Automatic Dense Semantic Mapping From Visual Street-level Imagery
|
|
- Amanda Stanley
- 5 years ago
- Views:
Transcription
1 Automatic Dense Semantic Mapping From Visual Street-level Imagery Sunando Sengupta [1], Paul Sturgess [1], Lubor Ladicky [2], Phillip H.S. Torr [1] [1] Oxford Brookes University [2] Visual Geometry Group, Oxford University 1
2 Dense Semantic Map Generate an overhead view of an urban region. Label every pixel in the Map View is associated with an object class label Pavement Car Pedestrian Bollard Shop Sign Sky Post 2 Vegetation Tree Signage Road Building Fence
3 Dense Semantic Map Street images captured inexpensively from vehicle with multiple mounted camera [1]. [1] Yotta. DCL, Yotta dcl case studies, Available: 3
4 Semantic Mapping Framework Street level Images acquisition Semantic mapping framework comprises of two stages 4
5 Semantic Mapping Framework Street level Images acquisition Image Segmentation Semantic mapping framework comprises of two stages Semantic Image Segmentation at street level. 5
6 Semantic Mapping Framework Street level Images acquisition Image Segmentation Semantic mapping framework comprises of two stages Semantic Image Segmentation at street level. Ground Plane Labelling at a global level. Ground plane labelling One of the first attempts to do dense overhead mapping from street level images. 6
7 Semantic Image Segmentation Label every pixel in the image with an object class Input Output Automatic Labeller Raw Image Labelled Image Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Object Class Labels Building Fence 7
8 Semantic Image Segmentation We use Conditional Random Field Framework (CRF) CRF construction Input Image X Final Segmentation 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. 8
9 Semantic Image Segmentation - CRF Total energy Optimal labelling given as 9 C c c c N j V i j i ij V i i i i x x x E ) ( ), ( ) ( ) (, x x E pix E pair E region
10 Semantic Image Segmentation - CRF Total energy E = E pix + E pair + E region E pix - Model individual pixel s cost of taking a label. Computed via the dense boosting approach Multi feature variant of texton boost [1] Car 0.2 Road 0.3 x [1] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr, Associative hierarchical crfs for object class image segmentation, in ICCV,
11 Semantic Image Segmentation - CRF Total energy E = E pix + E pair + E region E pair - Model each pixel neighbourhood interactions. Encourages label consistency in adjacent pixels Sensitive to edges in images. Contrast sensitive Potts model Car Road x i 0 g(i,j) Car Road x j E pair 11
12 Semantic Image Segmentation - CRF Total energy E = E pix + E pair + E region E region - Model behaviour of a group of pixels. Classify a region Encourages all the pixels in a region to take the same label. Group of pixels given by a multiple meanshift segmentations Car 0.3 Road 0.1 c 12
13 Semantic Image Segmentation Solved using alpha-expansion algorithm [1] Input Image Road Expansion Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence [1] Fast Approximate Energy Minimization via Graph Cuts. Yuri Boykov et al. ICCV 99 13
14 Semantic Image Segmentation Solved using alpha-expansion algorithm [1] Input Image Building Expansion Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence [1] Fast Approximate Energy Minimization via Graph Cuts. Yuri Boykov et al. ICCV 99 14
15 Semantic Image Segmentation Solved using alpha-expansion algorithm [1] Input Image Sky Expansion Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence [1] Fast Approximate Energy Minimization via Graph Cuts. Yuri Boykov et al. ICCV 99 15
16 Semantic Image Segmentation Solved using alpha-expansion algorithm [1] Input Image Pavement Expansion Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence [1] Fast Approximate Energy Minimization via Graph Cuts. Yuri Boykov et al. ICCV 99 16
17 Semantic Image Segmentation Solved using alpha-expansion algorithm [1] Input Image Final solution Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence [1] Fast Approximate Energy Minimization via Graph Cuts. Yuri Boykov et al. ICCV 99 17
18 Ground Plane Labelling Combine many labellings from street level imagery. Input Output Automatic Labeller Street Level labellings Labelled Ground Plane 18
19 Ground Plane CRF A CRF defined over the ground plane. Each ground plane pixel (zi) is a random variable taking a label from the label set. Energy for ground plane crf is E g ( Z) E g pix E g pair Z 19
20 Ground Plane Pixel Cost K X Z We assume a flat world. 20
21 Ground Plane Pixel Cost K X Z Homography Road Pavement Post/Pole A ground plane region is estimated. 21
