Download presentation
Presentation is loading. Please wait.
1
Dieter Fox University of Washington Department of Computer Science & Engineering
2
Joint work with Students: Brian Ferris, Julie Letchner, Lin Liao, Don Patterson, Alvin Raj, Amarnag Subramanya, Danny Wyatt UW faculty: Jeff Bilmes, Gaetano Borriello, Henry Kautz Intel Research Seattle: Tanzeem Choudhury, Matthai Philipose Funded by NSF, DARPA, MSR, Toyota Dieter Fox: Activity Recognition From Wearable Sensors2573 AU-08
3
U.S. by 2050: 80 million people over age 65 and 13-16 million Alzheimer's patients Goal: Develop technology to Support independent living by people with cognitive disabilities ▪ At home ▪ At work ▪ Throughout community Improve health care ▪ Long term monitoring of activities of daily living (ADL’s) ▪ Intervention before a health crisis 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors3
4
4 Transportation routines via Dynamic Bayes Nets Significant places via Conditional Random Fields Activity recognition projects Discussion 573 AU-08
5
Given data stream from a wearable GPS unit Infer the user’s location and mode of transportation (foot, car, bus, bike,...) Predict where user will go Detect novel behavior / user errors 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors5 [Liao-Fox-Kautz: AAAI-04, AIJ-07]
6
Dead and semi-dead zones near buildings, trees, etc. Sparse measurements inside vehicles, especially bus Multi-path propagation Inaccurate street map … 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors6
7
Map is directed graph Location: Edge e Distance d from start of edge Prediction: Move along edges according to velocity model Correction: Update estimate based on GPS reading 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors7
8
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors8 GPS reading z k-1 zkzk Edge, velocity, position x k-1 xkxk Time k-1 Time k Task: Estimate posterior over hidden states
10
Problem: Predicted location is multi-modal 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors10 e 1 e 2 e 3 k-1 x e 0 ? ?
11
Problem: GPS reading is not on the graph 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors11 e 1 e 2 e 3 z k k x
12
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors12 e 1 e 2 e 3 z k k x if =e 1 k x Problem: GPS reading is not on the graph
13
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors13 e 1 e 2 e 3 z k k x if =e 2 k x Problem: GPS reading is not on the graph
14
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors14 GPS reading z k-1 zkzk Edge, velocity, position x k-1 xkxk Time k-1 Time k Task: Estimate posterior over all hidden states k-1 k GPS association e k-1 ekek Edge transition
15
STREET MAP Source: Tiger / Line data BUS ROUTES / STOPS Source: Metro GIS 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors15 RESTAURANTS / STORES Source: MS MapPoint
16
Represents posterior by sets of weighted particles: Basic idea: Sample some variables of state space and solve other variables analytically conditioned on samples Here: Each particle contains Kalman filter for location: Update sets by sampling procedure (SISR) 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors16 Edge transitions, velocities, edge associations KF for position
17
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors17 GPS measurements Particles (Kalman filters)
18
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors18 GPS reading z k-1 zkzk Edge, velocity, position x k-1 xkxk Time k-1 Time k m k-1 mkmk Transportation mode Particles:
19
Encode prior knowledge into the model Modes have different velocity distributions Buses run on bus routes Get on/off the bus near bus stops Switch to car near car location 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors19
20
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors20 Measurements Projections Bus mode Car mode Foot mode Green Red Blue
21
Goal (destination): workplace (home, friends, restaurant,...) Trip segments: Home to Bus stop A on Foot Bus stop A to Bus stop B on Bus Bus stop B to workplace on Foot 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors21 BAWorkplace
22
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors22 GPS reading z k-1 zkzk Edge, velocity, position x k-1 xkxk Time k-1 Time k m k-1 mkmk Transportation mode t k-1 tktk Trip segment g k-1 gkgk Goal Particles: [Bui-Venkatesh-West: JAIR-02] [Liao-Fox-Kautz: AAAI-04, AIJ-07]
23
Customized model for each user Key to goal / path prediction and error detection Use low level model to learn variable domains Goals: locations where user stays for long time Transition points: locations with high mode transition probability Trip segments: connecting transition points or goals Use full model to learn parameters Transition probabilities (goals, trips, edges) via EM 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors23
24
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors24 Predicted goal Predicted path
25
GOING TO THE WORKPLACEGOING HOME 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors25 High probability transitions: bus car foot
26
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors26 0.5 43 0.5 5
27
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors27 GPS reading z k-1 zkzk Edge, velocity, position x k-1 xkxk Time k-1 Time k m k-1 mkmk Transportation mode t k-1 tktk Trip segment g k-1 gkgk Goal b k-1 bkbk Behavior mode normal / unknown / error [Patterson-Liao-etAl: Ubicomp-04]
28
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors28
29
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors29 Untrained flat model Trained model Instantiated model
30
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors30
31
Dieter Fox: Activity Recognition From Wearable Sensors31 Transportation routines via Dynamic Bayes Nets Significant places via Conditional Random Fields Activity recognition projects Discussion 573 AU-08
32
So far No distinction between different types of goals Model not transferable to other person Goals learned solely based on duration 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors32 [Liao-Fox-Kautz: NIPS-05,IJCAI-05,IJRR-07]
33
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors33 Store Home Bus stop Parking Friend Restaurant Work
