Lian Pin Koh: A drone's-eye view of conservation

86,933 views ・ 2013-11-18

TED


Please double-click on the English subtitles below to play the video.

00:13
When we think of Nepal,
0
13360
1932
00:15
we tend to think of the snow-capped mountains
1
15292
2455
00:17
of the Himalayas,
2
17747
1272
00:19
the crystal-clear still waters of its alpine lakes,
3
19019
3449
00:22
or the huge expanse of its grasslands.
4
22468
3046
00:25
What some of us may not realize
5
25514
2207
00:27
is that in the Himalayan foothills,
6
27721
2324
00:30
where the climate is much warmer
7
30045
2174
00:32
and the landscape much greener,
8
32219
2088
00:34
there lives a great diversity of wildlife,
9
34307
2426
00:36
including the one-horned rhinoceros,
10
36733
2736
00:39
the Asian elephant
11
39469
1674
00:41
and the Bengal tiger.
12
41143
2075
00:43
But unfortunately, these animals
13
43218
1852
00:45
are under constant threat from poachers
14
45070
2663
00:47
who hunt and kill them for their body parts.
15
47733
3312
00:51
To stop the killing of these animals,
16
51045
2209
00:53
battalions of soldiers and rangers
17
53254
2598
00:55
are sent to protect Nepal's national parks,
18
55852
3249
00:59
but that is not an easy task,
19
59101
1625
01:00
because these soldiers have to patrol
20
60726
2671
01:03
thousands of hectares of forests on foot
21
63397
2991
01:06
or elephant backs.
22
66388
1641
01:08
It is also risky for these soldiers
23
68029
2485
01:10
when they get into gunfights with poachers,
24
70514
2381
01:12
and therefore Nepal is always looking
25
72895
2016
01:14
for new ways to help with protecting the forests
26
74911
3296
01:18
and wildlife.
27
78207
1977
01:20
Well recently, Nepal acquired a new tool
28
80184
2509
01:22
in the fight against wildlife crime,
29
82693
2713
01:25
and these are drones,
30
85406
1706
01:27
or more specifically, conservation drones.
31
87112
3274
01:30
For about a year now, my colleagues and I
32
90386
2514
01:32
have been building drones for Nepal
33
92900
2260
01:35
and training the park protection personnel
34
95160
2498
01:37
on the use of these drones.
35
97658
1978
01:39
Not only does a drone give you
36
99636
1632
01:41
a bird's-eye view of the landscape,
37
101268
2474
01:43
but it also allows you to capture detailed,
38
103742
3035
01:46
high-resolution images of objects on the ground.
39
106777
3982
01:50
This, for example, is a pair of rhinoceros
40
110759
3509
01:54
taking a cooling bath on a hot summer day
41
114268
2937
01:57
in the lowlands of Nepal.
42
117205
1963
01:59
Now we believe that drones have
43
119168
2231
02:01
tremendous potential,
44
121399
1808
02:03
not only for combating wildlife crime,
45
123207
2778
02:05
but also for monitoring the health
46
125985
1963
02:07
of these wildlife populations.
47
127948
2539
02:10
So what is a drone?
48
130487
1850
02:12
Well, the kind of drone I'm talking about
49
132337
2509
02:14
is simply a model aircraft
50
134846
2101
02:16
fitted with an autopilot system,
51
136947
2445
02:19
and this autopilot unit contains a tiny computer,
52
139392
4269
02:23
a GPS, a compass, a barometric altimeter
53
143661
4054
02:27
and a few other sensors.
54
147715
2259
02:29
Now a drone like this
55
149974
1419
02:31
is meant to carry a useful payload,
56
151393
2206
02:33
such as a video camera
57
153599
1783
02:35
or a photographic camera.
58
155382
1988
02:37
It also requires a software that allows the user
59
157370
3349
02:40
to program a mission,
60
160719
1701
02:42
to tell the drone where to go.
61
162420
2406
02:44
Now people I talk to are often surprised
62
164826
2077
02:46
when they hear that these are the only
63
166903
2331
02:49
four components that make a conservation drone,
64
169234
3107
02:52
but they are even more surprised
65
172341
1504
02:53
when I tell them how affordable these components are.
66
173845
3500
02:57
The facts is, a conservation drone
67
177345
2286
02:59
doesn't cost very much more than
68
179631
2259
03:01
a good laptop computer
69
181890
1977
03:03
or a decent pair of binoculars.
70
183867
3259
03:07
So now that you've built your own conservation drone,
71
187126
2972
03:10
you probably want to go fly it,
72
190098
2162
03:12
but how does one fly a drone?
73
192260
1933
03:14
Well, actually, you don't,
74
194193
1592
03:15
because the drone flies itself.
75
195785
2490
03:18
All you have to do is to program a mission
76
198275
3130
03:21
to tell the drone where to fly.
