SlideShare a Scribd company logo
1 of 27
Urban 3D Semantic Modelling
Using Stereo Vision
Sunando Sengupta1, Eric Greveson2, Ali
Shahrokni2, Philip HS Torr1
1Oxford Brookes Vision Group,
22d3 Sensing.
Urban 3D Semantic Modelling Road Scene
• Given a sequence of stereo images we generate a dense
3D, semantic model
Input Stereo image Sequence Dense 3D Semantic Model
• Stereo images
Pipeline –Semantic Reconstruction
• Depth map generation
• Camera estimation
Pipeline –Semantic Reconstruction
• Surface reconstruction
Pipeline –Semantic Reconstruction
• Semantic labelling of street view images
Pipeline –Semantic Reconstruction
• Semantic model generation
Pipeline –Semantic Reconstruction
Camera Estimation
• Feature tracking using left-right pair and consecutive
frames
Camera Estimation
• Use the feature tracks to
estimate camera poses.
• Use bundle adjustment
[a]Andreas Geiger et. Al. Are we ready for Autonomous Driving? The KITTI Vision Benchmark
Suite CVPR 2012
Depth-Map Estimation
• Semiglobal block matching[1] for disparity estimation
• Per-pixel depth computed as z = B x f / d
[1] H. Hirschmueller, Stereo Processing by Semi-Global Matching and Mutual Information. PAMI 2008.
B – Baseline
f - Focal Length
d – pixel disparity
Depth Fusion
• Depth estimates are fused
using camera poses.
• Fused into truncated signed
distance (TSDF) volumetric
representation[1].
[1] Brian Curless and Marc Levoy, A Volumetric Method for Building Complex Models from Range Images
Siggraph 96.
TSDF Volume[1]
• Entire space divided into grids of voxels.
• For each voxel compute the truncated signed distance.
– +ve increasing when it lies in the free space,
– -ve when it lies behind the surface
– zero when lies on the surface
• Performed for all depth maps.
[1] B. Curless et. al. A volumetric method for building complex models from range images.
TSDF Volume
-.8
Camera
Actual
surfaceTSDF volume
TSDF Volume
-1 -.8 -.3 .2 .8 1 1 1
-1 -.9 -.4 .1 .5 1 1 1
-1 -1 -.8 -.2 .1 1 1 1
-1 -1 -.9 -.3 .2 .8 1 1
-1 -1 -.9 -.4 .3 .9 1 1
-1 -1 -.8 -.3 .3 .9 1 1
-1 -1 -.9 -.5 .2 .8 1 1
-1 -1 -.6 .1 .7 1 1 1
Camera
TSDF volume
Actual
surface
Incremental Volume Update
• Road scenes are arbitrary
length long sequence.
• 3x3x1 volume of voxel grids
initialised
Incremental Volume Update
• Road scenes are arbitrary
length long sequence.
• 3x3x1 volume of voxel grids
initialised
• Incrementally add volume as
the vehicle moves out of the
region
CRF
construction
Semantic Image Segmentation
• We use conditional random field framework (CRF)
Final SegmentationInput Image
17
• Each pixel is a node in a grid graph G = (V,E).
• Each node is a random variable x taking a label from
label set.
X
[1] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr, “Associative hierarchical crfs for
object class image segmentation,” in ICCV, 2009.
Semantic Image Segmentation
• Total energy E = Epix + Epair + Eregion
• Epix - Model individual pixel’s cost of taking a label.
– Computed via the dense boosting approach
– Multi feature variant of texton boost[1]
x
Car 0.2
Road 0.3
18
[1] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr, “Associative hierarchical crfs for
object class image segmentation,” in ICCV, 2009.
Semantic Image Segmentation
• Total energy E = Epix + Epair + Eregion
• Epair- Model each pixels neighbourhood interaction.
– Encourages label consistency in
adjacent pixels and sensitive to edges.
– Contrast sensitive Potts model xi xj
Car
Road
0
g(i,j)
Car
Road
19
Epair
Semantic Image Segmentation
• Total energy E = Epix + Epair + Eregion
• Eregion - Model behaviour of a group of pixels.
– Encourages all the pixels in a region to take the same label.
– Group of pixels given by a
multiple meanshift segmentations
c
Car 0.3
Road 0.1
20
Semantic Image Segmentation - Results
• Input Images, output of our image level CRF, ground
truths.
Mesh Face Labelling
• A histogram of labels is
built for each mesh face
(Zf ), by projecting the
points from the face into
labelled images.
• Majority label is
considered as the label
of the face.
Semantic Model
Top: Left – Surface reconstruction, Right – Semantic model
Bottom: Left - input image, Right- object label set
Evaluation
• The Model is projected back using the estimated camera
poses to create labelled images.
• The points in the model far away from the camera are
ignored in the projection.
Evaluation
• Metrics
– Recall = tp/(tp+fn)
– Intersection vs Union = tp/(tp+fn+fp)
Video
Future Work
http://cms.brookes.ac.uk/research/visiongroup/projects
• Use semantic to build the structure.
• Realtime implementation.
• Combine image level information and geometric
contextual information.
Thank you!!!

