GESTURE RECOGNITION: USING A MULTI SENSOR APPROACH SHALINI GUPTA, - - PowerPoint PPT Presentation

gesture recognition using a multi sensor approach
SMART_READER_LITE
LIVE PREVIEW

GESTURE RECOGNITION: USING A MULTI SENSOR APPROACH SHALINI GUPTA, - - PowerPoint PPT Presentation

GESTURE RECOGNITION: USING A MULTI SENSOR APPROACH SHALINI GUPTA, PAVLO MOLCHANOV, KIHWAN KIM, KARI PULLI, JAN KAUTZ NVIDIA RESEARCH DRIVER DISTRACTION GESTURE INTERFACE (http://www.softkinetic.com) DAY DAY NIGHT NO SUNLIGHT NO SUNLIGHT


slide-1
SLIDE 1

SHALINI GUPTA, PAVLO MOLCHANOV, KIHWAN KIM, KARI PULLI, JAN KAUTZ NVIDIA RESEARCH

GESTURE RECOGNITION: USING A MULTI SENSOR APPROACH

slide-2
SLIDE 2

DRIVER DISTRACTION

slide-3
SLIDE 3

GESTURE INTERFACE

(http://www.softkinetic.com)

slide-4
SLIDE 4

DAY

slide-5
SLIDE 5

DAY NIGHT

slide-6
SLIDE 6

NO SUNLIGHT

slide-7
SLIDE 7

NO SUNLIGHT SUNLIGHT

slide-8
SLIDE 8

sensors

COLOR + DEPTH RADAR

MULTI-SENSOR SOLUTION

slide-9
SLIDE 9

gesture UI sensors

COLOR + DEPTH RADAR

MULTI-SENSOR SOLUTION

slide-10
SLIDE 10

3D shape color velocity

3.2% INCREASED ACCURACY

+1.5m/s

  • 1.5m/s

0 m/s

slide-11
SLIDE 11

v t 0.15W velocity power

16X POWER EFFICIENCY

slide-12
SLIDE 12

v t 0.15W vT gesture gesture velocity power 2.5 W

16X POWER EFFICIENCY

slide-13
SLIDE 13

radar prototype

SHORT RANGE FMCW RADAR

slide-14
SLIDE 14

x y z v radar prototype 4D vector

SHORT RANGE FMCW RADAR

+1.5m/s

  • 1.5m/s

0 m/s

slide-15
SLIDE 15

POSITION RESULTS

slide-16
SLIDE 16

VELOCITY RESULTS

+1.5m/s

  • 1.5m/s

0 m/s

slide-17
SLIDE 17

GESTURE NETWORK

3D convolutional layer fully connected NN logistic regression subsampling layer 60 frames Trained on GPU

slide-18
SLIDE 18

10 GESTURES

PALM SWIPE SHAKE CALL left right up down left right clockwise counter-clockwise ROTATION

slide-19
SLIDE 19

INDOOR CAR SIMULATOR

slide-20
SLIDE 20

OUTDOOR CAR

slide-21
SLIDE 21

ERROR RATE

C D R D+C R+D R+C R+D+C 39.90% 9.10% 10.90%

D – depth C – color R - radar

slide-22
SLIDE 22

ERROR RATE

C D R D+C R+D R+C R+D+C 39.90% 9.10% 10.90% 7.90% 8.30% 7.40%

D – depth C – color R - radar

slide-23
SLIDE 23

ERROR RATE

C D R D+C R+D R+C R+D+C 39.90% 9.10% 10.90% 7.90% 8.30% 7.40% 5.90%

D – depth C – color R - radar

slide-24
SLIDE 24

ERROR RATE

D – depth C – color R - radar

Night Evening Day (shadow) Day (sunlight)

6.70% 3.00% 9.70% 20.90%

D+R (CNN) D+R+C (CNN) D+C (HOG)

slide-25
SLIDE 25

ERROR RATE

D – depth C – color R - radar

Night Evening Day (shadow) Day (sunlight)

6.70% 3.00% 9.70% 20.90% 6.70% 1.50% 8.30% 7.50%

D+R (CNN) D+R+C (CNN) D+C (HOG)

slide-26
SLIDE 26

ERROR RATE

D – depth C – color R - radar

Night Evening Day (shadow) Day (sunlight)

6.70% 1.50% 8.30% 7.50% 22.20% 2.45% 13.00% 20.90%

D+R (CNN) D+R+C (CNN) D+C (HOG*)

*Ohn-Bar and Trivedi, IEEE Trans. on

Intelligent Transportation Systems, 2014.

slide-27
SLIDE 27

52ms on Quadro 6000

DEMO

slide-28
SLIDE 28

CONCLUSION

GESTURE UI2 COLOR + DEPTH RADAR1

1Multi-sensor System for Driver’s Hand-Gesture Recognition, IEEE Automatic Face and Gesture Recognition, May 2015. 2Short-Range FMCW Monopulse Radar for Hand-Gesture Sensing, IEEE International Radar Conference, May 2015.

slide-29
SLIDE 29

THANK YOU

SHALINIG@NVIDIA.COM

slide-30
SLIDE 30

QUESTIONS?