77
201405
2260
03:23
But you simply do that by clicking on
78
203665
2319
03:25
a few way points on the Google Maps interface
79
205984
3249
03:29
using the open-source software.
80
209233
2250
03:31
Those missions could be as simple
81
211483
1947
03:33
as just a few way points,
82
213430
2026
03:35
or they could be slightly longer and more complicated,
83
215456
3377
03:38
to fly along a river system.
84
218833
2421
03:41
Sometimes, we fly the drone in a lawnmower-type pattern
85
221254
3849
03:45
and take pictures of that area,
86
225103
2120
03:47
and those pictures can be processed
87
227223
1971
03:49
to produce a map of that forest.
88
229194
2739
03:51
Other researchers might want to fly the drone
89
231933
2603
03:54
along the boundaries of a forest
90
234536
2142
03:56
to watch out for poachers or people
91
236678
2171
03:58
who might be trying to enter the forest illegally.
92
238849
2918
04:01
Now whatever your mission is,
93
241767
1880
04:03
once you've programmed it,
94
243647
1473
04:05
you simply upload it to the autopilot system,
95
245120
2983
04:08
bring your drone to the field,
96
248103
1640
04:09
and launch it simply by tossing it in the air.
97
249743
3215
04:12
And often we'll go about this mission
98
252958
2342
04:15
taking pictures or videos along the way,
99
255300
3060
04:18
and usually at that point,
100
258360
1934
04:20
we will go grab ourselves a cup of coffee,
101
260294
2217
04:22
sit back, and relax for the next few minutes,
102
262511
2930
04:25
although some of us sit back and panic for the next few minutes
103
265441
3511
04:28
worrying that the drone will not return.
104
268952
2218
04:31
Usually it does, and when it does,
105
271170
2273
04:33
it even lands automatically.
106
273443
3406
04:36
So what can we do with a conservation drone?
107
276849
2907
04:39
Well, when we built our first prototype drone,
108
279756
3393
04:43
our main objective was to fly it over
109
283149
2518
04:45
a remote rainforest in North Sumatra, Indonesia,
110
285667
3889
04:49
to look for the nest of a species of great ape
111
289556
3049
04:52
known as the orangutan.
112
292605
2156
04:54
The reason we wanted to do that was because
113
294761
2656
04:57
we needed to know how many individuals
114
297417
2029
04:59
of this species are still left in that forest.
115
299446
3387
05:02
Now the traditional method of surveying
116
302833
2186
05:05
for orangutans is to walk the forest on foot
117
305019
3602
05:08
carrying heavy equipment
118
308621
1887
05:10
and to use a pair of binoculars to look up in the treetops
119
310508
3650
05:14
where you might find an orangutan or its nest.
120
314158
3418
05:17
Now as you can imagine,
121
317576
1726
05:19
that is a very time-consuming, labor-intensive,
122
319302
2970
05:22
and costly process,
123
322272
1718
05:23
so we were hoping that drones
124
323990
1796
05:25
could significantly reduce the cost of surveying
125
325786
3325
05:29
for orangutan populations in Indonesia
126
329111
2567
05:31
and elsewhere in Southeast Asia.
127
331678
2467
05:34
So we were very excited when we captured
128
334145
2355
05:36
our first pair of orangutan nests on camera.
129
336500
3170
05:39
And this is it; this is the first ever picture
130
339670
3164
05:42
of orangutan nests taken with a drone.
131
342834
3040
05:45
Since then we have taken pictures
132
345874
2024
05:47
of dozens of these nests
133
347898
1618
05:49
from around various parts of Southeast Asia,
134
349516
2769
05:52
and we're now working with computer scientists
135
352285
2243
05:54
to develop algorithms that can automatically count
136
354528
3919
05:58
the number of nests from the thousands
137
358447
2017
06:00
of photos we've collected so far.
138
360464
3119
06:03
But nests are not the only objects
139
363583
1958
06:05
these drones can detect.
140
365541
1790
06:07
This is a wild orangutan
141
367331
2309
06:09
happily feeding on top of a palm tree,
142
369640
2521
06:12
seemingly oblivious to our drone that was flying overhead,
143
372161
3552
06:15
not once but several times.
144
375713
2384
06:18
We've also taken pictures of other animals
145
378097
3018
06:21
including forest buffalos in Gabon,
146
381115
3121
06:24
elephants, and even turtle nests.
147
384236
3215
06:27
But besides taking pictures of just the animals themselves,
148
387451
3540
06:30
we also take pictures of the habitats these animals live in,
149
390991
4001
06:34
because we want to keep track
150
394992
1614
06:36
of the health of these habitats.
151
396606
2954
06:39
Sometimes, we zoom out a little
152
399560
2219
06:41
and look at other things that might be happening
153
401779
2253
06:44
in the landscape.