22 Ground Plane Pixel Cost K X Z Homography Road Pavement Post/Pole Each point in the image projects to a unique point on the ground plane. Creating a homography 22
23 Ground Plane Pixel Cost K X Z Homography Road Pavement Post/Pole The image labelling is mapped to the ground plane via the homography. Ground plane Pixel histograms 23
24 Ground Plane Pixel Cost K X Z Homography Road Pavement Post/Pole Ground plane Pixel histograms Labels projected from many views are combined in a histogram. The normalised histogram gives the naïve probability of the ground plane pixel taking a label. 24
25 Ground Plane Pixel Cost K X Z Homography Road Pavement Post/Pole Ground plane Pixel histograms Labels projected from many views are combined in a histogram. The normalised histogram gives the naïve probability of the ground plane pixel taking a label. 25
26 Ground Plane labelling Histogram is built for every ground plane pixel giving E g pix Pairwise cost (E g pair) added to induce smoothness Contrast sensitive potts model Z
27 Ground Plane labelling Final CRF solution obtained using alpha expansion. Void
28 Ground Plane labelling Final CRF solution obtained using alpha expansion. Road expansion
29 Ground Plane labelling Final CRF solution obtained using alpha expansion. Building expansion
30 Ground Plane labelling Final CRF solution obtained using alpha expansion. Pavement expansion
31 Ground Plane labelling Final CRF solution obtained using alpha expansion. Car expansion
32 Ground Plane Labelling Final CRF solution obtained using alpha expansion. Final Solution
33 Dataset Subset of the images captured by the van 14.8 km of track, 8000 images from each camera. Pixel-level labelled ground truth images. Dataset available [1]. 13 object categories Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence Training - 44 images, testing - 42 images. [1] 33
34 SIS Results Input Semantic segmentation Ground Truth Pavement Car Pedestrian Bollard Shop Sign Sky Post Vegetation Tree Signage Road Building Fence Input Images, output of our image level CRF, ground truths. Used Automatic Labelling environment [1] [1] The Automatic Labelling Environment, L Ladicky, PHS Torr. Code available 34
35 Semantic Map Results Semantic map of Pembroke city 35
36 Ground plane Map Evaluation Street Images Back-projected Map results Ground Truth We back-project the ground plane map into image domain and evaluate the results. Global pixel accuracy of 82.9% 36
37 Results 37
38 Conclusions Presented a method to generate overhead view semantic mapping. Experiments on large tracks (~15km) which can be scaled up to country wide mapping Dataset available [1]. [1] 38
39 Future Work Perform a 3D street level semantic mapping and reconstruction. Add detailed street level information like information boards, traffic boards etc. Thank you!!! Oxford Brookes Vision group Oxford Brookes University 39
40
41 41
42 42
43 43
44 Ground Plane Pixel Cost K X Multi-view Z Homography Road Pavement Post/Pole Single view Using single view will create a shadow effect for objects violating flat world assumption and wrong label estimate 44
Combining Appearance and Structure from Motion Features for Road Scene Understanding
STURGESS et al.: COMBINING APPEARANCE AND SFM FEATURES 1 Combining Appearance and Structure from Motion Features for Road Scene Understanding Paul Sturgess paul.sturgess@brookes.ac.uk Karteek Alahari karteek.alahari@brookes.ac.uk
More informationSemantic Mapping of Road Scenes
Semantic Mapping of Road Scenes Sunando Sengupta Thesis submitted in partial fulfilment of the requirements of the award of Doctor of Philosophy Oxford Brookes University 2014 Abstract The problem of understanding
More informationRegion-based Segmentation and Object Detection
Region-based Segmentation and Object Detection Stephen Gould Tianshi Gao Daphne Koller Presented at NIPS 2009 Discussion and Slides by Eric Wang April 23, 2010 Outline Introduction Model Overview Model
More informationScalable Cascade Inference for Semantic Image Segmentation
STURGESS et al.: SCALABLE CASCADE INFERENCE 1 Scalable Cascade Inference for Semantic Image Segmentation Paul Sturgess 1 paul.sturgess@brookes.ac.uk L ubor Ladický 2 lubor@robots.ox.ac.uk Nigel Crook 1
More informationSegmentation. Bottom up Segmentation Semantic Segmentation
Segmentation Bottom up Segmentation Semantic Segmentation Semantic Labeling of Street Scenes Ground Truth Labels 11 classes, almost all occur simultaneously, large changes in viewpoint, scale sky, road,
More informationMulti-Class Image Labeling with Top-Down Segmentation and Generalized Robust P N Potentials
