SA-1 University of Washington University of Washington Department of Computer Science & Department of Computer Science & Engineering Engineering Robotics and State Estimation Lab Robotics and State Estimation Lab Dieter Fox Dieter Fox Stephen Friedman, Lin Liao, Benson Stephen Friedman, Lin Liao, Benson Limketkai Limketkai Conditional Random Fields Conditional Random Fields and their Application to and their Application to Labeling Objects and Labeling Objects and Places Places
48
Embed
University of Washington Department of Computer Science & Engineering
Conditional Random Fields and their Application to Labeling Objects and Places. University of Washington Department of Computer Science & Engineering Robotics and State Estimation Lab Dieter Fox Stephen Friedman, Lin Liao, Benson Limketkai. Relational Object Maps (RO-Maps). - PowerPoint PPT Presentation
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
SA-1
University of WashingtonUniversity of Washington
Department of Computer Science & Department of Computer Science & EngineeringEngineering
Robotics and State Estimation LabRobotics and State Estimation Lab
Dieter FoxDieter Fox
Stephen Friedman, Lin Liao, Benson LimketkaiStephen Friedman, Lin Liao, Benson Limketkai
Conditional Random Fields Conditional Random Fields and their Application to and their Application to
Labeling Objects and Places Labeling Objects and Places
►Current maps (topological, occupancy, Current maps (topological, occupancy, landmark) do not provide object-level landmark) do not provide object-level descriptions of environmentsdescriptions of environments
►Goal:Goal: describe environments in terms describe environments in terms of of objectsobjects (doors, walls, furniture, etc.) (doors, walls, furniture, etc.) and and placesplaces (hallways, rooms, open (hallways, rooms, open spaces).spaces).
►Needed:Needed: Probabilistic models to reason about Probabilistic models to reason about
complex spatial constraintscomplex spatial constraints Techniques to learn parameters of such Techniques to learn parameters of such
modelsmodels
Context is CrucialContext is Crucial
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
5
OverviewOverview
►Conditional Random FieldsConditional Random Fields
►Low-level detection of doors and wallsLow-level detection of doors and walls
►High-level place labelingHigh-level place labeling
►Future workFuture work
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
6
Conditional Random Fields (CRF)Conditional Random Fields (CRF)
►Undirected graphical modelUndirected graphical model► Introduced for labeling sequence dataIntroduced for labeling sequence data
► No independence assumption on No independence assumption on observations!observations!
► Extremely flexibleExtremely flexible
Hidden variables Y
Observations X
[Lafferty et al.; ICML 2001]
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
7
► Conditional probability defined via Conditional probability defined via clique clique potentialspotentials (non-negative functions over variable values in (non-negative functions over variable values in cliques of graph)cliques of graph)
Probabilities in CRFsProbabilities in CRFs
Cc
cccZp ),(
)(
1)|( yx
xxy
Hidden variables Y
Observations X
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
8
► Conditional probability defined via Conditional probability defined via clique clique potentialspotentials (non-negative functions over variable values in (non-negative functions over variable values in cliques of graph)cliques of graph)
► Partition functionPartition function Z(x) normalizes probabilities Z(x) normalizes probabilities(necessary since potentials are not normalized, as in directed (necessary since potentials are not normalized, as in directed models)models)
Probabilities in CRFsProbabilities in CRFs
Cc
cccZp ),(
)(
1)|( yx
xxy
y
yxxCc
cccZ ),()(
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
9
► Typically, potentials defined via log-linear Typically, potentials defined via log-linear modelmodel(linear combination of feature vectors extracted from variable (linear combination of feature vectors extracted from variable values)values)
► Compute conditional probability via local Compute conditional probability via local message passing called message passing called belief propagation (BP)belief propagation (BP)
► BP is exact if network has no loops (tree)BP is exact if network has no loops (tree)
► Corresponds to smoothing for linear chain CRFsCorresponds to smoothing for linear chain CRFs► General networks: loopy BP (might not converge)General networks: loopy BP (might not converge)► Can also compute MAP configurationCan also compute MAP configuration► Alternative: sample configurations via Alternative: sample configurations via MCMCMCMC
Inference in CRFsInference in CRFs
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
11
► Maximize conditional likelihood of Maximize conditional likelihood of labeled datalabeled data
► Conjugate gradient descentConjugate gradient descent Compute gradient of log-likelihood wrt. weightsCompute gradient of log-likelihood wrt. weights Inference at each maximization stepInference at each maximization step Optional: Maximize conditional pseudo likelihoodOptional: Maximize conditional pseudo likelihood
► Typically zero mean shrinkage prior on Typically zero mean shrinkage prior on weightsweights
Discriminative Training of CRFsDiscriminative Training of CRFs
Ccccc
TcZ
),(fexp),(
1maxarg* yxw
wxw
w
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
12
OverviewOverview
►Conditional Random FieldsConditional Random Fields
►Low-level detection of doors and wallsLow-level detection of doors and walls
►High-level place labelingHigh-level place labeling
►Future workFuture work
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
13
Relational Object MapsRelational Object Maps
►Objects: Doors, Wall segments, OtherObjects: Doors, Wall segments, Other Built from geometric primitives (line Built from geometric primitives (line
segments)segments) Can generate more complex objects from Can generate more complex objects from
existing ones via existing ones via physical aggregationphysical aggregation
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
14
Relational Object MapsRelational Object Maps
►Objects: Doors, Wall segments, OtherObjects: Doors, Wall segments, Other Built from geometric primitives (line Built from geometric primitives (line
segments)segments) Can generate more complex objects from Can generate more complex objects from
existing ones via existing ones via physical aggregationphysical aggregation
►Gibbs samplingGibbs sampling Assign random label to each line segmentAssign random label to each line segment At each MCMC step, update the label of At each MCMC step, update the label of
some object by sampling from the some object by sampling from the conditional distribution.conditional distribution.