154
404032
1464
06:45
This is an oil palm plantation in Sumatra.
155
405496
3300
06:48
Now oil palm is a major driver of deforestation
156
408796
3242
06:52
in that part of the world,
157
412038
1522
06:53
so we wanted to use this new drone technology
158
413560
3057
06:56
to keep track of the spread of these plantations
159
416617
3115
06:59
in Southeast Asia.
160
419732
2010
07:01
But drones could also be used to keep track of
161
421742
2363
07:04
illegal logging activities.
162
424105
2484
07:06
This is a recently logged forest,
163
426589
2441
07:09
again in Sumatra.
164
429030
1355
07:10
You could even still see the processed
165
430385
2159
07:12
wooden planks left on the ground.
166
432544
3628
07:16
But perhaps the most exciting part
167
436172
2289
07:18
about taking pictures from the air is
168
438461
2566
07:21
we could later stitch these pictures together
169
441027
2426
07:23
using special software to create a map
170
443453
2863
07:26
of the entire landscape, and this map
171
446316
2767
07:29
gives us crucial information
172
449083
2015
07:31
for monitoring land use change,
173
451098
2268
07:33
to let us know where and when plantations might be expanding,
174
453366
3747
07:37
where forests might be contracting,
175
457113
2277
07:39
or where fires might be breaking out.
176
459390
3382
07:42
Aerial images could also be processed
177
462772
2232
07:45
to produce three-dimensional
178
465004
2309
07:47
computer models of forests.
179
467313
1997
07:49
Now these models are not just visually appealing,
180
469310
2953
07:52
but they are also geometrically accurate,
181
472263
2501
07:54
which means researchers can now measure
182
474764
2777
07:57
the distance between trees,
183
477541
2125
07:59
calculate surface area, the volume of vegetation,
184
479666
3295
08:02
and so on, all of which are important information
185
482961
3199
08:06
for monitoring the health of these forests.
186
486160
3313
08:09
Recently, we've also begun experimenting
187
489473
2453
08:11
with thermal imaging cameras.
188
491926
2064
08:13
Now these cameras can detect
189
493990
1889
08:15
heat-emitting objects from the ground,
190
495879
1974
08:17
and therefore they are very useful for detecting poachers or their campfires at night.
191
497864
7372
08:25
So I've told you quite a lot about
192
505236
1884
08:27
what conservation drones are,
193
507120
2216
08:29
how you might operate one of these drones,
194
509336
2317
08:31
and what a drone could do for you.
195
511653
2009
08:33
I will now tell you where conservation drones
196
513662
2236
08:35
are being used around the world.
197
515898
2455
08:38
We built our first prototype drones in Switzerland.
198
518353
3053
08:41
We brought a few of these to Indonesia
199
521406
2141
08:43
for the first few test flights.
200
523547
2143
08:45
Since then, we've been building drones
201
525690
1815
08:47
for our collaborators from around the world,
202
527505
2682
08:50
and these include fellow biologists
203
530187
2180
08:52
and partners from major conservation organizations.
204
532367
3928
08:56
Perhaps the best and most rewarding part
205
536295
2290
08:58
about working with these collaborators
206
538585
2126
09:00
is the feedback they give us
207
540711
1480
09:02
on how to improve our drones.
208
542191
2643
09:04
Building drones for us is
209
544834
2131
09:06
a constant work in progress.
210
546965
2164
09:09
We are constantly trying to improve them in terms of
211
549129
3077
09:12
their range, their ruggedness,
212
552206
2614
09:14
and the amount of payload they can carry.
213
554820
2678
09:17
We also work with collaborators
214
557498
2042
09:19
to discover new ways of using these drones.
215
559540
3287
09:22
For example, camera traps are a common tool
216
562827
3280
09:26
used by biologists to take pictures of shy animals
217
566107
3895
09:30
hiding in the forests,
218
570002
1561
09:31
but these are motion-activated cameras,
219
571563
2334
09:33
so they snap a picture every time an animal
220
573897
2641
09:36
crosses their path.
221
576538
1672
09:38
But the problem with camera traps
222
578210
1552
09:39
is that the researcher has to go back to the forest
223
579762
3743
09:43
every so often to retrieve those images,
224
583505
3453
09:46
and that takes a lot of time,
225
586958
1652
09:48
especially if there are dozens
226
588610
1834
09:50
or hundreds of these cameras placed in the forest.
227
590444
3128
09:53
Now a drone could be designed to perform the task
228
593572
2811
09:56
much more efficiently.
229
596383
1724
09:58
This drone, carrying a special sensor,
230
598107
2670
10:00
could be flown over the forest
231
600777
2341
10:03
and remotely download these images
232
603118
2747
10:05
from wi-fi–enabled cameras.
233
605865
4137
10:10
Radio collars are another tool
234
610002
2137
10:12
that's commonly used by biologists.
