Learning for Active 3D Mapping
|
|
- Elaine Audrey Hall
- 6 years ago
- Views:
Transcription
1 Learning for Active 3D Mapping Karel Zimmermann, Tomáš Petříček, Vojtěch Šalanský, Tomáš Svoboda ICCV 2017 Vision for Robotics and Autonomous Systems Center for Machine Perception Department for cybernetics Faculty of Electrical Engineering
2 Motivation Motivation: New Solid State Lidars will allow independent steering of depth-measuring rays S3 principle Emitted laser beams Transmitted through Optical Phased Array Controlling optical properties of OPA elements, allows to steer laser beams in desired directions Reflected laser beams are captured by SPAD array Images of S3 Lidar redistributed with permission of Quanergy Systems (
3 Problem definition 1. Learn to reconstruct dense 3D voxel map from sparse depth measurements
4 Problem definition 1. Learn to reconstruct dense 3D voxel map from sparse depth measurements 2. Optimize reactive control of depth-measuring rays along an expected vehicle trajectory Images of S3 Lidar redistributed with permission of Quanergy Systems (
5 Overview of active 3D mapping Learning of 3D mapping network. M(x ) x y(x, ) M(x )
6 Overview of active 3D mapping Learning of 3D mapping network. M (x ) Planning of depth measuring rays... J( ) y(x, ) x M (x ) J( )
7 Overview of active 3D mapping Learning of 3D mapping network. M (x ) Planning of depth measuring rays... J( ) SSL provides following sparse measurement x( ) y(x( ), ) x( ) M (x ) J( )
8 Learning & Planning minimize common objective X arg min L(, ) voxels y(x( ), ) x( ) M (x ) J( )
9 Learning & Planning minimize common objective X y arg min L(, ) voxels y(x( ), ) x( ) M (x ) J( )
10 Learning & Planning minimize common objective X arg min L(y(x( ), ), y ) subject to J` ( ) K voxels y(x( ), ) x( ) M (x ) J( )
11 Learning as minimization over X arg min L(y(x( ), ), y ) subject to J` ( ) K voxels Result of planning is not differentiable y(x( ), ) x( ) M (x ) J( )
12 0 Locally approximate objective around X 0 arg min L(y(x( ), ), y ) subject to J` ( 0 ) K voxels 0 y(x( ), ) x( 0 ) M (x ) J( 0 )
13 1 = Minimize approximated objective to get 1 arg min X voxels L(y(x( 0 ), ), y ) 0 SGD 1
14 Minimize approximated objective to get 1 arg min X voxels L(y(x( 1 ), ), y ) 0 SGD 1
15 2 = Minimize approximated objective to get 1 arg min 1 SGD X voxels 0 2 L(y(x( 1 ), ), y )
16 Iteratively optimize approximated objective t+1 = arg min X voxels L(y(x( t ), ), y ) t t+1 Fix point of this mapping would assure: local optimality of the objective statistical consistency of the learning In practise, we iterate until validation error stops decreasing
17 Planning of depth measuring rays J No ground truth y available online Objective for planning is approximated y(x( ), ) x( ) M (x ) J
18 Planning of depth measuring rays J No ground truth y available online Objective for planning is approximated from current map y voxel i
19 Planning of depth measuring rays J No ground truth y available online Objective for planning is approximated from current map y voxel i 1 (y) (y) occupied unoccupied
20 Planning of depth measuring rays J No ground truth y available online Objective for planning is approximated from current map y i = H current loss in voxel i voxel i
21 Planning of depth measuring rays J No ground truth y available online Objective for planning is approximated from current map y i = H current loss in voxel i voxel i rays J Y j2j p ij prob. that voxel i is not visible by any ray j 2 J Total expected loss: X voxels i Y j2j p ij
22 Planning of depth measuring rays J No ground truth y available online Objective for planning is approximated from current map y i = H current loss in voxel i voxel i rays J Y j2j p ij prob. that voxel i is not visible by any ray j 2 J Total expected loss: X voxels i Y j2j p ij
23 Planning of depth measuring rays J Planning of J = {J 1...J L } over horizon L (i.e. for following positions ` =1...L): X Y arg min i p ij subject to J` apple K J voxels j2j Convex approximations Naive greedy algorithm Prioritized greedy algorithm Upper bound on the approximation ratio of prioritized greedy proposed optimal UB 30% optimal coverage 50%
