Visual disability Low vision 2015 Estimated blind people 2020 - - PowerPoint PPT Presentation

visual disability
SMART_READER_LITE
LIVE PREVIEW

Visual disability Low vision 2015 Estimated blind people 2020 - - PowerPoint PPT Presentation

Visual disability Low vision 2015 Estimated blind people 2020 Visually impaired 285 M Blind 54 M Blind 39 M Global data souce: WHO, IBU See the world through the eyes of a visually impaired person Normal vision Cataract Glaucoma


slide-1
SLIDE 1
slide-2
SLIDE 2

Low vision 2015 Visually impaired 285 M Estimated blind people 2020 Blind 39 M Blind 54 M

Global data souce: WHO, IBU

Visual disability

slide-3
SLIDE 3

See the world through the eyes of a visually impaired person

slide-4
SLIDE 4

Normal vision

slide-5
SLIDE 5

Cataract

slide-6
SLIDE 6

Glaucoma

slide-7
SLIDE 7

Macular degeneration

slide-8
SLIDE 8

Diabetic Retinopathy

slide-9
SLIDE 9

Complete blindness

slide-10
SLIDE 10

One goal: independence

slide-11
SLIDE 11

Text recognition

slide-12
SLIDE 12

Object recognition

slide-13
SLIDE 13

Mobility assistance

slide-14
SLIDE 14

Scene and photos description

slide-15
SLIDE 15

Face recognition

slide-16
SLIDE 16

Day-lasting battery OTA Upgrades Smartphone App Real time performance (offline) Obstacle perception

Possible approaches

Single Camera Stereo Camera CPU Stereo Camera FPGA Stereo Camera GPU

slide-17
SLIDE 17
slide-18
SLIDE 18

How Horus works

Externalinput identification Cameras aquire images Image are transferred to the computing unit

3 2 1

Audio is transferred back to the headset

5

Information extraction

4

Sound output

6

slide-19
SLIDE 19

What Horus does

Horus can help the user with:

Scene description Face recognition Text reading Object recognition Mobility assistance

slide-20
SLIDE 20

ON/OFF button After powering Horus, the user can choose the desired functionality by navigating a vocal menu using the navigation buttons.

User interaction

Navigationbuttons

Scene description Text reading Face recognition Mobility assistance Object recognition

Navigation menu

slide-21
SLIDE 21

Whole process runs on NVIDIA TK1

A sunset over the mountains Convolutional network Language model

Image description with Deep Learning

slide-22
SLIDE 22

CNN: 595ms LSTM: 1200ms

TOTAL: 1795ms

CNN: 22ms LSTM: 498ms

TOTAL: 520ms

300 MB Processing time on GPU Memory footprint

Results on TK1 CPU vs GPU (CNN + LSTM)

Processing time on GPU

~3.5X faster on GPU

slide-23
SLIDE 23

User

High-pitched sound left

Horus uses 3D sound to report the presence of obstacles during movement. The space in front of the user is divided in different sectors: lateral obstacles generate high-pitched sounds in one of the two speakers, while central obstacles generate low pitched centered sounds. These sounds are repetitive and they increase in repetition frequency as the

  • bstacle gets closer.

High-pitched sound right

Reporting obstacles

Low-pitched sound center

slide-24
SLIDE 24

5650 ms 116 ms Processing time on GPU (Visionworks)

Results on TK1 CPU vs GPU (SGBM @480p)

Processing time on CPU

~48X faster on GPU

slide-25
SLIDE 25

If the text is located in the upper part of the fieldof view, Horus emits a high-pitched sound to tell the userto lower the text If the text is located in the lower part of the fieldof view, Horus emits a low-pitched sound to tell the userto raise the text

Example of audio feedback

slide-26
SLIDE 26

Source frame

Face recognition

Face detection Tracking CNN Classification

slide-27
SLIDE 27

Future improvements 3D reconstruction of faces 3D undistortion of sheets Object recognition Multi language LSTM models

slide-28
SLIDE 28

www.horus.tech info@horus.tech