左边是一个人的手腕,
00:46
and on the right, you see video of a sleeping infant,
9
46339
3147
右边是一个熟睡的婴儿,
00:49
but if I didn't tell you that these were videos,
10
49486
3146
但是如果我不告诉你们这是一段视频,
00:52
you might assume that you were looking at two regular images,
11
52632
3761
你们可能会认为 这只是两张普通的图片,
00:56
because in both cases,
12
56393
1672
因为乍一看,
这两段视频几乎是完全静止的。
00:58
these videos appear to be almost completely still.
13
58065
3047
01:02
But there's actually a lot of subtle motion going on here,
14
62175
3885
但实际上,画面中 有许多细微的运动变化,
01:06
and if you were to touch the wrist on the left,
15
66060
2392
如果你能碰到左边的那个手腕,
01:08
you would feel a pulse,
16
68452
1996
你会感受到脉搏的跳动,
01:10
and if you were to hold the infant on the right,
17
70448
2485
如果你抱起右边的婴儿,
01:12
you would feel the rise and fall of her chest
18
72933
2391
你能感受到她胸腔的起伏,
01:15
as she took each breath.
19
75324
1390
感受到她的每一次呼吸。
01:17
And these motions carry a lot of significance,
20
77762
3576
这些动作都很重要,
01:21
but they're usually too subtle for us to see,
21
81338
3343
但由于过于细微, 很难被我们察觉,
01:24
so instead, we have to observe them
22
84681
2276
要想感受到这些动作的存在
01:26
through direct contact, through touch.
23
86957
2900
只能通过直接接触。
01:30
But a few years ago,
24
90997
1265
然而几年前,
01:32
my colleagues at MIT developed what they call a motion microscope,
25
92262
4405
我在麻省理工学院的同事们 开发出了一种被称为“动作显微镜”的软件,
01:36
which is software that finds these subtle motions in video
26
96667
4384
能够发现视频中细微的运动,
01:41
and amplifies them so that they become large enough for us to see.
27
101051
3562
并将其放大到肉眼可见的级别。
01:45
And so, if we use their software on the left video,
28
105416
3483
如果我们运用这一软件分析左边的视频,
01:48
it lets us see the pulse in this wrist,
29
108899
3250
我们就能看到手腕上的脉搏跳动,
01:52
and if we were to count that pulse,
30
112149
1695
通过计算脉搏数量,
01:53
we could even figure out this person's heart rate.
31
113844
2355
就能得知这个人的心率。
01:57
And if we used the same software on the right video,
32
117095
3065
而用这一软件分析右边的视频,
02:00
it lets us see each breath that this infant takes,
33
120160
3227
我们就能看清婴儿的每一次呼吸,
02:03
and we can use this as a contact-free way to monitor her breathing.
34
123387
4137
不需要触碰就能监控她的呼吸。
02:08
And so this technology is really powerful because it takes these phenomena
35
128884
5348
这项技术非常强大, 因为它能帮助我们看到
02:14
that we normally have to experience through touch
36
134232
2367
原本要靠触觉才能感受到的东西,
02:16
and it lets us capture them visually and non-invasively.
37
136599
2957
并且这一过程是可见和无创的。
02:21
So a couple years ago, I started working with the folks that created that software,
38
141104
4411
因此在几年前,我开始 与这个软件的编写者们一起工作,
02:25
and we decided to pursue a crazy idea.
39
145515
3367
我们产生了一个疯狂的想法。
02:28
We thought, it's cool that we can use software
40
148882
2693
我们觉得,运用软件将细微的动作
02:31
to visualize tiny motions like this,
41
151575
3135
可视化的这个点子非常酷,
02:34
and you can almost think of it as a way to extend our sense of touch.
42
154710
4458
你甚至可以把它当做拓展 人类触觉感官的好方法。
02:39
But what if we could do the same thing with our ability to hear?