FLOROS ET AL.: MULTI-CLASS IMAGE LABELING WITH TOP-DOWN SEGMENTATIONS 1 Multi-Class Image Labeling with Top-Down Segmentation and Generalized Robust P N Potentials Georgios Floros 1 floros@umic.rwth-aachen.de
More informationMesh Based Semantic Modelling for Indoor and Outdoor Scenes
2013 IEEE Conference on Computer Vision and Pattern Recognition Mesh Based Semantic Modelling for Indoor and Outdoor Scenes Julien P. C. Valentin 1,3 Sunando Sengupta 1,3 Jonathan Warrell 1 Ali Shahrokni
More informationPOST PROCESSING VOTING TECHNIQUES FOR LOCAL STEREO MATCHING
STUDIA UNIV. BABEŞ BOLYAI, INFORMATICA, Volume LIX, Number 1, 2014 POST PROCESSING VOTING TECHNIQUES FOR LOCAL STEREO MATCHING ALINA MIRON Abstract. In this paper we propose two extensions to the Disparity
More informationGraph Cuts. Srikumar Ramalingam School of Computing University of Utah
Graph Cuts Srikumar Ramalingam School o Computing University o Utah Outline Introduction Pseudo-Boolean Functions Submodularity Max-low / Min-cut Algorithm Alpha-Expansion Segmentation Problem [Boykov
More informationAnalysis: TextonBoost and Semantic Texton Forests. Daniel Munoz Februrary 9, 2009
Analysis: TextonBoost and Semantic Texton Forests Daniel Munoz 16-721 Februrary 9, 2009 Papers [shotton-eccv-06] J. Shotton, J. Winn, C. Rother, A. Criminisi, TextonBoost: Joint Appearance, Shape and Context
More informationDecomposing a Scene into Geometric and Semantically Consistent Regions
Decomposing a Scene into Geometric and Semantically Consistent Regions Stephen Gould sgould@stanford.edu Richard Fulton rafulton@cs.stanford.edu Daphne Koller koller@cs.stanford.edu IEEE International
More informationJoint Semantic and Geometric Segmentation of Videos with a Stage Model
Joint Semantic and Geometric Segmentation of Videos with a Stage Model Buyu Liu ANU and NICTA Canberra, ACT, Australia buyu.liu@anu.edu.au Xuming He NICTA and ANU Canberra, ACT, Australia xuming.he@nicta.com.au
More informationGraph Cuts. Srikumar Ramalingam School of Computing University of Utah
Graph Cuts Srikumar Ramalingam School o Computing University o Utah Outline Introduction Pseudo-Boolean Functions Submodularity Max-low / Min-cut Algorithm Alpha-Expansion Segmentation Problem [Boykov
More informationJoint 2D-3D Temporally Consistent Semantic Segmentation of Street Scenes
Joint 2D-3D Temporally Consistent Semantic Segmentation of Street Scenes Georgios Floros and Bastian Leibe UMIC Research Centre RWTH Aachen University, Germany {floros,leibe}@umic.rwth-aachen.de Abstract
More informationAcquiring Semantics Induced Topology in Urban Environments
2012 IEEE International Conference on Robotics and Automation RiverCentre, Saint Paul, Minnesota, USA May 14-18, 2012 Acquiring Semantics Induced Topology in Urban Environments Gautam Singh and Jana Košecká
More informationNonparametric Semantic Segmentation for 3D Street Scenes
2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) November 3-7, 2013. Tokyo, Japan Nonparametric Semantic Segmentation for 3D Street Scenes Hu He and Ben Upcroft Abstract
More informationGeometric and Semantic 3D Reconstruction: Part 4A: Volumetric Semantic 3D Reconstruction. CVPR 2017 Tutorial Christian Häne UC Berkeley
Geometric and Semantic 3D Reconstruction: Part 4A: Volumetric Semantic 3D Reconstruction CVPR 2017 Tutorial Christian Häne UC Berkeley Dense Multi-View Reconstruction Goal: 3D Model from Images (Depth
More informationSimultaneous Multi-class Pixel Labeling over Coherent Image Sets
Simultaneous Multi-class Pixel Labeling over Coherent Image Sets Paul Rivera Research School of Computer Science Australian National University Canberra, ACT 0200 Stephen Gould Research School of Computer
More information2 OVERVIEW OF RELATED WORK
Utsushi SAKAI Jun OGATA This paper presents a pedestrian detection system based on the fusion of sensors for LIDAR and convolutional neural network based image classification. By using LIDAR our method
More informationLearning Depth-Sensitive Conditional Random Fields for Semantic Segmentation of RGB-D Images
Learning Depth-Sensitive Conditional Random Fields for Semantic Segmentation of RGB-D Images Andreas C. Müller and Sven Behnke Abstract We present a structured learning approach to semantic annotation
More informationDiscrete Optimization of Ray Potentials for Semantic 3D Reconstruction
Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction Marc Pollefeys Joined work with Nikolay Savinov, Christian Haene, Lubor Ladicky 2 Comparison to Volumetric Fusion Higher-order ray
More informationWhat have we leaned so far?