More Related Content

What's hot

Build Your Own 3D Scanner: 3D Scanning with Structured Lighting
Build Your Own 3D Scanner: 3D Scanning with Structured LightingBuild Your Own 3D Scanner: 3D Scanning with Structured Lighting
Build Your Own 3D Scanner: 3D Scanning with Structured LightingDouglas Lanman
 
Build Your Own 3D Scanner: 3D Scanning with Swept-Planes
Build Your Own 3D Scanner: 3D Scanning with Swept-PlanesBuild Your Own 3D Scanner: 3D Scanning with Swept-Planes
Build Your Own 3D Scanner: 3D Scanning with Swept-PlanesDouglas Lanman
 
Visual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsVisual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsNAVER Engineering
 
Introductory Level of SLAM Seminar
Introductory Level of SLAM SeminarIntroductory Level of SLAM Seminar
Introductory Level of SLAM SeminarDong-Won Shin
 
Analysis of KinectFusion
Analysis of KinectFusionAnalysis of KinectFusion
Analysis of KinectFusionDong-Won Shin
 
Build Your Own 3D Scanner: The Mathematics of 3D Triangulation
Build Your Own 3D Scanner: The Mathematics of 3D TriangulationBuild Your Own 3D Scanner: The Mathematics of 3D Triangulation
Build Your Own 3D Scanner: The Mathematics of 3D TriangulationDouglas Lanman
 
LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...
LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...
LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...Minh Quan Nguyen
 
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...Sergio Orts-Escolano
 
FastCampus 2018 SLAM Workshop
FastCampus 2018 SLAM WorkshopFastCampus 2018 SLAM Workshop
FastCampus 2018 SLAM WorkshopDong-Won Shin
 
Survey on optical flow estimation with DL
Survey on optical flow estimation with DLSurvey on optical flow estimation with DL
Survey on optical flow estimation with DLLeapMind Inc
 
IAP (Invariant Attribute Profiles)
IAP (Invariant Attribute Profiles)IAP (Invariant Attribute Profiles)
IAP (Invariant Attribute Profiles)Naimur Rahman
 
Deep image retrieval - learning global representations for image search - ub ...
Deep image retrieval - learning global representations for image search - ub ...Deep image retrieval - learning global representations for image search - ub ...
Deep image retrieval - learning global representations for image search - ub ...Universitat de Barcelona
 
OpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developmentsOpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developmentsvirtualcitySYSTEMS GmbH
 
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalllAdvanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalllMuddassar Abbasi
 
Temporary Coherence 3D Animation
Temporary Coherence 3D AnimationTemporary Coherence 3D Animation
Temporary Coherence 3D AnimationAkshat Singh
 
Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...
Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...
Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...CSCJournals
 
Tracking Robustness and Green View Index Estimation of Augmented and Diminish...
Tracking Robustness and Green View Index Estimation of Augmented and Diminish...Tracking Robustness and Green View Index Estimation of Augmented and Diminish...
Tracking Robustness and Green View Index Estimation of Augmented and Diminish...Tomohiro Fukuda
 
Convolutional Patch Representations for Image Retrieval An unsupervised approach
Convolutional Patch Representations for Image Retrieval An unsupervised approachConvolutional Patch Representations for Image Retrieval An unsupervised approach
Convolutional Patch Representations for Image Retrieval An unsupervised approachUniversitat de Barcelona
 

What's hot (20)

Build Your Own 3D Scanner: 3D Scanning with Structured Lighting
Build Your Own 3D Scanner: 3D Scanning with Structured LightingBuild Your Own 3D Scanner: 3D Scanning with Structured Lighting
Build Your Own 3D Scanner: 3D Scanning with Structured Lighting
 
Build Your Own 3D Scanner: 3D Scanning with Swept-Planes
Build Your Own 3D Scanner: 3D Scanning with Swept-PlanesBuild Your Own 3D Scanner: 3D Scanning with Swept-Planes
Build Your Own 3D Scanner: 3D Scanning with Swept-Planes
 
Visual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environmentsVisual odometry & slam utilizing indoor structured environments
Visual odometry & slam utilizing indoor structured environments
 
Introductory Level of SLAM Seminar
Introductory Level of SLAM SeminarIntroductory Level of SLAM Seminar
Introductory Level of SLAM Seminar
 
Analysis of KinectFusion
Analysis of KinectFusionAnalysis of KinectFusion
Analysis of KinectFusion
 
Orb feature by nitin
Orb feature by nitinOrb feature by nitin
Orb feature by nitin
 
Kintinuous review
Kintinuous reviewKintinuous review
Kintinuous review
 
Build Your Own 3D Scanner: The Mathematics of 3D Triangulation
Build Your Own 3D Scanner: The Mathematics of 3D TriangulationBuild Your Own 3D Scanner: The Mathematics of 3D Triangulation
Build Your Own 3D Scanner: The Mathematics of 3D Triangulation
 
LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...
LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...
LocalizationandMappingforAutonomousNavigationin OutdoorTerrains: A StereoVisi...
 
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
A Three-Dimensional Representation method for Noisy Point Clouds based on Gro...
 
FastCampus 2018 SLAM Workshop
FastCampus 2018 SLAM WorkshopFastCampus 2018 SLAM Workshop
FastCampus 2018 SLAM Workshop
 
Survey on optical flow estimation with DL
Survey on optical flow estimation with DLSurvey on optical flow estimation with DL
Survey on optical flow estimation with DL
 
IAP (Invariant Attribute Profiles)
IAP (Invariant Attribute Profiles)IAP (Invariant Attribute Profiles)
IAP (Invariant Attribute Profiles)
 
Deep image retrieval - learning global representations for image search - ub ...
Deep image retrieval - learning global representations for image search - ub ...Deep image retrieval - learning global representations for image search - ub ...
Deep image retrieval - learning global representations for image search - ub ...
 
OpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developmentsOpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developments
 
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalllAdvanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
 
Temporary Coherence 3D Animation
Temporary Coherence 3D AnimationTemporary Coherence 3D Animation
Temporary Coherence 3D Animation
 
Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...
Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...
Interferogram Filtering Using Gaussians Scale Mixtures in Steerable Wavelet D...
 
Tracking Robustness and Green View Index Estimation of Augmented and Diminish...
Tracking Robustness and Green View Index Estimation of Augmented and Diminish...Tracking Robustness and Green View Index Estimation of Augmented and Diminish...
Tracking Robustness and Green View Index Estimation of Augmented and Diminish...
 