►When the label of an object When the label of an object kk is is changed, need to update the cliques changed, need to update the cliques and the parameters of objects and the parameters of objects involving object involving object kk..
►Goal: Estimate labels (types) of Goal: Estimate labels (types) of objectsobjects
►Complication: Clique structures Complication: Clique structures change based on label of objectchange based on label of object
physical aggregation
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
17
Experimental SetupExperimental Setup
►Maps of five different environmentsMaps of five different environments: : one of Allen (UW) and four from Radishone of Allen (UW) and four from Radish—Robotics Data Set Repository—Robotics Data Set Repository
►Two to three hallways per environmentTwo to three hallways per environment; ; line segments labelled by handline segments labelled by hand
►Five-fold cross-validationFive-fold cross-validation ( (i.e.i.e., train on , train on hallways of four environments and test hallways of four environments and test on hallways from fifth environment)on hallways from fifth environment)
►Enables better planning and natural Enables better planning and natural interface between humans and robotsinterface between humans and robots
SA-1
Goal
RoomRoom
CorridorCorridor DoorwayDoorway
Courtesy of Wolfram Burgard
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
28
Local Approach Using Local Approach Using AdaBoostAdaBoost
► Learn to label individual locationsLearn to label individual locations
► Extract laser range-features from occupancy Extract laser range-features from occupancy map (size of area, difference between laser map (size of area, difference between laser beams, FFTs, axes of ellipse, … )beams, FFTs, axes of ellipse, … )
► Learn to classify locations using supervised Learn to classify locations using supervised AdaBoost learningAdaBoost learning
SA-1
Simple Features
• gap = d > θ• f = # gaps
minimum
• f =area • f =perimeter • f = d
ddi
N
1f
d
• f = d•
d
Σ di
Courtesy of Wolfram Burgard
SA-1
Combining Features
• Observation: There are many simple features fi.
• Problem: Each single feature fi gives poor classification rates.
• Solution: Combine multiple simple features to form a strong classifier using AdaBoost.
Courtesy of Wolfram Burgard
SA-1
Key Idea of AdaBoost
observation1
.
.
.
observationN
B
O
O
S
T
I
N
G
w1h1
.
wT hT
.
.
Σ
Strong binary classifier H
using weak hypotheses hj
{1,0}θ
Courtesy of Wolfram Burgard
SA-1
Courtesy of Wolfram Burgard
Example Experiment
Training (top) # examples:
16045
Test (bottom)# examples:
18726classification:
93.94%
Building 079 Univ. of Freiburg
RoomRoomCorridorCorridor DoorwayDoorway
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
33
Voronoi Random FieldsVoronoi Random Fields
►Local approach does not take Local approach does not take neighborhood relation between locations neighborhood relation between locations into accountinto account
►Neighboorhood defined via Voronoi GraphNeighboorhood defined via Voronoi Graph
► IdeaIdea: Label points on Voronoi Graph using : Label points on Voronoi Graph using CRFCRF
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
34
Voronoi Random FieldsVoronoi Random Fields
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
35
FeaturesFeatures
►SpatialSpatial: : Scan-based [Martinez-Mozos et al. 04]Scan-based [Martinez-Mozos et al. 04] Voronoi graph-basedVoronoi graph-based
►ConnectivityConnectivity via Voronoi graph: via Voronoi graph: Type of neighborsType of neighbors Number of neighborsNumber of neighbors Size of loopSize of loop
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
36
LearningLearning
►Learn decision stumps using AdaBoostLearn decision stumps using AdaBoost
►Feed decision stumps as binary features Feed decision stumps as binary features into CRFinto CRF
►Learn weights using pseudo-likelihood in Learn weights using pseudo-likelihood in CRFCRF
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
37
MapsMaps
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
38
MapsMaps
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
39
MapsMaps
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
40
MapsMaps
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
41
Experimental ResultsExperimental Results
►Leave one out cross validation on 4 Leave one out cross validation on 4 mapsmaps
►ConsistencyConsistency:: Pick pair of pointsPick pair of points Compute shortest pathCompute shortest path Compare place sequence to ground truth Compare place sequence to ground truth
using edit-distanceusing edit-distance
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
47
ConclusionsConclusions
►First steps toward object / place mapsFirst steps toward object / place maps
►CRFs provide powerful and flexible CRFs provide powerful and flexible framework for learning and inferenceframework for learning and inference
►Relational Markov networks provide Relational Markov networks provide language for reasoning about objects language for reasoning about objects and CRF structuresand CRF structures
SSS-06CRFs for Mapping Places and Objects
Dieter FoxUW Robotics & State Estimation Lab
48
Next StepsNext Steps
► Joint place labeling and object detectionJoint place labeling and object detection
► Combine low-level and high-level CRFsCombine low-level and high-level CRFs k-best style inference to find placesk-best style inference to find places Label objects conditioned on placesLabel objects conditioned on places Re-evaluate place hypothesesRe-evaluate place hypotheses
► Use visual featuresUse visual features► Joint feature and CRF learningJoint feature and CRF learning