What have we leaned so far? Camera structure Eye structure Project 1: High Dynamic Range Imaging What have we learned so far? Image Filtering Image Warping Camera Projection Model Project 2: Panoramic
More informationSemantic Segmentation with Heterogeneous Sensor Coverages
Semantic Segmentation with Heterogeneous Sensor Coverages Cesar Cadena and Jana Košecká (a) (b) (c) (d) Fig. 1: Our novel semantic parsing approach can seamlessly integrate evidence from multiple sensors
More informationCS4495/6495 Introduction to Computer Vision. 3B-L3 Stereo correspondence
CS4495/6495 Introduction to Computer Vision 3B-L3 Stereo correspondence For now assume parallel image planes Assume parallel (co-planar) image planes Assume same focal lengths Assume epipolar lines are
More informationMarkov Networks in Computer Vision. Sargur Srihari
Markov Networks in Computer Vision Sargur srihari@cedar.buffalo.edu 1 Markov Networks for Computer Vision Important application area for MNs 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction
More informationUrban Scene Segmentation, Recognition and Remodeling. Part III. Jinglu Wang 11/24/2016 ACCV 2016 TUTORIAL
Part III Jinglu Wang Urban Scene Segmentation, Recognition and Remodeling 102 Outline Introduction Related work Approaches Conclusion and future work o o - - ) 11/7/16 103 Introduction Motivation Motivation
More informationSupplementary Material for: Road Detection using Convolutional Neural Networks
Supplementary Material for: Road Detection using Convolutional Neural Networks Aparajit Narayan 1, Elio Tuci 2, Frédéric Labrosse 1, Muhanad H. Mohammed Alkilabi 1 1 Aberystwyth University, 2 Middlesex
More informationTraining models for road scene understanding with automated ground truth Dan Levi
Training models for road scene understanding with automated ground truth Dan Levi With: Noa Garnett, Ethan Fetaya, Shai Silberstein, Rafi Cohen, Shaul Oron, Uri Verner, Ariel Ayash, Kobi Horn, Vlad Golder,
More informationWhat, Where & How Many? Combining Object Detectors and CRFs
What, Where & How Many? Combining Object Detectors and CRFs Lubor Ladicky, Paul Sturgess, Karteek Alahari, Chris Russell, and Philip H.S. Torr Oxford Brookes University http://cms.brookes.ac.uk/research/visiongroup
More informationHOG-based Pedestriant Detector Training
HOG-based Pedestriant Detector Training evs embedded Vision Systems Srl c/o Computer Science Park, Strada Le Grazie, 15 Verona- Italy http: // www. embeddedvisionsystems. it Abstract This paper describes
More informationProject 2 due today Project 3 out today. Readings Szeliski, Chapter 10 (through 10.5)
Announcements Stereo Project 2 due today Project 3 out today Single image stereogram, by Niklas Een Readings Szeliski, Chapter 10 (through 10.5) Public Library, Stereoscopic Looking Room, Chicago, by Phillips,
More informationCRF Based Point Cloud Segmentation Jonathan Nation
CRF Based Point Cloud Segmentation Jonathan Nation jsnation@stanford.edu 1. INTRODUCTION The goal of the project is to use the recently proposed fully connected conditional random field (CRF) model to
More informationScene Understanding From a Moving Camera for Object Detection and Free Space Estimation
Scene Understanding From a Moving Camera for Object Detection and Free Space Estimation Vladimir Haltakov, Heidrun Belzner and Slobodan Ilic Abstract Modern vehicles are equipped with multiple cameras
More informationBinocular stereo. Given a calibrated binocular stereo pair, fuse it to produce a depth image. Where does the depth information come from?