43
159168
4059
那如果我们能用相同的方法 来增强我们的听觉呢?
02:44
What if we could use video to capture the vibrations of sound,
44
164508
4665
如果我们能通过视频捕捉到声音的振动,
02:49
which are just another kind of motion,
45
169173
2827
声音的振动实际上也是一种运动,
02:52
and turn everything that we see into a microphone?
46
172000
3346
将“看到”的东西录入麦克风呢?
02:56
Now, this is a bit of a strange idea,
47
176236
1971
也许听起来有点不太好理解,
02:58
so let me try to put it in perspective for you.
48
178207
2586
我试着为大家解释一下。
03:01
Traditional microphones work by converting the motion
49
181523
3488
传统麦克风的工作原理
03:05
of an internal diaphragm into an electrical signal,
50
185011
3599
是将其内部薄膜的振动转换成电信号,
03:08
and that diaphragm is designed to move readily with sound
51
188610
4318
这个薄膜极易随声音振动,
03:12
so that its motion can be recorded and interpreted as audio.
52
192928
4807
这个振动可以被记录下来 并还原成声音。
03:17
But sound causes all objects to vibrate.
53
197735
3668
而声音事实上可以 引起任何物体的振动。
03:21
Those vibrations are just usually too subtle and too fast for us to see.
54
201403
5480
只不过这种振动对我们而言 通常很细微而且转瞬即逝。
03:26
So what if we record them with a high-speed camera
55
206883
3738
但如果我们用高速摄影机 将这种振动录下来,
03:30
and then use software to extract tiny motions
56
210621
3576
并通过软件从这些高速视频中
03:34
from our high-speed video,
57
214197
2090
提取出这些细小的振动,
03:36
and analyze those motions to figure out what sounds created them?
58
216287
4274
然后分析这些振动来 弄清声音的来源,会怎么样呢?
03:41
This would let us turn visible objects into visual microphones from a distance.
59
221859
5449
这样一来我们可以将远处的 可见物体转化为可视化麦克风。
03:49
And so we tried this out,
60
229080
2183
我们进行了各种尝试,
03:51
and here's one of our experiments,
61
231263
1927
以下是我们的试验之一,
03:53
where we took this potted plant that you see on the right
62
233190
2949
右边是一株盆栽植物,
03:56
and we filmed it with a high-speed camera
63
236139
2438
我们用高速摄影机拍下它,
03:58
while a nearby loudspeaker played this sound.
64
238577
3529
同时旁边的音箱在播放这个声音。
04:02
(Music: "Mary Had a Little Lamb")
65
242275
8190
(音乐:玛丽有一只小羊羔)
04:11
And so here's the video that we recorded,
66
251820
2824
这是我们录下的视频,
04:14
and we recorded it at thousands of frames per second,
67
254644
3924
用的是每秒数千帧的速度,
04:18
but even if you look very closely,
68
258568
2322
但即使你凑得非常近,
04:20
all you'll see are some leaves
69
260890
1951
也只能看到一些叶子
04:22
that are pretty much just sitting there doing nothing,
70
262841
3065
静静地呆在那儿,一动不动,
04:25
because our sound only moved those leaves by about a micrometer.
71
265906
4806
因为刚才的音乐 只能让叶子移动一微米,
04:31
That's one ten-thousandth of a centimeter,
72
271103
4276
也就是一厘米的万分之一,
04:35
which spans somewhere between a hundredth and a thousandth
73
275379
4156
只占这幅图像中一个像素的
04:39
of a pixel in this image.
74
279535
2299
百分之一到千分之一。
04:41
So you can squint all you want,
75
281881
2887
你大可以眯着眼使劲儿看,
04:44
but motion that small is pretty much perceptually invisible.
