Scribd
Upload
7 views18 pages

Intuwition Mobicom2019

intuwition-mobicom2019

Uploaded by

jyvrdh9yvg
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views18 pages

Intuwition Mobicom2019

intuwition-mobicom2019

Uploaded by

jyvrdh9yvg
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 18

On the Feasibility of

WiFi-Based Material Sensing


October 24, 2019
Diana Zhang*, Jingxian Wang*, Junsu Jang†, Junbo Zhang*,
Swarun Kumar*
*Carnegie Mellon University, †MIT Media Lab
Drones are increasingly useful in obstacle-rich environments.

Disaster Sites
Urban Settings Warehouses

2
Drones must make obstacle-specific responses to maximize utility

The sensing system must be infrastructure-free and contained entirely on the drone. 3
Current infrastructure-free sensing solutions cannot enable this.

Obstacle Type Non-Line-of-Sight


Identification Sensing

?
Vision-based RF-Based
(LIDAR, Infrared,…) (WiFi, RADAR,…)

4
IntuWition

A complementary WiFi-Based sensing system that can detect


material of obstacles in line-of-sight and non-line-of-sight settings.

• Uses existing WiFi radio already on many drones


• Does not assume infrastructure
• Applies beyond drones – vehicles, product testing, disasters, etc.

5
IntuWition comprises two major parts:

wood
(1, 2)
1. Localization
metal 2. Material
Material Sensing
Sensing
(3, 6)

human
(9, 2)

Tx Rx

6
Radar Polarimetry can measure material-specific responses

α wood =180°
Different α values
can be used to
distinguish materials

α metal =90°

7
To bring Radar Polarimetry to WiFi, a vertically
polarized signal must be transmitted and received
α wood =180°

α metal =90°

8
Challenge #1: Multi-Bounce

Vs.

9
Since the α values of multi-bounce are related
to the single-reflection, these can be removed
α wood =180°

α metal =90°

Algorithm looks for alpha and locations that are consistent with physics of multi-
bounce, to eliminate them as spurious (details in paper) 10
Challenge #2: Several Variations in Material

11
Solution: Devise machine learning models
Material Classification Accuracy by Model
100 94
88
90
80 73 76
69
Accuracy (%) 70
60
50
40
30
20
10
0
PCA kNN SVM NB MLP
Machine Learning Model

ML model accounts for additional challenges: location, texture – details in the paper.
12
IntuWition’s System Overview:

IN SUMMARY…

13
We tested polarimetry as a material identification
feature across a variety of materials and platforms.

14
Our system showed high classification rates
for five classes of materials.
5 classes, sheets of material

15
Further, our system also worked well for
classifying real-life objects as wood or metal.

Wood vs. Metal Classification of Real-Life Objects

16
Limitations

• Can’t detect signal when too weak, too occluded, or too many multi-bounce
effects
• Cannot distinguish materials of similar polarization characteristics
• May respond excessively to surface characteristics (e.g. clothing)

17
IntuWition is a system that explores sensing
the material and location of occluded objects
• Uses COTS WiFi radios
• Our evaluation demonstrates promising accuracy in material classification
• Applies broadly beyond drones: vehicles, disaster response, product testing, etc.
• Future work includes more objects, on-board processing, and sensor fusion

www.witechlab.com/intuwition

18

You might also like