Binocular Stereo Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image Where does the depth information come from? Binocular stereo Given a calibrated binocular stereo
More informationMeasuring the World: Designing Robust Vehicle Localization for Autonomous Driving. Frank Schuster, Dr. Martin Haueis
Measuring the World: Designing Robust Vehicle Localization for Autonomous Driving Frank Schuster, Dr. Martin Haueis Agenda Motivation: Why measure the world for autonomous driving? Map Content: What do
More informationSemantic Motion Segmentation Using Dense CRF Formulation
Semantic Motion Segmentation Using Dense CRF Formulation N Dinesh Reddy Robotics Research Center IIIT Hyderabad, India Prateek Singhal Robotics Research Center IIIT Hyderabad, India K Madhava Krishna Robotics
More informationCS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep
CS395T paper review Indoor Segmentation and Support Inference from RGBD Images Chao Jia Sep 28 2012 Introduction What do we want -- Indoor scene parsing Segmentation and labeling Support relationships
More informationSemantic Video Segmentation From Occlusion Relations Within a Convex Optimization Framework
Semantic Video Segmentation From Occlusion Relations Within a Convex Optimization Framework Brian Taylor, Alper Ayvaci, Avinash Ravichandran, and Stefano Soatto University of California, Los Angeles Honda
More informationSegmentation Based Stereo. Michael Bleyer LVA Stereo Vision
Segmentation Based Stereo Michael Bleyer LVA Stereo Vision What happened last time? Once again, we have looked at our energy function: E ( D) = m( p, dp) + p I < p, q > We have investigated the matching
More informationConvex Optimization for Scene Understanding
Convex Optimization for Scene Understanding Mohamed Souiai 1, Claudia Nieuwenhuis 2, Evgeny Strekalovskiy 1 and Daniel Cremers 1 1 Technical University of Munich 2 UC Berkeley, ICSI, USA Abstract In this
More informationMarkov Networks in Computer Vision
Markov Networks in Computer Vision Sargur Srihari srihari@cedar.buffalo.edu 1 Markov Networks for Computer Vision Some applications: 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction
More informationPredicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus Presented by: Rex Ying and Charles Qi Input: A Single RGB Image Estimate
More informationExploiting Sparsity for Real Time Video Labelling
2013 IEEE International Conference on Computer Vision Workshops Exploiting Sparsity for Real Time Video Labelling Lachlan Horne, Jose M. Alvarez, and Nick Barnes College of Engineering and Computer Science,
More informationTurgay Senlet ALL RIGHTS RESERVED
2015 Turgay Senlet ALL RIGHTS RESERVED VISUAL LOCALIZATION, SEMANTIC VIDEO SEGMENTATION AND LABELING USING SATELLITE MAPS by TURGAY SENLET A Dissertation submitted to the Graduate School-New Brunswick
More informationEFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD
EFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD Weihao Li a, Michael Ying Yang a,b a TU Dresden, Computer Vision Lab Dresden, Dresden, Germany - weihao.li@mailbox.tu-dresden.de
More information3D Scene Understanding by Voxel-CRF
3D Scene Understanding by Voxel-CRF Byung-soo Kim University of Michigan bsookim@umich.edu Pushmeet Kohli Microsoft Research Cambridge pkohli@microsoft.com Silvio Savarese Stanford University ssilvio@stanford.edu
More informationComputer Vision at Cambridge: Reconstruction,Registration and Recognition
Computer Vision at Cambridge: Reconstruction,Registration and Recognition Roberto Cipolla Research team http://www.eng.cam.ac.uk/~cipolla/people.html Cognitive Systems Engineering Cognitive Systems Engineering
More informationSegmentation in electron microscopy images
Segmentation in electron microscopy images Aurelien Lucchi, Kevin Smith, Yunpeng Li Bohumil Maco, Graham Knott, Pascal Fua. http://cvlab.epfl.ch/research/medical/neurons/ Outline Automated Approach to
More informationLearning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009
Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer
More informationAdvanced point cloud processing
Advanced point cloud processing George Vosselman ITC Enschede, the Netherlands INTERNATIONAL INSTITUTE FOR GEO-INFORMATION SCIENCE AND EARTH OBSERVATION Laser scanning platforms Airborne systems mounted
More informationCS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching
Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix
More informationVisual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA
Visual Perception for Autonomous Driving on the NVIDIA DrivePX2 and using SYNTHIA Dr. Juan C. Moure Dr. Antonio Espinosa http://grupsderecerca.uab.cat/hpca4se/en/content/gpu http://adas.cvc.uab.es/elektra/