76
284768
3335
但如此细微的运动 从感官上来说是不可见的。
04:49
But it turns out that something can be perceptually invisible
77
289667
4157
但事实证明感官上不可见的东西
04:53
and still be numerically significant,
78
293824
2809
在数值上可能很惊人,
04:56
because with the right algorithms,
79
296633
2002
因为通过正确的算法,
04:58
we can take this silent, seemingly still video
80
298635
3687
我们就可以从这段无声的 看似静止的视频中
05:02
and we can recover this sound.
81
302322
1527
还原出这段声音。
05:04
(Music: "Mary Had a Little Lamb")
82
304690
7384
(音乐:玛丽有一只小羊羔)
05:12
(Applause)
83
312074
5828
(掌声)
05:22
So how is this possible?
84
322058
1939
这怎么可能呢?
05:23
How can we get so much information out of so little motion?
85
323997
4344
我们怎么能从如此细小的运动中 得到如此丰富的信息?
05:28
Well, let's say that those leaves move by just a single micrometer,
86
328341
5361
我们必须承认这些叶子 只移动了一微米,
05:33
and let's say that that shifts our image by just a thousandth of a pixel.
87
333702
4308
只改变了图像中一个像素的千分之一。
05:39
That may not seem like much,
88
339269
2572
看起来很微不足道,
05:41
but a single frame of video
89
341841
1996
但是视频中的每一帧
05:43
may have hundreds of thousands of pixels in it,
90
343837
3257
都包含数以万计的像素,
05:47
and so if we combine all of the tiny motions that we see
91
347094
3454
当我们将整幅画面中 所有细微的运动
05:50
from across that entire image,
92
350548
2298
组合在一起来看的时候,
05:52
then suddenly a thousandth of a pixel
93
352846
2623
无数个千分之一像素聚在一起
05:55
can start to add up to something pretty significant.
94
355469
2775
就能组合出有十分意义的信息。
05:58
On a personal note, we were pretty psyched when we figured this out.
95
358870
3635
老实说,当我们想通 这一点的时候真是乐疯了。
06:02
(Laughter)
96
362505
2320
(笑声)
06:04
But even with the right algorithm,
97
364825
3253
但是,即便运用正确的算法
06:08
we were still missing a pretty important piece of the puzzle.
98
368078
3617
我们还是会丢失掉很多重要的信息。
06:11
You see, there are a lot of factors that affect when and how well
99
371695
3604
这项技术能否成功
06:15
this technique will work.
100
375299
1997
取决于很多因素。
06:17
There's the object and how far away it is;
101
377296
3204
比如目标物体的距离;
06:20
there's the camera and the lens that you use;
102
380500
2394
摄影机和镜头的选用;
06:22
how much light is shining on the object and how loud your sound is.
103
382894
4091
光线是否充足, 声音是否够大等等。
06:27
And even with the right algorithm,
104
387945
3375
因此,即便我们的算法正确,
06:31
we had to be very careful with our early experiments,
105
391320
3390
在早期试验中 我们还是得万分谨慎,
06:34
because if we got any of these factors wrong,
106
394710
2392
因为一着不慎,满盘皆输,
06:37
there was no way to tell what the problem was.
107
397102
2368
得不到有用的信息, 也查不出原因。
06:39
We would just get noise back.
108
399470
2647
还原出来的只有噪音。
06:42
And so a lot of our early experiments looked like this.
109
402117
3320
初期的试验场景是这样的。
06:45
And so here I am,
110
405437
2206
左边的是我,
06:47
and on the bottom left, you can kind of see our high-speed camera,
111
407643
4040
左下角是我们的高速摄影机,
06:51
which is pointed at a bag of chips,
112
411683
2183
正对着一袋薯片,
06:53
and the whole thing is lit by these bright lamps.
113
413866
2949
薯片被一盏明亮的灯照着。
06:56
And like I said, we had to be very careful in these early experiments,
114
416815
4365
就像刚才我说的, 在初期试验中我们需要十分小心,
07:01
so this is how it went down.
115
421180
2508
得有多小心呢?请看。
07:03
(Video) Abe Davis: Three, two, one, go.