Convolutional Patch Representations for Image Retrieval An unsupervised approach
Convolutional Patch Representations for Image Retrieval An unsupervised approachConvolutional Patch Representations for Image Retrieval An unsupervised approach
Convolutional Patch Representations for Image Retrieval An unsupervised approach
 

Similar to Urban 3D Semantic Modelling Using Stereo Vision

Fisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingFisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingYu Huang
 
Fisheye Omnidirectional View in Autonomous Driving II
Fisheye Omnidirectional View in Autonomous Driving IIFisheye Omnidirectional View in Autonomous Driving II
Fisheye Omnidirectional View in Autonomous Driving IIYu Huang
 
BEV Semantic Segmentation
BEV Semantic SegmentationBEV Semantic Segmentation
BEV Semantic SegmentationYu Huang
 
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation FieldsCVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation FieldsJun Saito
 
Carved visual hulls for image based modeling
Carved visual hulls for image based modelingCarved visual hulls for image based modeling
Carved visual hulls for image based modelingaftab alam
 
Depth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors IIDepth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors IIYu Huang
 
Deep Local Parametric Filters for Image Enhancement
Deep Local Parametric Filters for Image EnhancementDeep Local Parametric Filters for Image Enhancement
Deep Local Parametric Filters for Image EnhancementSean Moran
 
Introduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer VisionIntroduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer Visionothersk46
 
NetVLAD: CNN architecture for weakly supervised place recognition
NetVLAD:  CNN architecture for weakly supervised place recognitionNetVLAD:  CNN architecture for weakly supervised place recognition
NetVLAD: CNN architecture for weakly supervised place recognitionGeunhee Cho
 
Texture_Mapping_RGB-D_Sensor_Survey.pptx
Texture_Mapping_RGB-D_Sensor_Survey.pptxTexture_Mapping_RGB-D_Sensor_Survey.pptx
Texture_Mapping_RGB-D_Sensor_Survey.pptxssuser906a0e
 
Lec13 stereo converted
Lec13 stereo convertedLec13 stereo converted
Lec13 stereo convertedBaliThorat1
 
Miniproject final group 14
Miniproject final group 14Miniproject final group 14
Miniproject final group 14Ashish Mundhra
 
Automated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceAutomated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceLiza Charalambous
 
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...mustafa sarac
 
Passive stereo vision with deep learning
Passive stereo vision with deep learningPassive stereo vision with deep learning
Passive stereo vision with deep learningYu Huang
 
Sergey A. Sukhanov, "3D content production"
Sergey A. Sukhanov, "3D content production"Sergey A. Sukhanov, "3D content production"
Sergey A. Sukhanov, "3D content production"Mikhail Vink
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial ImagesKoshy Geoji
 
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...ijma
 

Similar to Urban 3D Semantic Modelling Using Stereo Vision (20)

Fisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingFisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous Driving
 
Fisheye Omnidirectional View in Autonomous Driving II
Fisheye Omnidirectional View in Autonomous Driving IIFisheye Omnidirectional View in Autonomous Driving II
Fisheye Omnidirectional View in Autonomous Driving II
 
BEV Semantic Segmentation
BEV Semantic SegmentationBEV Semantic Segmentation
BEV Semantic Segmentation
 
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation FieldsCVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
CVPR 2012 Review Seminar - Multi-View Hair Capture using Orientation Fields
 
Carved visual hulls for image based modeling
Carved visual hulls for image based modelingCarved visual hulls for image based modeling
Carved visual hulls for image based modeling
 
Depth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors IIDepth Fusion from RGB and Depth Sensors II
Depth Fusion from RGB and Depth Sensors II
 
Deep Local Parametric Filters for Image Enhancement
Deep Local Parametric Filters for Image EnhancementDeep Local Parametric Filters for Image Enhancement
Deep Local Parametric Filters for Image Enhancement
 