More informationSpatial Pattern Templates for Recognition of Objects with Regular Structure
Spatial Pattern Templates for Recognition of Objects with Regular Structure Radim Tyleček and Radim Šára Center for Machine Perception Czech Technical University in Prague Abstract. We propose a method
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely, Zhengqi Li Stereo Single image stereogram, by Niklas Een Mark Twain at Pool Table", no date, UCR Museum of Photography Stereo Given two images from different viewpoints
More informationConditional Random Fields as Recurrent Neural Networks
BIL722 - Deep Learning for Computer Vision Conditional Random Fields as Recurrent Neural Networks S. Zheng, S. Jayasumana, B. Romera-Paredes V. Vineet, Z. Su, D. Du, C. Huang, P.H.S. Torr Introduction
More informationContextual Classification with Functional Max-Margin Markov Networks
Contextual Classification with Functional Max-Margin Markov Networks Dan Munoz Nicolas Vandapel Drew Bagnell Martial Hebert Geometry Estimation (Hoiem et al.) Sky Problem 3-D Point Cloud Classification
More informationRobust Higher Order Potentials for Enforcing Label Consistency
Robust Higher Order Potentials for Enforcing Label Consistency Pushmeet Kohli Microsoft Research Cambridge pkohli@microsoft.com L ubor Ladický Philip H. S. Torr Oxford Brookes University lladicky,philiptorr}@brookes.ac.uk
More informationarxiv: v1 [cs.cv] 7 Jan 2017
Urban Scene Segmentation with Laser-Constrained CRFs Charika De Alvis Lionel Ott Fabio Ramos arxiv:1701.01892v1 [cs.cv] 7 Jan 2017 Abstract Robots typically possess sensors of different modalities, such
More informationSemantic 3D Occupancy Mapping through Efficient High Order CRFs
Semantic 3D Occupancy Mapping through Efficient High Order CRFs Shichao Yang, Yulan Huang and Sebastian Scherer Abstract Semantic 3D mapping can be used for many applications such as robot navigation and
More informationDiscrete Optimization Methods in Computer Vision CSE 6389 Slides by: Boykov Modified and Presented by: Mostafa Parchami Basic overview of graph cuts
Discrete Optimization Methods in Computer Vision CSE 6389 Slides by: Boykov Modified and Presented by: Mostafa Parchami Basic overview of graph cuts [Yuri Boykov, Olga Veksler, Ramin Zabih, Fast Approximation
More informationChapters 1 7: Overview
Chapters 1 7: Overview Photogrammetric mapping: introduction, applications, and tools GNSS/INS-assisted photogrammetric and LiDAR mapping LiDAR mapping: principles, applications, mathematical model, and
More informationSemantic Parsing of Street Scene Images Using 3D LiDAR Point Cloud
2013 IEEE International Conference on Computer Vision Workshops Semantic Parsing of Street Scene Images Using 3D LiDAR Point Cloud Pouria Babahajiani Tampere University of Technology Tampere, Finland pouria.babahajiani@tut.fi
More informationCollaborative Mapping with Streetlevel Images in the Wild. Yubin Kuang Co-founder and Computer Vision Lead
Collaborative Mapping with Streetlevel Images in the Wild Yubin Kuang Co-founder and Computer Vision Lead Mapillary Mapillary is a street-level imagery platform, powered by collaboration and computer vision.
More informationPulling Things out of Perspective
Pulling Things out of Perspective L ubor Ladický ETH Zürich, Switzerland lubor.ladicky@inf.ethz.ch Jianbo Shi University of Pennsylvania, USA jshi@seas.upenn.edu Marc Pollefeys ETH Zürich, Switzerland
More informationVehicle Dimensions Estimation Scheme Using AAM on Stereoscopic Video
Workshop on Vehicle Retrieval in Surveillance (VRS) in conjunction with 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance Vehicle Dimensions Estimation Scheme Using
More informationHarmony Potentials for Joint Classification and Segmentation
Harmony Potentials for Joint Classification and Segmentation Josep M. Gonfaus 1,2, Xavier Boix 1, Joost van de Weijer 1,2 Andrew D. Bagdanov 1 Joan Serrat 1,2 Jordi Gonzàlez 1,2 1 Centre de Visió per Computador
More informationSpatial Latent Dirichlet Allocation
Spatial Latent Dirichlet Allocation Xiaogang Wang and Eric Grimson Computer Science and Computer Science and Artificial Intelligence Lab Massachusetts Tnstitute of Technology, Cambridge, MA, 02139, USA
More informationSensor Fusion for Semantic Segmentation of Urban Scenes
2015 IEEE International Conference on Robotics and Automation (ICRA) Washington State Convention Center Seattle, Washington, May 26-30, 2015 Sensor Fusion for Semantic Segmentation of Urban Scenes Richard
More informationEFFICIENT ROAD MAPPING VIA INTERACTIVE IMAGE SEGMENTATION
In: Stilla U, Rottensteiner F, Paparoditis N (Eds) CMRT09. IAPRS, Vol. XXXVIII, Part 3/W4 --- Paris, France, 3-4 September, 2009 EFFICIENT ROAD MAPPING VIA INTERACTIVE IMAGE SEGMENTATION O. Barinova, R.