116
423688
3761
(视频:三、二、一,开始)
07:07
Mary had a little lamb! Little lamb! Little lamb!
117
427449
5387
(视频:玛丽有一只小羊羔! 小羊羔!小羊羔!)
07:12
(Laughter)
118
432836
4500
(笑声)
07:17
AD: So this experiment looks completely ridiculous.
119
437336
2814
这试验看起来真是弱爆了。
07:20
(Laughter)
120
440150
1788
(笑声)
07:21
I mean, I'm screaming at a bag of chips --
121
441938
2345
我可是对着一袋薯片在咆哮——
07:24
(Laughter) --
122
444283
1551
(笑声)
07:25
and we're blasting it with so much light,
123
445834
2117
而且我们用的灯功率太大,
07:27
we literally melted the first bag we tried this on. (Laughter)
124
447951
4479
差点把第一袋薯片点着了。 (笑声)
07:32
But ridiculous as this experiment looks,
125
452525
3274
虽然看起来很不靠谱,
07:35
it was actually really important,
126
455799
1788
但结果还是不错的,
07:37
because we were able to recover this sound.
127
457587
2926
因为我们最终还原出了这段声音。
07:40
(Audio) Mary had a little lamb! Little lamb! Little lamb!
128
460513
4712
(音频:玛丽有一只小羊羔! 小羊羔!小羊羔!)
07:45
(Applause)
129
465225
4088
(掌声)
07:49
AD: And this was really significant,
130
469313
1881
这绝对是一个里程碑,
07:51
because it was the first time we recovered intelligible human speech
131
471194
4119
因为这是我们第一次 从一段无声录像中
07:55
from silent video of an object.
132
475424
2341
还原出具有意义的人声。
07:57
And so it gave us this point of reference,
133
477765
2391
因此我们以此为出发点
08:00
and gradually we could start to modify the experiment,
134
480156
3871
不断修正我们的试验,
08:04
using different objects or moving the object further away,
135
484106
3805
更换试验对象,调整距离,
08:07
using less light or quieter sounds.
136
487911
2770
减小光线强度,降低声音等等。
08:11
And we analyzed all of these experiments
137
491887
2874
我们不断分析试验结果,
08:14
until we really understood the limits of our technique,
138
494761
3622
直到发现这一技术的局限性,
08:18
because once we understood those limits,
139
498383
1950
因为只有搞清楚局限在哪儿
08:20
we could figure out how to push them.
140
500333
2346
我们才能不断取得突破。
08:22
And that led to experiments like this one,
141
502679
3181
于是,就有了下面这个试验,
08:25
where again, I'm going to speak to a bag of chips,
142
505860
2739
这一次,我还是对着一袋薯片说话,
08:28
but this time we've moved our camera about 15 feet away,
143
508599
4830
但将摄影机后退到了15英尺 (4.572米)远的室外,
08:33
outside, behind a soundproof window,
144
513429
2833
隔着一层隔音玻璃,
08:36
and the whole thing is lit by only natural sunlight.
145
516262
2803
只借助自然光线。
08:40
And so here's the video that we captured.
146
520529
2155
这是我们拍下的视频。
08:44
And this is what things sounded like from inside, next to the bag of chips.
147
524450
4559
这是在室内, 在薯片旁说话的原声。
08:49
(Audio) Mary had a little lamb whose fleece was white as snow,
148
529009
5038
(音频:玛丽有一只小羊羔, 身上羊毛白又好,
08:54
and everywhere that Mary went, that lamb was sure to go.
149
534047
5619
无论玛丽走到哪, 小羊都会跟着跑。)
08:59
AD: And here's what we were able to recover from our silent video
150
539666
4017
这是通过我们从室外 隔音玻璃后采集的无声影像
09:03
captured outside behind that window.
