Sherlock: Automatically Locating Objects for Humans

1
Sherlock Automatically Locating Objects for
Humans

• Aditya Nemmaluri, Mark D. Corner, Prashant Shenoy
• Department of Computer Science
• UMass Amherst

2
Cant Find Your Keys?

• People own uncountable objects (1000s?)
• Humans dont posses DB indexing abilities
• Lose, lend, misplace, waste time, rebuy, ...
• A grand challenge for pervasive computing

3
Wouldnt it be Nice?
Index, Search, and Locate Anything!
4
RFID Changes Everything

• Non-computers become computers
• For dimes, pennies, or less
• no batteries scalability
• Affix tags to every inanimate object
• Clothes, books, tools, doors, food, trash...

5
Challenges

• Localization the finer the better
• User interfaces augmented reality
• Search temporal and physical data
• Security and privacy

6
Sherlock

• Infrastructure based, steerable antennas
• Combine with PTZ cameras
• Localize objects to an small area
• Rely on humans to do the rest
• Practical demonstration in a realistic setting
• Search and display results

7
Sherlock Architecture
8
RFID Endpoint

• RFID reader equipped w/steerable antenna
• Can identify each passive tag within view
• Cant localize them directly
• Localization depends on (not)seeing tag
• Antenna has limited beamwidth/range
• Sherlock steers antenna intelligently

9
Localization-Pan
10
Localization-Zoom
11
Idealized Localization
Can locate tag to narrow (10 degree sliver)
12
Does This Work?

• Set up 30 tags in a near-ideal setting
• 60-70 degree antenna beam width (spec)
• Expect to see 60-70 degree tag beam width
• Expect low error rates
• tag is actually in that narrow 10 degrees

13
Ideal Results
14
Realistic Setting

• 100 Tags in a one person office
• books, doors, coffee mugs, staplers...
• metal cabinets, desks, windows, walls...

15
Realistic Results
16
Reflections/Occlusions
Occlusions
Reflections
17
Conservative Correction
Add 30-45 degrees depending on measured
beamwidth Yields zero error rate 10 degree sliver
becomes 70-100 degrees
18
Multiple Antennas

• Fuse 3D area from multiple antennas
• Chances are one gets a good view of tag
• Use a 3D intersection algorithm

19
Scan Strategies

• Localization takes time (lots of fine steps)
• Delays detection of new or stale objects
• Coarse, Fine, Localize see paper for details

20
Implementation

• Mechanically steerable antenna
• substitute for electronically steerable
• Two antennas (range 3m)
• ThingMagic Mercury5 Reader
• Alien RFID tags 98x12mm 76x76mm
• libGTS graphics library for 3D Intersections

21
Steerable Antenna
PTZ Base as stand in for electronic steering
22
Evaluation

• Same office environment as before
• Can it localize objects quickly?
• Can it localize to a reasonable volume?

23
Office Environment
24
Latency
25
Single Antenna
Useable localization Half of objects are
difficult to localize
26
Two Antennas
Many difficult localizations solved with second
antenna
27
Visualization

• For each localization take snap shot of area
• Project volume onto 2D photo
• Works if camera has view of object

28
Web Interface
29
Related Work

• RFID Localization (Hähnel et. al)
• SLAM robotics problem
• Ferret (Liu et. al)
• mobile reader
• RFID Radar
• TTF technology, precise timing

30
Sherlock

• Practical room-level object indexing system
• Iterative and robust localization algorithm
• Visualization and search system