More informationScene Segmentation in Adverse Vision Conditions
Scene Segmentation in Adverse Vision Conditions Evgeny Levinkov Max Planck Institute for Informatics, Saarbrücken, Germany levinkov@mpi-inf.mpg.de Abstract. Semantic road labeling is a key component of
More informationMulti-view Stereo. Ivo Boyadzhiev CS7670: September 13, 2011
Multi-view Stereo Ivo Boyadzhiev CS7670: September 13, 2011 What is stereo vision? Generic problem formulation: given several images of the same object or scene, compute a representation of its 3D shape
More informationEvaluation of Different Methods for Using Colour Information in Global Stereo Matching Approaches
Evaluation of Different Methods for Using Colour Information in Global Stereo Matching Approaches Michael Bleyer 1, Sylvie Chambon 2, Uta Poppe 1 and Margrit Gelautz 1 1 Vienna University of Technology,
More informationUndirected Graphical Models. Raul Queiroz Feitosa
Undirected Graphical Models Raul Queiroz Feitosa Pros and Cons Advantages of UGMs over DGMs UGMs are more natural for some domains (e.g. context-dependent entities) Discriminative UGMs (CRF) are better
More informationA Hierarchical Conditional Random Field Model for Labeling and Segmenting Images of Street Scenes
A Hierarchical Conditional Random Field Model for Labeling and Segmenting Images of Street Scenes Qixing Huang Stanford University huangqx@stanford.edu Mei Han Google Inc. meihan@google.com Bo Wu Google
More informationLarge-Scale Traffic Sign Recognition based on Local Features and Color Segmentation
Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation M. Blauth, E. Kraft, F. Hirschenberger, M. Böhm Fraunhofer Institute for Industrial Mathematics, Fraunhofer-Platz 1,
More informationImage-Based Buildings and Facades
Image-Based Buildings and Facades Peter Wonka Associate Professor of Computer Science Arizona State University Daniel G. Aliaga Associate Professor of Computer Science Purdue University Challenge Generate
More informationEnergy Minimization for Segmentation in Computer Vision
S * = arg S min E(S) Energy Minimization for Segmentation in Computer Vision Meng Tang, Dmitrii Marin, Ismail Ben Ayed, Yuri Boykov Outline Clustering/segmentation methods K-means, GrabCut, Normalized
More informationAutomatic occlusion removal from facades for 3D urban reconstruction
Automatic occlusion removal from facades for 3D urban reconstruction C. Engels 1, D. Tingdahl 1, M. Vercruysse 1, T. Tuytelaars 1, H. Sahli 2, and L. Van Gool 1,3 1 K.U.Leuven, ESAT-PSI/IBBT 2 V.U.Brussel,
More informationStatic Scene Reconstruction
GPU supported Real-Time Scene Reconstruction with a Single Camera Jan-Michael Frahm, 3D Computer Vision group, University of North Carolina at Chapel Hill Static Scene Reconstruction 1 Capture on campus
More informationA robust stereo prior for human segmentation
A robust stereo prior for human segmentation Glenn Sheasby, Julien Valentin, Nigel Crook, Philip Torr Oxford Brookes University Abstract. The emergence of affordable depth cameras has enabled significant
More informationCar Detecting Method using high Resolution images
Car Detecting Method using high Resolution images Swapnil R. Dhawad Department of Electronics and Telecommunication Engineering JSPM s Rajarshi Shahu College of Engineering, Savitribai Phule Pune University,
More informationCS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching
Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix
More information2013 IEEE International Conference on Computer Vision. Exemplar Cut
2013 IEEE International Conference on Computer Vision Exemplar Cut Jimei Yang, Yi-Hsuan Tsai and Ming-Hsuan Yang University of California, Merced 5200 North Lake Road, Merced CA {jyang44, ytsai2, mhyang}@ucmerced.edu
More informationSemantic Segmentation of Street-Side Images
Semantic Segmentation of Street-Side Images Michal Recky 1, Franz Leberl 2 1 Institute for Computer Graphics and Vision Graz University of Technology recky@icg.tugraz.at 2 Institute for Computer Graphics
More informationCS 231A Computer Vision (Winter 2018) Problem Set 3
CS 231A Computer Vision (Winter 2018) Problem Set 3 Due: Feb 28, 2018 (11:59pm) 1 Space Carving (25 points) Dense 3D reconstruction is a difficult problem, as tackling it from the Structure from Motion
More informationMultiple View Geometry
Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric
More informationLearning Deep Structured Models for Semantic Segmentation. Guosheng Lin
Learning Deep Structured Models for Semantic Segmentation Guosheng Lin Semantic Segmentation Outline Exploring Context with Deep Structured Models Guosheng Lin, Chunhua Shen, Ian Reid, Anton van dan Hengel;
More informationStereo. 11/02/2012 CS129, Brown James Hays. Slides by Kristen Grauman
Stereo 11/02/2012 CS129, Brown James Hays Slides by Kristen Grauman Multiple views Multi-view geometry, matching, invariant features, stereo vision Lowe Hartley and Zisserman Why multiple views? Structure
More information4.1 Identification of Potential Water Ponding 4.2 Monitoring of Road Inventory 4.3 Monitoring of surface condition
TRIMM is supported by funding from the 7 th Framework Programme Call: SST.2011.5.2-2. Theme: Advanced and cost effective road infrastructure construction, management and maintenance Alex Wright 4.1 Identification
More informationA New Direction in GIS Data Collection or Why Are You Still in the Field?