151
543683
2345
还原出来的声音。
09:06
(Audio) Mary had a little lamb whose fleece was white as snow,
152
546028
4435
(音频:玛丽有一只小羊羔, 身上羊毛白又好,
09:10
and everywhere that Mary went, that lamb was sure to go.
153
550463
5457
无论玛丽走到哪, 小羊都会跟着跑。)
09:15
(Applause)
154
555920
6501
(掌声)
09:22
AD: And there are other ways that we can push these limits as well.
155
562421
3542
我们还调整了其它参数。
09:25
So here's a quieter experiment
156
565963
1798
比如说降低音量,
09:27
where we filmed some earphones plugged into a laptop computer,
157
567761
4110
这有一副耳机,插在笔记本电脑上,
09:31
and in this case, our goal was to recover the music that was playing on that laptop
158
571871
4110
在这个实验中,我们想仅通过拍摄下 这对塑料耳机的
09:35
from just silent video
159
575981
2299
无声视频来还原
09:38
of these two little plastic earphones,
160
578280
2507
笔记本里播放的音乐,
09:40
and we were able to do this so well
161
580787
2183
结果很理想,
09:42
that I could even Shazam our results.
162
582970
2461
我甚至能用Shazam 来识别出这段音乐。
09:45
(Laughter)
163
585431
2411
(笑声)
09:49
(Music: "Under Pressure" by Queen)
164
589191
10034
(音乐:“皇后乐队”的《重压之下》)
10:01
(Applause)
165
601615
4969
(掌声)
10:06
And we can also push things by changing the hardware that we use.
166
606584
4551
我们还尝试了更换试验设备 来完善我们的成果。
10:11
Because the experiments I've shown you so far
167
611135
2461
因为前面我给大家展示的试验
10:13
were done with a camera, a high-speed camera,
168
613596
2322
都是通过高速摄影机完成的,
10:15
that can record video about a 100 times faster
169
615918
2879
它的拍摄速度比大多数手机摄像头
10:18
than most cell phones,
170
618797
1927
快100倍,
10:20
but we've also found a way to use this technique
171
620724
2809
但是我们也找到了用普通摄影机
10:23
with more regular cameras,
172
623533
2230
来完成试验的方法,
10:25
and we do that by taking advantage of what's called a rolling shutter.
173
625763
4069
我们利用了叫做“滚动快门”的技术。
10:29
You see, most cameras record images one row at a time,
174
629832
4798
大部分摄像头是逐行拍摄影像的,
10:34
and so if an object moves during the recording of a single image,
175
634630
5702
因此如果在拍摄单张照片时 物体发生了移动,
10:40
there's a slight time delay between each row,
176
640344
2717
每一行影像间就会出现少许延迟,
10:43
and this causes slight artifacts
177
643061
3157
这种延迟使得视频的每一帧
10:46
that get coded into each frame of a video.
178
646218
3483
都会产生轻微的变形。
10:49
And so what we found is that by analyzing these artifacts,
179
649701
3806
通过分析这种变形,
10:53
we can actually recover sound using a modified version of our algorithm.
180
653507
4615
运用调整过的算法 我们还是可以还原声音。
10:58
So here's an experiment we did
181
658122
1912
在接下来这个试验里,
11:00
where we filmed a bag of candy
182
660034
1695
我们拍摄的是一袋糖果,
11:01
while a nearby loudspeaker played
183
661729
1741
旁边的喇叭里播放的
11:03
the same "Mary Had a Little Lamb" music from before,
184
663470
2972
还是之前那首“玛丽有一只小羊羔”,
11:06
but this time, we used just a regular store-bought camera,
185
666442
4203
但这一次我们使用的是 能在店里买到的普通摄影机,
11:10
and so in a second, I'll play for you the sound that we recovered,
186
670645
3174
下面请听我们还原出来的声音,
11:13
and it's going to sound distorted this time,
187
673819
2050
这次的声音有些失真,
11:15
but listen and see if you can still recognize the music.
