Title: Automated Intruder Tracking using Particle Filtering and a Network of Binary Motion Sensors
1Automated Intruder Tracking using Particle
Filtering and a Network of Binary Motion Sensors
- Jeremy Schiff
- EECS Department
- University of California, Berkeley
- Ken Goldberg
- IEOR and EECS Departments
- University of California, Berkeley
- http//www.cs.berkeley.edu/jschiff
- Supported by NSF Grants 0424422/0535218
2Outline
- Introduction
- Related Work
- Problem Formulation
- Setup and Assumptions
- Particle Filtering
- Results
- Simulation
- Experimental
- Conclusion/Future Work
3Motivation
- New class of technologies due to 9/11
- Automated Security
- Wireless Sensor Networks
- X10 PIR sensors - 25
- Robotic Webcams
- Pan, Tilt, Zoom
- 500 Mpixels/Steradian
- Increased computer processing speeds
- Enables Realtime Applications
4Goal and Approach
- Wish to secure an environment
- Low Cost Binary Sensors
- X10 25
- Optical Beam
- Floor Pad
- Manufactured in China
- Noisy triggering pattern
- Refraction
- Use sensor triggering patterns to accurately
localize an intruder
5Intuition
- Utilize Sensor Overlap Information
6Intuition
- Utilize Sensor Overlap Information
7Outline
- Introduction
- Related Work
- Problem Formulation
- Setup and Assumptions
- Particle Filtering
- Experiments
- Simulation
- Real-world
- Conclusion/Future Work
8Related Work
- Pursuer/Evader Games
- Using line-of sight optical sensors
- Isler, Kannan, Khanna 2004
- Avoid being seen by evader
- Bandyopadhyay et al. 2004
- Tracking Worn Devices
- Track Infrared Beacon
- Shen et al. 2004
- Dynamic Shipment Planning using RFIDs
- Kim et al. 2005
9Related Work II
- Video Tracking Systems
- Micilotta and Bowden 2004
- Multiple Classes of Sensors
- Multiple exclusive modes
- Cochran, Sinno, Clausen 1999
- Fuse data of multiple sensor types
- Jeffery et al. 2005
- Automated Camera Control
- Song et al. 2005
Virtual Devices
Physical Devices
10Related Work III
- Probabilistic Tracking Approaches
- Kalman Filtering
- Kalman 1960
- Extended Kalman Filtering
- Lefebvre, Bruyninckx, De Schutter 2004
- Particle Filtering
- Book Thrun, Burgard, Fox 2005
- Arulampalam et al. 2002
11Related Work IV
- Multiple humans controlling a camera
- Song and Goldberg 2003
- Song, Goldberg and Pashkevich 2003
- Panorama Generation
- Song et al. 2005
- Art Gallery Problem
- Shermer 1990
- Urrutia 2000
12Outline
- Introduction
- Related Work
- Problem Formulation
- Setup and Assumptions
- Particle Filtering
- Experiments
- Simulation
- Real-world
- Conclusion/Future Work
13Setup and Assumptions
- Room Geometry
- List of nodes and edges
- Discretize space
- Discretize time
14Setup and Assumptions II
- Intruder occupied world-space cell j in iteration
-
- Sensor i triggered during iteration
-
- Sensor i experienced refraction period in
iteration -
15Setup and Assumptions III
- Three Conditional Distributions
- Trigger while experiencing refraction
-
- Trigger from intruder
-
- Trigger from no intruder
-
16Output
- Estimated intruder location
- Objective
- Minimize error between ground truth and
estimation.
17Characterization
- Per sensor type
- Grid over sensor space
- Determine
- Refraction period
- False Negative Rate
- False Positive Rate
18Deployment
- Convert to world-space
- Overlay grid
- Transformed point to Cells
19Deployment II
- Determine potential non-zero characterization
cells via convex hull - Inverse Distance Weighting
- Interpolation according to distance
- Determines values for cells without readings
inside convex hull
20Particle filters
- Non-Parametric
- Sample Based Method (Particles)
- Particle Density Likelihood
- Tracking requires three distributions
- Initialization Distribution
-
-
- Transition Model (Intruder Model)
-
-
- Observation Model
-
- Determines
21Example
22Example
23Intruder Model
- State
- Position, Orientation, Speed, and Refracting
Sensors - Euler Integration for position
- Gaussian Random Walk for new speed and
orientation - Orientation change inversely proportional to
speed - Deterministic refraction periods
- Rejection Sampling to enforce room geometry
24Intruder Model II
- Time between iterations
-
- Empirically determined constants
-
25Intruder Model - Example
Example state at iteration 0
26Intruder Model - Example
Accepted state for iteration 1
27Intruder Model - Example
Example state at iteration 1
28Intruder Model - Example
Accepted state for iteration 2
29Intruder Model - Example
Example state at iteration 2
30Intruder Model - Example
Rejected state for iteration 2
31Intruder Model - Example
Example state at iteration 2
32Intruder Model - Example
Rejected state for iteration 2
33Intruder Model - Example
Example state at iteration 2
34Intruder Model - Example
Accepted state for iteration 2
35Sensor Model
- Evidence is vector of which sensors are
triggering - Triggering of sensors independent given intruder
state implies -
- If sensor refracting
-
- Otherwise
-
36Outline
- Introduction
- Related Work
- Problem Formulation
- Setup and Assumptions
- Particle Filtering
- Experiments
- Simulation
- Real-world
- Conclusion/Future Work
37Simulation Setup
- 22 Optical Beams
- Perfect
- Optimal Performance
- 14 Triangular Motion Sensor
- Perfect Imperfect
38Simulation Results
- Example Path
- Ground Truth
- Red Circles
- Estimations
- Grey Circles
39Simulation Results II
- Baseline Estimate
- Perfect Optical-Beam Sensors
40Simulation Results III
- Perfect Triangular Motion Sensors
- Imperfect Triangular Motion Sensors
41Simulation Results IV
- Error over Time 4 Sec. Refraction, Imperfect
Sensors - Density - 8 Sec. Refraction, Imperfect Sensors
42In-Lab Results
- 8 Passive Infrared Sensors
- X10
- 8 second refraction time
- Room 8x6 meters
- .3 m /Cell dimension
- Sampled every 2 seconds
- 1000 Particles
43In-Lab Results II
44Outline
- Introduction
- Related Work
- Problem Formulation
- Setup and Assumptions
- Particle Filtering
- Results
- Simulation
- Experimental
- Conclusion/Future Work
45Conclusions
- Real-time Tracking System
- Binary Sensors with Refraction Period
- Particle Filtering for Sensor Fusion
- Conditional Probability Models
- Models
- Intruder Velocity
- Room Geometry
- Sensor Characterization
46Future Work
- Effects of varying different components
- Number Particles
- Types of sensors
- Spatial arrangements of sensors
- Multiple intruders
- Decentralize
- Vision Processing
- Other applications
- Warehouse Tracking
47Thank You
- Jeremy Schiff jschiff_at_cs.berkeley.edu
- Ken Goldberg goldberg_at_ieor.berkeley.edu
- URL www.cs.berkeley.edu/jschiff