Tele immersion
Tele immersionTele immersion
Tele immersion
 
Introduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer VisionIntroduction to Binocular Stereo in Computer Vision
Introduction to Binocular Stereo in Computer Vision
 
NetVLAD: CNN architecture for weakly supervised place recognition
NetVLAD:  CNN architecture for weakly supervised place recognitionNetVLAD:  CNN architecture for weakly supervised place recognition
NetVLAD: CNN architecture for weakly supervised place recognition
 
Texture_Mapping_RGB-D_Sensor_Survey.pptx
Texture_Mapping_RGB-D_Sensor_Survey.pptxTexture_Mapping_RGB-D_Sensor_Survey.pptx
Texture_Mapping_RGB-D_Sensor_Survey.pptx
 
Lec13 stereo converted
Lec13 stereo convertedLec13 stereo converted
Lec13 stereo converted
 
Miniproject final group 14
Miniproject final group 14Miniproject final group 14
Miniproject final group 14
 
Automated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceAutomated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillance
 
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...Lecture 01   frank dellaert - 3 d reconstruction and mapping: a factor graph ...
Lecture 01 frank dellaert - 3 d reconstruction and mapping: a factor graph ...
 
Passive stereo vision with deep learning
Passive stereo vision with deep learningPassive stereo vision with deep learning
Passive stereo vision with deep learning
 
Sergey A. Sukhanov, "3D content production"
Sergey A. Sukhanov, "3D content production"Sergey A. Sukhanov, "3D content production"
Sergey A. Sukhanov, "3D content production"
 
Digital Image Fundamentals - II
Digital Image Fundamentals - IIDigital Image Fundamentals - II
Digital Image Fundamentals - II
 
Vehicle detection in Aerial Images
Vehicle detection in Aerial ImagesVehicle detection in Aerial Images
Vehicle detection in Aerial Images
 
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...
 

Recently uploaded

Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
G9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptG9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptMAESTRELLAMesa2
 
Work, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE PhysicsWork, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE Physicsvishikhakeshava1
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )aarthirajkumar25
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Cultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptxCultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptxpradhanghanshyam7136
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTSérgio Sacani
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhousejana861314
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCEPRINCE C P
 
Types of different blotting techniques.pptx
Types of different blotting techniques.pptxTypes of different blotting techniques.pptx
Types of different blotting techniques.pptxkhadijarafiq2012
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 

Recently uploaded (20)

Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
G9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptG9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.ppt
 
Work, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE PhysicsWork, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE Physics
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Cultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptxCultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptx
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOST
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhouse
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
 
Types of different blotting techniques.pptx
Types of different blotting techniques.pptxTypes of different blotting techniques.pptx
Types of different blotting techniques.pptx
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Engler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomyEngler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomy
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 