188
675869
2836
但仔细听一下, 看你能否分辨出来这段音乐。
11:19
(Audio: "Mary Had a Little Lamb")
189
679723
6223
(音频:玛丽有一只小羊羔)
11:37
And so, again, that sounds distorted,
190
697527
3465
就是这样,听起来有点失真,
11:40
but what's really amazing here is that we were able to do this
191
700992
4386
但别忘了 我们这次用的是普通摄影机,
11:45
with something that you could literally run out
192
705378
2626
你随便到一家百思买 这样的电器商店
11:48
and pick up at a Best Buy.
193
708004
1444
就可以买到。
11:51
So at this point,
194
711122
1363
那么目前为止,
11:52
a lot of people see this work,
195
712485
1974
相信许多人看到这儿
11:54
and they immediately think about surveillance.
196
714459
3413
立刻想到了监听。
11:57
And to be fair,
197
717872
2415
说实话,
12:00
it's not hard to imagine how you might use this technology to spy on someone.
198
720287
4133
用这个技术去监听 还真不是什么难事。
12:04
But keep in mind that there's already a lot of very mature technology
199
724420
3947
但请大家注意, 早就有很多成熟的技术
12:08
out there for surveillance.
200
728367
1579
被用于监听了。
12:09
In fact, people have been using lasers
201
729946
2090
实际上,将激光投射在物体上
12:12
to eavesdrop on objects from a distance for decades.
202
732036
2799
进行远距离监听的技术 已经出现几十年了。
12:15
But what's really new here,
203
735978
2025
但我们这项技术的创新之处,
12:18
what's really different,
204
738003
1440
与众不同之处
12:19
is that now we have a way to picture the vibrations of an object,
205
739443
4295
在于我们掌握了一种 描绘物体振动的方法,
12:23
which gives us a new lens through which to look at the world,
206
743738
3413
使我们能通过一种全新的镜头 去看这个世界。
12:27
and we can use that lens
207
747151
1510
通过这个镜头,
12:28
to learn not just about forces like sound that cause an object to vibrate,
208
748661
4899
不仅能看清使物体产生振动的外力, 比如声音,
12:33
but also about the object itself.
209
753560
2288
还能了解物体本身的性质。
12:36
And so I want to take a step back
210
756975
1693
因此我想换个角度
12:38
and think about how that might change the ways that we use video,
211
758668
4249
思考这将如何改变 我们使用视频的方式,
12:42
because we usually use video to look at things,
212
762917
3553
我们通常用视频来“看”东西,
12:46
and I've just shown you how we can use it
213
766470
2322
而我刚刚给大家展示的是如何用视频
12:48
to listen to things.
214
768792
1857
来“听”东西。
12:50
But there's another important way that we learn about the world:
215
770649
3971
但是还有一种认识世界的重要方式,
12:54
that's by interacting with it.
216
774620
2275
就是与世界互动。
12:56
We push and pull and poke and prod things.
217
776895
3111
我们可以移动或触碰某个物体。
13:00
We shake things and see what happens.
218
780006
3181
或者摇晃它,看它会发生什么变化。
13:03
And that's something that video still won't let us do,
219
783187
4273
但这一变化(可能太过微小) 视频没法捕捉,
13:07
at least not traditionally.
220
787460
2136
至少用传统的方式实现不了。
13:09
So I want to show you some new work,
221
789596
1950
因此我想向大家展示一项新的成果,
13:11
and this is based on an idea I had just a few months ago,
222
791546
2667
这项成果基于我几个月前的一个想法,
13:14
so this is actually the first time I've shown it to a public audience.
223
794213
3301
今天其实是我第一次将它公之于众。
13:17
And the basic idea is that we're going to use the vibrations in a video
224
797514
5363
简而言之就是, 我们会利用视频里的振动
13:22
to capture objects in a way that will let us interact with them
225
802877
4481
来与物体进行互动,
13:27
and see how they react to us.