24 Experiment: Structure of 3D mapping network 2 R 20M
25 Experiment: Setting Steerable SSL is not yet avaiable Simulation of SSL on Kitti dataset.
26 apping Figure 4. Recall to false-positive rate on test data for network h0 (Random) and h4 (Coupled). False positives which can be attributed to discretization error (in 1-voxel distance to occupied voxels) do not count. Experiment: Qualitative evaluation Note: Detailed quantitative evaluation in poster and paper iment, we used 17 and 3 sequences from category for training and validation, respecquences from the City category for testing. lternating procedure of learning and pland above (see Sec. 3 5), we learned mapping 1,..., ht using batch size 1 and momentum ng rate always started at = Trainetwork h0 took iterations and twice learning rate, to 10 4 after iteraafter iterations. Training the succest took iterations (approximately one entially decreasing learning rate to ved that the net ht achieve best results al4 planning-training iterations. n from the ROC curves in Fig. 4, the perforplanning-training iterations overcomes netlanning. When we have evaluate network g for new input, ROC curve was almost infrom the one generated by h0 with random Sparse measurements trees cars Reconstructed map network xl contains around 2.5% of known f the voxels are estimated by the CNN. ROC ction are computed using global confidence nd truth map y. An examples from reconown in Fig. 5. Czech Technical University in Prague Figure 5. Two examples of global map reconstruction. The black son to a Recurrent Faculty Image-based Ar- Engineering, of Electrical of car. Cybernetics line denotes Department trajectory of the Top row: The measurement Ground truth
27 Experiment: Summary & Questions [1] Zimmermann, Petricek, Salansky, Svoboda, Learning for Active 3D Mapping, ICCV,
Multi-View 3D Object Detection Network for Autonomous Driving
Multi-View 3D Object Detection Network for Autonomous Driving Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia CVPR 2017 (Spotlight) Presented By: Jason Ku Overview Motivation Dataset Network Architecture
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 informationMultiview 3D tracking with an Incrementally. Constructed 3D model
Multiview 3D tracking with an Incrementally Tomáš Svoboda with Karel Zimmermann and Petr Doubek svoboda@cmp.felk.cvut.cz Czech Technical University Prague, Center for Machine Perception http://cmp.felk.cvut.cz
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 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 informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha
More informationObject Detection. CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR
Object Detection CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR Problem Description Arguably the most important part of perception Long term goals for object recognition: Generalization
More informationarxiv: v1 [cs.cv] 20 Dec 2016
End-to-End Pedestrian Collision Warning System based on a Convolutional Neural Network with Semantic Segmentation arxiv:1612.06558v1 [cs.cv] 20 Dec 2016 Heechul Jung heechul@dgist.ac.kr Min-Kook Choi mkchoi@dgist.ac.kr
More informationPara-catadioptric Camera Auto Calibration from Epipolar Geometry
Para-catadioptric Camera Auto Calibration from Epipolar Geometry Branislav Mičušík and Tomáš Pajdla Center for Machine Perception http://cmp.felk.cvut.cz Department of Cybernetics Faculty of Electrical
More informationCalibration of a rotating multi-beam Lidar
The 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems October 18-22, 2010, Taipei, Taiwan Calibration of a rotating multi-beam Lidar Naveed Muhammad 1,2 and Simon Lacroix 1,2 Abstract