GeoAutomation The Mobile Mapping System Survey-Enabled Imagery A New Direction in GIS Data Collection or Why Are You Still in the Field? Presentation to: URISA BC GIS Technology Showcase January 19, 2011
More informationStereo. Many slides adapted from Steve Seitz
Stereo Many slides adapted from Steve Seitz Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image image 1 image 2 Dense depth map Binocular stereo Given a calibrated
More informationAutomated Super-Voxel Based Features Classification of Urban Environments by Integrating 3D Point Cloud and Image Content
Automated Super-Voxel Based Features Classification of Urban Environments by Integrating 3D Point Cloud and Image Content Pouria Babahajiani #1, Lixin Fan *2, Joni Kamarainen #3, Moncef Gabbouj #4 # Department
More informationMobile Mapping and Navigation. Brad Kohlmeyer NAVTEQ Research
Mobile Mapping and Navigation Brad Kohlmeyer NAVTEQ Research Mobile Mapping & Navigation Markets Automotive Enterprise Internet & Wireless Mobile Devices 2 Local Knowledge & Presence Used to Create Most
More informationGRMC Global Resources Management Consultancy Inc.
GRMC Global Resources Management Consultancy Inc. Rail. Road. Infrastructure. Global Resources Management Consultancy USA 333 West 39th street, 2nd Floor, Suite 202, New York NY 10018 T: 212-564-2085 F:
More informationMulticlass Pixel Labeling with Non-Local Matching Constraints
Multiclass Pixel Labeling with Non-Local Matching Constraints Stephen Gould Research School of Computer Science Australian National University stephen.gould@anu.edu.au Abstract A popular approach to pixel
More informationLearning CRFs using Graph Cuts
Appears in European Conference on Computer Vision (ECCV) 2008 Learning CRFs using Graph Cuts Martin Szummer 1, Pushmeet Kohli 1, and Derek Hoiem 2 1 Microsoft Research, Cambridge CB3 0FB, United Kingdom
More informationSemantic Segmentation. Zhongang Qi
Semantic Segmentation Zhongang Qi qiz@oregonstate.edu Semantic Segmentation "Two men riding on a bike in front of a building on the road. And there is a car." Idea: recognizing, understanding what's in
More informationRecap from Previous Lecture
Recap from Previous Lecture Tone Mapping Preserve local contrast or detail at the expense of large scale contrast. Changing the brightness within objects or surfaces unequally leads to halos. We are now
More informationBackground Estimation for a Single Omnidirectional Image Sequence Captured with a Moving Camera
[DOI: 10.2197/ipsjtcva.6.68] Express Paper Background Estimation for a Single Omnidirectional Image Sequence Captured with a Moving Camera Norihiko Kawai 1,a) Naoya Inoue 1 Tomokazu Sato 1,b) Fumio Okura
More informationarxiv: v1 [cs.cv] 16 Mar 2018
The ApolloScape Dataset for Autonomous Driving Xinyu Huang, Xinjing Cheng, Qichuan Geng, Binbin Cao, Dingfu Zhou, Peng Wang, Yuanqing Lin, and Ruigang Yang arxiv:1803.06184v1 [cs.cv] 16 Mar 2018 Baidu
More information