226
807358
1974
然后看物体如何反应。
13:31
So here's an object,
227
811120
1764
这是我们的试验对象,
13:32
and in this case, it's a wire figure in the shape of a human,
228
812884
3832
一个用铁丝做成的小人,
13:36
and we're going to film that object with just a regular camera.
229
816716
3088
我们使用的是一台普通的摄影机。
13:39
So there's nothing special about this camera.
230
819804
2124
没有任何特别之处。
13:41
In fact, I've actually done this with my cell phone before.
231
821928
2961
实际上,我用手机也能做到。
13:44
But we do want to see the object vibrate,
232
824889
2252
但如果我们想让这个小人振动,
13:47
so to make that happen,
233
827141
1133
要怎么做呢,
13:48
we're just going to bang a little bit on the surface where it's resting
234
828274
3346
我们仅仅在放置小人的 台子上敲了几下,
13:51
while we record this video.
235
831620
2138
并把过程拍了下来。
13:59
So that's it: just five seconds of regular video,
236
839398
3671
就这样,我们得到了一段 五秒钟的普通视频,
14:03
while we bang on this surface,
237
843069
2136
敲了几下台子,
14:05
and we're going to use the vibrations in that video
238
845205
3513
我们将利用视频里的振动
14:08
to learn about the structural and material properties of our object,
239
848718
4544
来研究这个小人的 结构特征和材料特征,
14:13
and we're going to use that information to create something new and interactive.
240
853262
4834
并利用这些信息 创造出一种新的具有互动性的东西。
14:24
And so here's what we've created.
241
864866
2653
这就是我们的成果
14:27
And it looks like a regular image,
242
867519
2229
看起来像一张普通的图片,
14:29
but this isn't an image, and it's not a video,
243
869748
3111
但这不是图片, 也不是视频,
14:32
because now I can take my mouse
244
872859
2368
因为我可以移动鼠标
14:35
and I can start interacting with the object.
245
875227
2859
与这个小人进行互动。
14:44
And so what you see here
246
884936
2357
现在大家看到的
14:47
is a simulation of how this object
247
887389
2226
是模拟小人在受到外力时
14:49
would respond to new forces that we've never seen before,
248
889615
4458
会如何反应, 即使这种外力是初次施加的,
14:54
and we created it from just five seconds of regular video.
249
894073
3633
而这都来源于那 短短五秒钟的普通视频。
14:59
(Applause)
250
899249
4715
(掌声)
15:09
And so this is a really powerful way to look at the world,
251
909421
3227
这的确是一种审视世界的有效方法,
15:12
because it lets us predict how objects will respond
252
912648
2972
让我们可以预测物体在新的条件下
15:15
to new situations,
253
915620
1823
会作何反应,
15:17
and you could imagine, for instance, looking at an old bridge
254
917443
3473
想象一下,前面有一座很旧的桥,
15:20
and wondering what would happen, how would that bridge hold up
255
920916
3527
我们不知道它是否足够结实,
15:24
if I were to drive my car across it.
256
924443
2833
我们能不能把车开过去。
15:27
And that's a question that you probably want to answer
257
927276
2774
而这种问题 最好在你开车上桥之前
15:30
before you start driving across that bridge.
258
930050
2560
就搞清楚答案。
15:33
And of course, there are going to be limitations to this technique,
259
933988
3272
当然,这项技术有它的局限,
15:37
just like there were with the visual microphone,
260
937260
2462
就像之前的视觉麦克风试验一样,
15:39
but we found that it works in a lot of situations
261
939722
3181
但我们也发现 它能在许多场景下发挥作用,
15:42
that you might not expect,
262
942903
1875
有时甚至出乎你的意料,
15:44
especially if you give it longer videos.
