Respectful Cameras

1
Respectful Cameras

• Jeremy Schiff
• EECS Department
• University of California, Berkeley
• Ken Goldberg, Marci Meingast,
• Deirdre Mulligan, Pam Samuelson
• IEOR, EECS, Law
• University of California, Berkeley
• http//www.cs.berkeley.edu/jschiff/RespectfulCame
  ras
• NSF Science and Technology Center, Team for
  Research in Ubiquitous Secure Technologies, NSF
  CCF-0424422, with additional support from Cisco,
  HP, IBM, Intel, Microsoft, Symmantec, Telecom
  Italia and United Technologies.

2
Background

• New class of Robotic Cameras since 9/11/2001
• 20,000 -gt Under 1,000
• Static -gt Pan, tilt, zoom (21x)
• UK - 3 Million Outdoor Cameras
• Now Deploying in Large US Cities

Zoom Example
3
Invasiveness
4
Objective
5
Static Marker Detection

• Adaboost
• Training Phase
• Input is data and label
• Classifying Phase
• Data -gt label
• Linear function of weak classifiers
• Example
• Construction Hat Color

6
Features

• Input from images
• Each pixel
• red, green, blue (RGB)
• Values 0 to 255
• Project into higher dimension
• Convert to 9 dimensions
• RGB
• HSV
• Stable over changing lighting
• LAB
• Good for detecting specularities

7
Classifiers

• Operates on each dimension
• Threshold value
• Above good and below bad
• Above bad and below good
• Example

8
Connected Component

• Groups adjacent pixels
• Threshold
• Minimum Area
• Bounding Box
• Acceptable Ratio Between Dimensions

9
Marker Tracking

• Particle Filtering
• Probabilistic Method for Tracking
• Motivates Probabilistic AdaBoost

10
Particle filters

• Non-Parametric
• Sample Based Method (Particles)
• Particle Density Likelihood
• Tracking requires three distributions
• Initialization Distribution
• Transition Model (Intruder Model)
• Observation Model
• Determines

11
Observation Model
0.1
0.1
0.1
0.2
1-p
0.8
0.6
0.0
0.4
p
0.7
0.9
0.4
0.2
p
0.1
0.2
0.3
0.2
0.9
0.9
0.9
0.8
0.8
0.6
1.0
0.6
0.79375
0.7
0.9
0.6
0.8
0.9
0.8
0.7
0.8
12
Transition Model

• State
• Position
• Bounding-box Width
• Bounding-box Height
• Orientation
• Speed
• Add Gaussian Noise to width, height, orientation
  and speed
• Euler Integration to determine new position

13
Multiple Filters

• Single Filter Per Marker
• Define overlap
• Add Filter when overlap of Static Image Cluster
  and all filters is below threshold
• Delete Filter when prob. of best particle lt 0.5
• Delete Filter when 2 filters overlap gt threshold

14
Video Nearby Hats
15
Video Nearby Hats
16
Video Lighting
17
Video Lighting
18
Video Crossing
19
Video Crossing
20
Video Shirt
21
Video Shirt
22
Future Work

• Other Features
• Edge Detection
• Feature Structure
• Generalize to Other Domains
• Other Obstruction Mechanisms
• Encryption
• Full Body
• Multiple Cameras

23
Thank You

• Jeremy Schiff jschiff_at_cs.berkeley.edu
• URL www.cs.berkeley.edu/jschiff/RespectfulCamera
  s