235
612139
2248
10:14
Now these collars are put onto animals.
236
614387
2667
10:17
They transmit a radio signal which allows
237
617054
2801
10:19
the researcher to track the movements of these animals across the landscape.
238
619855
5147
10:25
But the traditional way of tracking animals
239
625002
2657
10:27
is pretty ridiculous,
240
627659
2222
10:29
because it requires the researcher to be walking
241
629881
2944
10:32
on the ground carrying a huge and cumbersome radio antenna,
242
632825
4114
10:36
not unlike those old TV antennae we used to have
243
636939
2873
10:39
on our rooftops. Some of us still do.
244
639812
2968
10:42
A drone could be used to do the same job
245
642780
2265
10:45
much more efficiently.
246
645045
1659
10:46
Why not equip a drone
247
646704
1706
10:48
with a scanning radio receiver,
248
648410
2003
10:50
fly that over the forest canopy
249
650413
1994
10:52
in a certain pattern
250
652407
1538
10:53
which would allow the user or the operator
251
653945
2792
10:56
to triangulate the location
252
656737
2582
10:59
of these radio-collared animals remotely
253
659319
2987
11:02
without having to step foot in the forest.
254
662306
2973
11:05
A third and perhaps most exciting way
255
665279
2503
11:07
of using these drones
256
667782
1530
11:09
is to fly them to a really remote,
257
669312
2950
11:12
never-explored-before rainforest
258
672262
2276
11:14
somewhere hidden in the tropics,
259
674538
1824
11:16
and parachute down a tiny spy microphone
260
676362
3933
11:20
that would allow us to eavesdrop on the calls
261
680295
2446
11:22
of mammals, birds, amphibians,
262
682741
3322
11:26
the Yeti, the Sasquatch, Bigfoot, whatever.
263
686063
4277
11:30
That would give us biologists
264
690340
1739
11:32
a pretty good idea of what animals
265
692079
1886
11:33
might be living in those forests.
266
693965
2550
11:36
And finally, I would like to show you
267
696515
2049
11:38
the latest version of our conservation drone.
268
698564
3101
11:41
The MAJA drone has a wingspan
269
701665
2139
11:43
of about two meters.
270
703804
1674
11:45
It weighs only about two kilograms,
271
705478
1950
11:47
but it can carry half its weight.
272
707428
2461
11:49
It is a fully autonomous system.
273
709889
2595
11:52
During its mission, it can even transmit
274
712484
2387
11:54
a live video feed back to a ground station laptop,
275
714871
3963
11:58
which allows the user
276
718834
1543
12:00
to see what the drone is seeing in real time.
277
720377
2930
12:03
It carries a variety of sensors,
278
723307
2422
12:05
and the photo quality of some of these sensors
279
725729
2338
12:08
can be as high as one to two centimeters per pixel.
280
728067
4210
12:12
This drone can stay in the air for 40 to 60 minutes,
281
732277
3681
12:15
which gives it a range of up to 50 kilometers.
282
735958
3124
12:19
That is quite sufficient for most
283
739082
1915
12:20
of our conservation applications.
284
740997
2999
12:23
Now, conservation drones began as
285
743996
2070
12:26
a crazy idea from two biologists
286
746066
2191
12:28
who are just deeply passionate about this technology.
287
748257
3285
12:31
And we believe, strongly believe,
288
751542
2150
12:33
that drones can and will be a game changer
289
753692
3347
12:37
for conservation research and applications.
290
757039
3034
12:40
We've had our fair share of skeptics and critics
291
760073
3175
12:43
who thought that we were just fooling around with toy planes.
292
763248
3521
12:46
And in a way, they are right.
293
766769
1426
12:48
I mean, let's be honest,
294
768195
1629
12:49
drones are the ultimate toys for boys.
295
769824
3688
12:53
But at the same time, we've also gotten to know
296
773512
2406
12:55
many wonderful colleagues and collaborators
297
775918
2249
12:58
who share our vision
298
778167
1548
12:59
and see the potential of conservation drones.
299
779715
2856
13:02
To us, it is obvious that conservation biologists
300
782571
3599
13:06
and practitioners should make full use
301
786170
2258
13:08
of every available tool, including drones,
302
788428
3534
13:11
in our fight to save the last remaining forests
303
791962
2641
13:14
and wildlife of this planet.
304
794603
1787
13:16
Thank you.
305
796390
1998
13:18
(Applause)
306
798388
5722
About this website

This site will introduce you to YouTube videos that are useful for learning English. You will see English lessons taught by top-notch teachers from around the world. Double-click on the English subtitles displayed on each video page to play the video from there. The subtitles scroll in sync with the video playback. If you have any comments or requests, please contact us using this contact form.

https://forms.gle/WvT1wiN1qDtmnspy7