34
Undirected graphical model Introduced for labeling sequence data [Lafferty-et al: ICML-01] No independence assumption on observations! Trained discriminatively from labeled data Applied successfully to Natural language processing [McCallum-Li: CoNLL-03], [Roth-Yih: ICML-05] Computer vision [Kumar-Hebert: NIPS-04], [Quattoni-Collins-Darrel: NIPS-05] Robotics [Limketkai-Liao-Fox: IJCAI-05], [Friedman-Pasula-Fox: IJCAI-07] Dieter Fox: Activity Recognition From Wearable Sensors34573 AU-08
35
Posterior factorizes into log-linear clique potentials Local potentials link states to observations / features Neighborhood potentials link states to neighboring states Dieter Fox: Activity Recognition From Wearable Sensors35 Hidden states x Observations z 573 AU-08 Conditional Random Fields
36
Posterior factorizes into log-linear clique potentials Local potentials link states to observations / features Neighborhood potentials link states to neighboring states Dieter Fox: Activity Recognition From Wearable Sensors36 Hidden states x Observations z 573 AU-08 Conditional Random Fields
37
Posterior factorizes into log-linear clique potentials Local potentials link states to observations / features Neighborhood potentials link states to neighboring states Dieter Fox: Activity Recognition From Wearable Sensors37 Hidden states x Observations z 573 AU-08 Conditional Random Fields Partition function WeightsFeature functions
38
Conditional distribution parameterized via weights w: Maximize conditional log-likelihood with shrinkage prior: Maximization via stochastic / conjugate gradient, L-BFGS Alternative: maximize pseudo log-likelihood Dieter Fox: Activity Recognition From Wearable Sensors38573 AU-08 [Besag: 1975]
39
BP computes posteriors via local message passing Sum-product for posterior Max-product for MAP Exact if network has no loops Otherwise, run loopy belief propagation and hope it works Alternatives: ICM, graph-cut, MCMC, … Dieter Fox: Activity Recognition From Wearable Sensors39573 AU-08....
40
Temporal pattern: duration, time of day, etc. Geographic evidence: is there a restaurant / store / bus stop nearby? Transition relation: adjacent activities Spatial feature: relation between place and activity Summation constraint: number of places labeled home or workplace 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors40
41
GPS trace 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors41 … … Activity sequence walk, drive, ride bus, work, visit, sleep, pickup, get on/off bus a1a1 a2a2 a3a3 a4a4 a5a5 a N-2 a N-1 aNaN [Liao-Fox-Kautz: NIPS-05]
42
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors42 … GPS trace Two weeks data (> 50,000 gps points) Inference: loopy BP (10 minutes); Learning: Pseudo-likelihood (3 minutes) … Activity sequence walk, drive, ride bus, work, visit, sleep, pickup, get on/off bus a1a1 a2a2 a3a3 a4a4 a5a5 a N-2 a N-1 aNaN … Significant places home, work, bus stop, parking lot, friend’s home p1p1 p2p2 p3p3 pKpK Global, soft constraints # homes, workplaces wh [Liao-Fox-Kautz: NIPS-05]
43
Generalize from people with labeled data to others without labeled data Relational Markov Networks to specify CRFs and parameter sharing via templates 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors43 Training data User1 User2 User3 Generic model Other users Supervised learning Shared parameters [Taskar-Abbeel-Koller: UAI-02]
44
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors44
45
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors45
46
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors46
47
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors47 Cross-validation using data from 4 persons
48
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors48
49
Dieter Fox: Activity Recognition From Wearable Sensors49 Transportation routines via Dynamic Bayes Nets Significant places via Conditional Random Fields Activity recognition projects Discussion 573 AU-08
50
Dieter Fox: Activity Recognition From Wearable Sensors50 [Ferris-Haehnel-Fox: RSS-06]
51
GP regression nonparametric smooth interpolation uncertainty estimates 573 AU-08 Dieter Fox: Activity Recognition From Wearable Sensors 51 Mean Variance
52
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors52
53
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors53 Battery Camera (on ribbon cable) GPS receiver iMote2 + two sensor boards MicrophoneCamera Light sensors 2 GB SD card Indicator LEDs Records 4 hours of audio, images (1/sec), GPS, and sensor data (accelerometer, barometric pressure, light intensity, gyroscope, magnetometer)
54
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors54 Courtesy of G. Borriello
55
55573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors [Subramanya-Raj-Bilmes-Fox: UAI-06, ISRR-06] Boosted cassifiers [Lester-Choudhury-etAl: IJCAI-05] Virtual evidence boosting [Liao-Choudhury-Fox-Kautz: IJCAI-07] Accuracy: 88% activities, 93% environment
56
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors56 GPS traces Image sequence (currently in car) Timeline of soldier activities
57
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors57 [Patterson-Fox-Kautz-Philipose: ISWC-05] [Philipose-Fishkin-etAl: Pervasive-04]
58
573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors58
59
59573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors
60
Performs object aggregation and smoothing over object types Accuracy: 88% SED: 6.4 60573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors
61
61 Transportation routines via Dynamic Bayes Nets Significant places via Conditional Random Fields Activity recognition projects Discussion 573 AU-08
62
Graph-based representation well suited to compactly represent and learn motion patterns Hierarchical graphical models (DBN, CRF) powerful tools for bridging gap between continuous sensor data and abstract states Conditional Random Fields can handle high- dimensional / dependent feature vectors Sensor-based activity recognition is an exciting research area with potentially huge impact! 573 AU-08Dieter Fox: Activity Recognition From Wearable Sensors62
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.