Urban 3D Semantic Modelling Using Stereo Vision

  • 1. Urban 3D Semantic Modelling Using Stereo Vision Sunando Sengupta1, Eric Greveson2, Ali Shahrokni2, Philip HS Torr1 1Oxford Brookes Vision Group, 22d3 Sensing.
  • 2. Urban 3D Semantic Modelling Road Scene • Given a sequence of stereo images we generate a dense 3D, semantic model Input Stereo image Sequence Dense 3D Semantic Model
  • 3. • Stereo images Pipeline –Semantic Reconstruction
  • 4. • Depth map generation • Camera estimation Pipeline –Semantic Reconstruction
  • 5. • Surface reconstruction Pipeline –Semantic Reconstruction
  • 6. • Semantic labelling of street view images Pipeline –Semantic Reconstruction
  • 7. • Semantic model generation Pipeline –Semantic Reconstruction
  • 8. Camera Estimation • Feature tracking using left-right pair and consecutive frames
  • 9. Camera Estimation • Use the feature tracks to estimate camera poses. • Use bundle adjustment [a]Andreas Geiger et. Al. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite CVPR 2012
  • 10. Depth-Map Estimation • Semiglobal block matching[1] for disparity estimation • Per-pixel depth computed as z = B x f / d [1] H. Hirschmueller, Stereo Processing by Semi-Global Matching and Mutual Information. PAMI 2008. B – Baseline f - Focal Length d – pixel disparity
  • 11. Depth Fusion • Depth estimates are fused using camera poses. • Fused into truncated signed distance (TSDF) volumetric representation[1]. [1] Brian Curless and Marc Levoy, A Volumetric Method for Building Complex Models from Range Images Siggraph 96.
  • 12. TSDF Volume[1] • Entire space divided into grids of voxels. • For each voxel compute the truncated signed distance. – +ve increasing when it lies in the free space, – -ve when it lies behind the surface – zero when lies on the surface • Performed for all depth maps. [1] B. Curless et. al. A volumetric method for building complex models from range images.
  • 14. TSDF Volume -1 -.8 -.3 .2 .8 1 1 1 -1 -.9 -.4 .1 .5 1 1 1 -1 -1 -.8 -.2 .1 1 1 1 -1 -1 -.9 -.3 .2 .8 1 1 -1 -1 -.9 -.4 .3 .9 1 1 -1 -1 -.8 -.3 .3 .9 1 1 -1 -1 -.9 -.5 .2 .8 1 1 -1 -1 -.6 .1 .7 1 1 1 Camera TSDF volume Actual surface
  • 15. Incremental Volume Update • Road scenes are arbitrary length long sequence. • 3x3x1 volume of voxel grids initialised
  • 16. Incremental Volume Update • Road scenes are arbitrary length long sequence. • 3x3x1 volume of voxel grids initialised • Incrementally add volume as the vehicle moves out of the region
  • 17. CRF construction Semantic Image Segmentation • We use conditional random field framework (CRF) Final SegmentationInput Image 17 • Each pixel is a node in a grid graph G = (V,E). • Each node is a random variable x taking a label from label set. X [1] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr, “Associative hierarchical crfs for object class image segmentation,” in ICCV, 2009.
  • 18. Semantic Image Segmentation • Total energy E = Epix + Epair + Eregion • Epix - Model individual pixel’s cost of taking a label. – Computed via the dense boosting approach – Multi feature variant of texton boost[1] x Car 0.2 Road 0.3 18 [1] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr, “Associative hierarchical crfs for object class image segmentation,” in ICCV, 2009.
  • 19. Semantic Image Segmentation • Total energy E = Epix + Epair + Eregion • Epair- Model each pixels neighbourhood interaction. – Encourages label consistency in adjacent pixels and sensitive to edges. – Contrast sensitive Potts model xi xj Car Road 0 g(i,j) Car Road 19 Epair
  • 20. Semantic Image Segmentation • Total energy E = Epix + Epair + Eregion • Eregion - Model behaviour of a group of pixels. – Encourages all the pixels in a region to take the same label. – Group of pixels given by a multiple meanshift segmentations c Car 0.3 Road 0.1 20
  • 21. Semantic Image Segmentation - Results • Input Images, output of our image level CRF, ground truths.
  • 22. Mesh Face Labelling • A histogram of labels is built for each mesh face (Zf ), by projecting the points from the face into labelled images. • Majority label is considered as the label of the face.
  • 23. Semantic Model Top: Left – Surface reconstruction, Right – Semantic model Bottom: Left - input image, Right- object label set
  • 24. Evaluation • The Model is projected back using the estimated camera poses to create labelled images. • The points in the model far away from the camera are ignored in the projection.
  • 25. Evaluation • Metrics – Recall = tp/(tp+fn) – Intersection vs Union = tp/(tp+fn+fp)
  • 26. Video
  • 27. Future Work http://cms.brookes.ac.uk/research/visiongroup/projects • Use semantic to build the structure. • Realtime implementation. • Combine image level information and geometric contextual information. Thank you!!!