More informationEvaluating optical flow vectors through collision points of object trajectories in varying computergenerated snow intensities for autonomous vehicles
Eingebettete Systeme Evaluating optical flow vectors through collision points of object trajectories in varying computergenerated snow intensities for autonomous vehicles 25/6/2018, Vikas Agrawal, Marcel
More informationMachine learning based automatic extrinsic calibration of an onboard monocular camera for driving assistance applications on smart mobile devices
Technical University of Cluj-Napoca Image Processing and Pattern Recognition Research Center www.cv.utcluj.ro Machine learning based automatic extrinsic calibration of an onboard monocular camera for driving
More informationW4. Perception & Situation Awareness & Decision making
W4. Perception & Situation Awareness & Decision making Robot Perception for Dynamic environments: Outline & DP-Grids concept Dynamic Probabilistic Grids Bayesian Occupancy Filter concept Dynamic Probabilistic
More informationRECOVERY OF PARTIALLY OBSERVED DATA APPEARING IN CLUSTERS. Sunrita Poddar, Mathews Jacob
RECOVERY OF PARTIALLY OBSERVED DATA APPEARING IN CLUSTERS Sunrita Poddar, Mathews Jacob Department of Electrical and Computer Engineering The University of Iowa, IA, USA ABSTRACT We propose a matrix completion
More informationJoint Vanishing Point Extraction and Tracking (Supplementary Material)
Joint Vanishing Point Extraction and Tracking (Supplementary Material) Till Kroeger1 1 Dengxin Dai1 Luc Van Gool1,2 Computer Vision Laboratory, D-ITET, ETH Zurich 2 VISICS, ESAT/PSI, KU Leuven {kroegert,
More informationSingle-Shot Refinement Neural Network for Object Detection -Supplementary Material-
Single-Shot Refinement Neural Network for Object Detection -Supplementary Material- Shifeng Zhang 1,2, Longyin Wen 3, Xiao Bian 3, Zhen Lei 1,2, Stan Z. Li 4,1,2 1 CBSR & NLPR, Institute of Automation,
More informationSupporting Information
Supporting Information Ullman et al. 10.1073/pnas.1513198113 SI Methods Training Models on Full-Object Images. The human average MIRC recall was 0.81, and the sub-mirc recall was 0.10. The models average
More informationWhy the Self-Driving Revolution Hinges on one Enabling Technology: LiDAR
Why the Self-Driving Revolution Hinges on one Enabling Technology: LiDAR Markus Prison Director Business Development Europe Quanergy ID: 23328 Who We Are The leader in LiDAR (laser-based 3D spatial sensor)
More informationStereo Vision A simple system. Dr. Gerhard Roth Winter 2012
Stereo Vision A simple system Dr. Gerhard Roth Winter 2012 Stereo Stereo Ability to infer information on the 3-D structure and distance of a scene from two or more images taken from different viewpoints
More informationAerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments. Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno
Aerial Robotic Autonomous Exploration & Mapping in Degraded Visual Environments Kostas Alexis Autonomous Robots Lab, University of Nevada, Reno Motivation Aerial robotic operation in GPS-denied Degraded
More informationRegionlet Object Detector with Hand-crafted and CNN Feature
Regionlet Object Detector with Hand-crafted and CNN Feature Xiaoyu Wang Research Xiaoyu Wang Research Ming Yang Horizon Robotics Shenghuo Zhu Alibaba Group Yuanqing Lin Baidu Overview of this section Regionlet
More information/10/$ IEEE 4048
21 IEEE International onference on Robotics and Automation Anchorage onvention District May 3-8, 21, Anchorage, Alaska, USA 978-1-4244-54-4/1/$26. 21 IEEE 448 Fig. 2: Example keyframes of the teabox object.