263
944778
2768
特别是当视频时间足够长的时候。
15:47
So for example, here's a video that I captured
264
947546
2508
举个例子,这段视频
15:50
of a bush outside of my apartment,
265
950054
2299
拍的是我公寓外的灌木丛,
15:52
and I didn't do anything to this bush,
266
952353
3088
我没有动过它,
15:55
but by capturing a minute-long video,
267
955441
2705
只是拍了一段1分钟长的视频,
15:58
a gentle breeze caused enough vibrations
268
958146
3378
微风不断吹动灌木,
16:01
that we could learn enough about this bush to create this simulation.
269
961524
3587
让我能够收集到足够的信息 来完成这段模拟。
16:07
(Applause)
270
967270
6142
(掌声)
16:13
And so you could imagine giving this to a film director,
271
973412
2972
想象一下, 如果电影导演掌握了这项技术,
16:16
and letting him control, say,
272
976384
1719
他就可以在后期制作时
16:18
the strength and direction of wind in a shot after it's been recorded.
273
978103
4922
随心所欲地控制风的大小和方向。
16:24
Or, in this case, we pointed our camera at a hanging curtain,
274
984810
4535
来看另一个例子, 我们拍摄了一副挂起来的窗帘,
16:29
and you can't even see any motion in this video,
275
989345
4129
在这段视频里 你甚至看不出来窗帘在动,
16:33
but by recording a two-minute-long video,
276
993474
2925
但是利用2分钟长的一段视频,
16:36
natural air currents in this room
277
996399
2438
仅仅靠房间里的自然空气流动
16:38
created enough subtle, imperceptible motions and vibrations
278
998837
4412
引发的无法察觉的动作和振动,
16:43
that we could learn enough to create this simulation.
279
1003249
2565
就能使我们提取出足够多的 信息来完成这段模拟。
16:48
And ironically,
280
1008243
2366
神奇的是,
16:50
we're kind of used to having this kind of interactivity
281
1010609
3088
以往我们都是针对虚拟物体,
16:53
when it comes to virtual objects,
282
1013697
2647
针对游戏和3D模型
16:56
when it comes to video games and 3D models,
283
1016344
3297
来实现这种互动,
16:59
but to be able to capture this information from real objects in the real world
284
1019641
4404
而这项技术仅仅是利用 普通的视频
17:04
using just simple, regular video,
285
1024045
2817
对现实世界中的 真实物体进行采样,
17:06
is something new that has a lot of potential.
286
1026862
2183
它极富新意, 具有广阔的应用前景。
17:10
So here are the amazing people who worked with me on these projects.
287
1030410
4904
这些是跟我共同研究 这项技术的优秀的同事。
17:16
(Applause)
288
1036057
5596
(掌声)
17:24
And what I've shown you today is only the beginning.
289
1044819
3057
今天向大家展示的 只是一个技术雏形。
17:27
We've just started to scratch the surface
290
1047876
2113
关于如何使用这种新型图像,
17:29
of what you can do with this kind of imaging,
291
1049989
2972
我们才刚刚入门,
17:32
because it gives us a new way
292
1052961
2286
它为我们提供了一种
17:35
to capture our surroundings with common, accessible technology.
293
1055342
4724
运用已有的普通技术 来记录周围事物的新方法。
17:40
And so looking to the future,
294
1060066
1929
展望一下未来,
17:41
it's going to be really exciting to explore
295
1061995
2037
我们迫不及待地想要看到如何
17:44
what this can tell us about the world.
296
1064032
1856
利用这项技术去更好地了解世界。
17:46
Thank you.
297
1066381
1204
谢谢大家。
17:47
(Applause)
298
1067610
6107
(掌声)
关于本网站

这个网站将向你介绍对学习英语有用的YouTube视频。你将看到来自世界各地的一流教师教授的英语课程。双击每个视频页面上显示的英文字幕,即可从那里播放视频。字幕会随着视频的播放而同步滚动。如果你有任何意见或要求,请使用此联系表与我们联系。

https://forms.gle/WvT1wiN1qDtmnspy7