Editor's Notes

  1. In this work we attempt to create a semantic model of a road scene. We perform a dense 3D reconstruction and associate semantic meaning to the model. Such a reconstruction is particularly useful for intelligent/autonomous navigation where the system needs to recreate the environment in which it resides and also recognise the objects present there. In our case, we perform modelling of a road scene, where each voxel in the reconstructed model is labeled with class labels like car, road, pavement, building. The input to our system is a sequence of stereo images., while the right side shows our desired output.
  2. The camera pose estimation has two main steps, namely feature matching and bundle adjustment We consider feature matches satifying both the left-right frames and the consecutive fames (stereo and ego-motion), estimate the camera pose. This helps the bundle adjuster to estimate the camera poses and feature points more accurately. In the bundle adjustment phase, our optimiser estimates camera poses and the associated features viewed by the last n cameras (20).
  3. This is an example of hte feature and carea pose estimation. The figure shows the camera centres and 3D points, registered manually to the Google map.
  4. For generating the surface, we first estimate the depth maps from stereo pairs. These are merged into a the Truncated Signed Distance (TSDF) volume using the estimated camera poses. Finally a mesh iscreated using marching tetrahedra algorithm
  5. For each of hte depth estimate we get from the stereo image pairs in merged into the volume. The tsdf volume building works as follows. Entire space is divided into grid of voxels. Distance is measured for each voxel from the surface. The distance is zero at the surface. Positive and increasing in the free space towards the camera, negative and decreasing for the voxels that lie inside. The distance measure is truncated at some value. This is done for each depth maps. Finally the the voxel with zero estimates lie on the surface.
  6. A simple example, of how the tsdf volume is build. Each estimate of the depth update the voxels.
  7. The zeros give the surface.
  8. As we are reconstructing road scenes which can run from hundreds of meters to kilometer, we use an online grid update method We consider an active 3x3x1 grid of voxel volumes at any time of the fusion. As the vehicle track goes out of the range of current grid, the current grid blocks are written to memory and a new grid is initialised.
  9. We use Conditional Random field (CRF). This has achieved state of the art results in classification of road scene data in recent years. In this framework,. The image is described as a grid graph. All the pixels in the image are the vertices of the graph. each pixel is modelled as a variable which takes a value from the label set which we need to find out.
  10. We now define each of the energy component in details. Epix models the individual pixels cost of taking a label. Generally this is the classifier cost. In our case it is computed via the boosting approach. This is shown in the example, the green node has the cost of taking the label car.2 and road 0.1. similarly all the cost of other nodes are also computed.
  11. The next cost item is the pairwise cost which models the pixel neighbourhood region. This kind of cost will try to enforce the consistency in label among adjacent pixels. Thus it is Sensitive to edges and preserves boundaries in images. Here in this example you can see the cost of two pixels taking the same label car is zero but non zero otherwise.
  12. The final cost terms models the behaviour of the group of the pixels defining a region. Here the region is found by unsupervised segmentetiontion technique like meanshift, and encourages the entire region to be classified into a same class label. In this example the entire clique will take a cost for an object label.
  13. These are some of hte street level details
  14. For each of the mesh face in the reconstructed model, we sample a certain number of points on the face. These face points are projected into the labeled images and a label histogram is built for each of hte mesh face. Majority label is associated as the label of that particular mesh face.
  15. As generating ground truth 3d models is quite expensive, to evaluate the model, we project the mesh labels into the image domain and compare with the ground truth.
  16. We evaluate our model on both recall and intersection-union metrics.
  17. This is the result video of our system. We use the stereo images from KITTI dataset. Use semi-global block mathcing stereo to obtain the disparity maps. The depth estimated from the disparity maps are fused into the volume usinga tsdf. The street image s are labelled in a crf framework and finally a labelled dense 3D reconstruciton is obtained. We try our method on large scale upto a kilometer. The inset image is hte google earth mage of the corresponding vehice track overlaid on the gmap image.
  18. Thank you.