More informationStereoScan: Dense 3D Reconstruction in Real-time
STANFORD UNIVERSITY, COMPUTER SCIENCE, STANFORD CS231A SPRING 2016 StereoScan: Dense 3D Reconstruction in Real-time Peirong Ji, pji@stanford.edu June 7, 2016 1 INTRODUCTION In this project, I am trying
More informationDynamic Routing Between Capsules
Report Explainable Machine Learning Dynamic Routing Between Capsules Author: Michael Dorkenwald Supervisor: Dr. Ullrich Köthe 28. Juni 2018 Inhaltsverzeichnis 1 Introduction 2 2 Motivation 2 3 CapusleNet
More informationProbabilistic Surfel Fusion for Dense LiDAR Mapping Chanoh Park, Soohwan Kim, Peyman Moghadam, Clinton Fookes, Sridha Sridharan
Probabilistic Surfel Fusion for Dense LiDAR Mapping Chanoh Park, Soohwan Kim, Peyman Moghadam, Clinton Fookes, Sridha Sridharan ICCV workshop 2017 www.data61.csiro.au Introduction Narrow FoV Short sensing
More informationFinding Tiny Faces Supplementary Materials
Finding Tiny Faces Supplementary Materials Peiyun Hu, Deva Ramanan Robotics Institute Carnegie Mellon University {peiyunh,deva}@cs.cmu.edu 1. Error analysis Quantitative analysis We plot the distribution
More informationTracking in image sequences
CENTER FOR MACHINE PERCEPTION CZECH TECHNICAL UNIVERSITY Tracking in image sequences Lecture notes for the course Computer Vision Methods Tomáš Svoboda svobodat@fel.cvut.cz March 23, 2011 Lecture notes
More informationLecture 10 Dense 3D Reconstruction
Institute of Informatics Institute of Neuroinformatics Lecture 10 Dense 3D Reconstruction Davide Scaramuzza 1 REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time M. Pizzoli, C. Forster,
More informationDetection and Tracking of Moving Objects Using 2.5D Motion Grids
Detection and Tracking of Moving Objects Using 2.5D Motion Grids Alireza Asvadi, Paulo Peixoto and Urbano Nunes Institute of Systems and Robotics, University of Coimbra September 2015 1 Outline: Introduction
More informationA System for Real-time Detection and Tracking of Vehicles from a Single Car-mounted Camera
A System for Real-time Detection and Tracking of Vehicles from a Single Car-mounted Camera Claudio Caraffi, Tomas Vojir, Jiri Trefny, Jan Sochman, Jiri Matas Toyota Motor Europe Center for Machine Perception,
More informationAutonomous navigation in industrial cluttered environments using embedded stereo-vision
Autonomous navigation in industrial cluttered environments using embedded stereo-vision Julien Marzat ONERA Palaiseau Aerial Robotics workshop, Paris, 8-9 March 2017 1 Copernic Lab (ONERA Palaiseau) Research
More informationFusion Framework for Moving-Object Classification. Omar Chavez, Trung-Dung Vu (UJF) Trung-Dung Vu (UJF) Olivier Aycard (UJF) Fabio Tango (CRF)
Fusion Framework for Moving-Object Classification Omar Chavez, Trung-Dung Vu (UJF) Trung-Dung Vu (UJF) Olivier Aycard (UJF) Fabio Tango (CRF) Introduction Advance Driver Assistant Systems (ADAS) help drivers
More informationTorontoCity: Seeing the World with a Million Eyes
TorontoCity: Seeing the World with a Million Eyes Authors Shenlong Wang, Min Bai, Gellert Mattyus, Hang Chu, Wenjie Luo, Bin Yang Justin Liang, Joel Cheverie, Sanja Fidler, Raquel Urtasun * Project Completed
More informationDeep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material Introduction In this supplementary material, Section 2 details the 3D annotation for CAD models and real
More informationA Patch Prior for Dense 3D Reconstruction in Man-Made Environments
A Patch Prior for Dense 3D Reconstruction in Man-Made Environments Christian Häne 1, Christopher Zach 2, Bernhard Zeisl 1, Marc Pollefeys 1 1 ETH Zürich 2 MSR Cambridge October 14, 2012 A Patch Prior for
More informationCIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm
CIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm Instructions This is an individual assignment. Individual means each student must hand in their
More informationAN APPROACH TO EXTRACT MOVING OBJECTS FROM MLS DATA USING A VOLUMETRIC BACKGROUND REPRESENTATION
AN APPROACH TO EXTRACT MOVING OBJECTS FROM MLS DATA USING A VOLUMETRIC BACKGROUND REPRESENTATION Joachim Gehrung ab, Marcus Hebel a, Michael Arens a, Uwe Stilla b a Fraunhofer Institute of Optronics, System
More informationSolid State LiDAR for Ubiquitous 3D Sensing
April 6, 2016 Solid State LiDAR for Ubiquitous 3D Sensing Louay Eldada, Ph.D. CEO, Co-founder Quanergy Systems New Paradigm in 3D Sensing Disruptive Technologies: Solid State 3D LiDAR sensors Embedded
More informationFoundations for Summarizing and Learning Latent Structure in Video
Foundations for Summarizing and Learning Latent Structure in Video Presenter: Kevin Pitstick, MTS Engineer PI: Ed Morris, MTS Senior Engineer Copyright 2017 Carnegie Mellon University. All Rights Reserved.
More informationSupplementary: Cross-modal Deep Variational Hand Pose Estimation
Supplementary: Cross-modal Deep Variational Hand Pose Estimation Adrian Spurr, Jie Song, Seonwook Park, Otmar Hilliges ETH Zurich {spurra,jsong,spark,otmarh}@inf.ethz.ch Encoder/Decoder Linear(512) Table
More informationAn ICA based Approach for Complex Color Scene Text Binarization
An ICA based Approach for Complex Color Scene Text Binarization Siddharth Kherada IIIT-Hyderabad, India siddharth.kherada@research.iiit.ac.in Anoop M. Namboodiri IIIT-Hyderabad, India anoop@iiit.ac.in
More informationFrom 3D descriptors to monocular 6D pose: what have we learned?
ECCV Workshop on Recovering 6D Object Pose From 3D descriptors to monocular 6D pose: what have we learned? Federico Tombari CAMP - TUM Dynamic occlusion Low latency High accuracy, low jitter No expensive
More informationVision-Based Pedestrian Detection: The PROTECTOR System
Vision-Based Pedestrian Detection: The PROTECTOR System D.M. Gavrila, J. Giebel and S. Munder Machine Perception, DaimlerChrysler Research, Ulm, Germany dariu.gavrila,jan.giebel,stefan.munder @DaimlerChrysler.com
More informationObject Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning
Allan Zelener Dissertation Proposal December 12 th 2016 Object Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning Overview 1. Introduction to 3D Object Identification
More informationConvex Optimization / Homework 2, due Oct 3
Convex Optimization 0-725/36-725 Homework 2, due Oct 3 Instructions: You must complete Problems 3 and either Problem 4 or Problem 5 (your choice between the two) When you submit the homework, upload a
More informationEvaluation of Probabilistic Occupancy Map for Player Tracking in Team Sports
POSTER 2014, PRAGUE MAY 15 1 Evaluation of Probabilistic Occupancy Map for Player Tracking in Team Sports Matej ŠMÍD, Jan POKORNÝ Dept. of Cybernetics, Czech Technical University, Technická 2, 166 27 Praha,
More informationSupplementary Materials for Learning to Parse Wireframes in Images of Man-Made Environments
Supplementary Materials for Learning to Parse Wireframes in Images of Man-Made Environments Kun Huang, Yifan Wang, Zihan Zhou 2, Tianjiao Ding, Shenghua Gao, and Yi Ma 3 ShanghaiTech University {huangkun,
More informationSupplementary Material for Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
Supplementary Material for Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains Jiahao Pang 1 Wenxiu Sun 1 Chengxi Yang 1 Jimmy Ren 1 Ruichao Xiao 1 Jin Zeng 1 Liang Lin 1,2 1 SenseTime Research
More informationCS491/691: Introduction to Aerial Robotics
CS491/691: Introduction to Aerial Robotics Topic: Sampling-based Autonomous Exploration Dr. Kostas Alexis (CSE) Real-life is 3D, Complex, Possibly unknown Known Model to Compute Global Inspection Path
More informationDeep Learning in Image Processing
Deep Learning in Image Processing Roland Memisevic University of Montreal & TwentyBN ICISP 2016 Roland Memisevic Deep Learning in Image Processing ICISP 2016 f 2? cathedral high-rise f 1 It s the features,
More informationDetector of Facial Landmarks Learned by the Structured Output SVM
Detector of Facial Landmarks Learned by the Structured Output SVM Michal Uřičář, Vojtěch Franc and Václav Hlaváč Department of Cybernetics, Faculty Electrical Engineering Czech Technical University in
More informationSupplementary Material : Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision
Supplementary Material : Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision Due to space limitation in the main paper, we present additional experimental results in this supplementary
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 informationAdaptive Learning of an Accurate Skin-Color Model
Adaptive Learning of an Accurate Skin-Color Model Q. Zhu K.T. Cheng C. T. Wu Y. L. Wu Electrical & Computer Engineering University of California, Santa Barbara Presented by: H.T Wang Outline Generic Skin
More informationIdentifying Car Model from Photographs
Identifying Car Model from Photographs Fine grained Classification using 3D Reconstruction and 3D Shape Registration Xinheng Li davidxli@stanford.edu Abstract Fine grained classification from photographs
More informationColored Point Cloud Registration Revisited Supplementary Material
Colored Point Cloud Registration Revisited Supplementary Material Jaesik Park Qian-Yi Zhou Vladlen Koltun Intel Labs A. RGB-D Image Alignment Section introduced a joint photometric and geometric objective
More informationCamera model and calibration
Camera model and calibration Karel Zimmermann, zimmerk@cmp.felk.cvut.cz (some images taken from Tomáš Svoboda s) Czech Technical University in Prague, Center for Machine Perception http://cmp.felk.cvut.cz
More informationJoint Object Detection and Viewpoint Estimation using CNN features
Joint Object Detection and Viewpoint Estimation using CNN features Carlos Guindel, David Martín and José M. Armingol cguindel@ing.uc3m.es Intelligent Systems Laboratory Universidad Carlos III de Madrid
More informationProject 3 Q&A. Jonathan Krause
Project 3 Q&A Jonathan Krause 1 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations 2 Outline R-CNN Review Error metrics Code Overview Project 3 Report Project 3 Presentations
More informationOctree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material Peak memory usage, GB 10 1 0.1 0.01 OGN Quadratic Dense Cubic Iteration time, s 10
More informationExploiting Indoor Mobile Laser Scanner Trajectories for Interpretation of Indoor Scenes
Exploiting Indoor Mobile Laser Scanner Trajectories for Interpretation of Indoor Scenes March 2018 Promoter: Prof. Dr. Ir. George Vosselman Supervisor: Michael Peter 1 Indoor 3D Model Reconstruction to
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationIn-Situ Surface Roughness Measurement of Laser Beam Melted Parts a Feasibility Study of Layer Image Analysis
In-Situ Surface Roughness Measurement of Laser Beam Melted Parts a Feasibility Study of Layer Image Analysis Joschka zur Jacobsmühlen 1, Stefan Kleszczynski 2, Alexander Ladewig 3, Gerd Witt 2 and Dorit
More informationLearning to Segment Object Candidates
Learning to Segment Object Candidates Pedro Pinheiro, Ronan Collobert and Piotr Dollar Presented by - Sivaraman, Kalpathy Sitaraman, M.S. in Computer Science, University of Virginia Facebook Artificial
More informationDense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm
Computer Vision Group Prof. Daniel Cremers Dense Tracking and Mapping for Autonomous Quadrocopters Jürgen Sturm Joint work with Frank Steinbrücker, Jakob Engel, Christian Kerl, Erik Bylow, and Daniel Cremers
More informationSelf Driving. DNN * * Reinforcement * Unsupervised *
CNN 응용 Methods Traditional Deep-Learning based Non-machine Learning Machine-Learning based method Supervised SVM MLP CNN RNN (LSTM) Localizati on GPS, SLAM Self Driving Perception Pedestrian detection
More informationMask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi
Mask R-CNN By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Types of Computer Vision Tasks http://cs231n.stanford.edu/ Semantic vs Instance Segmentation Image
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 informationStereo Human Keypoint Estimation
Stereo Human Keypoint Estimation Kyle Brown Stanford University Stanford Intelligent Systems Laboratory kjbrown7@stanford.edu Abstract The goal of this project is to accurately estimate human keypoint
More informationA Study of Vehicle Detector Generalization on U.S. Highway
26 IEEE 9th International Conference on Intelligent Transportation Systems (ITSC) Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November -4, 26 A Study of Vehicle Generalization on U.S. Highway Rakesh
More informationMoonRiver: Deep Neural Network in C++
MoonRiver: Deep Neural Network in C++ Chung-Yi Weng Computer Science & Engineering University of Washington chungyi@cs.washington.edu Abstract Artificial intelligence resurges with its dramatic improvement
More informationA Deep Learning Approach to Vehicle Speed Estimation
A Deep Learning Approach to Vehicle Speed Estimation Benjamin Penchas bpenchas@stanford.edu Tobin Bell tbell@stanford.edu Marco Monteiro marcorm@stanford.edu ABSTRACT Given car dashboard video footage,
More informationPresented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey
Presented at the FIG Congress 2018, May 6-11, 2018 in Istanbul, Turkey Evangelos MALTEZOS, Charalabos IOANNIDIS, Anastasios DOULAMIS and Nikolaos DOULAMIS Laboratory of Photogrammetry, School of Rural
More informationReal-Time* Multiple Object Tracking (MOT) for Autonomous Navigation
Real-Time* Multiple Object Tracking (MOT) for Autonomous Navigation Ankush Agarwal,1 Saurabh Suryavanshi,2 ankushag@stanford.edu saurabhv@stanford.edu Authors contributed equally for this project. 1 Google
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 informationAutomatic Dense Semantic Mapping From Visual Street-level Imagery
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,
More informationRANSAC RANdom SAmple Consensus
Talk Outline importance for computer vision principle line fitting epipolar geometry estimation RANSAC RANdom SAmple Consensus Tomáš Svoboda, svoboda@cmp.felk.cvut.cz courtesy of Ondřej Chum, Jiří Matas
More informationDeep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing Supplementary Material Chi Li, M. Zeeshan Zia 2, Quoc-Huy Tran 2, Xiang Yu 2, Gregory D. Hager, and Manmohan Chandraker 2 Johns
More informationRGBD Occlusion Detection via Deep Convolutional Neural Networks
1 RGBD Occlusion Detection via Deep Convolutional Neural Networks Soumik Sarkar 1,2, Vivek Venugopalan 1, Kishore Reddy 1, Michael Giering 1, Julian Ryde 3, Navdeep Jaitly 4,5 1 United Technologies Research
More informationSupplemental Material: Discovering Groups of People in Images
Supplemental Material: Discovering Groups of People in Images Wongun Choi 1, Yu-Wei Chao 2, Caroline Pantofaru 3 and Silvio Savarese 4 1. NEC Laboratories 2. University of Michigan, Ann Arbor 3. Google,
More informationIntrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting R. Maier 1,2, K. Kim 1, D. Cremers 2, J. Kautz 1, M. Nießner 2,3 Fusion Ours 1
More informationSensory Augmentation for Increased Awareness of Driving Environment
Sensory Augmentation for Increased Awareness of Driving Environment Pranay Agrawal John M. Dolan Dec. 12, 2014 Technologies for Safe and Efficient Transportation (T-SET) UTC The Robotics Institute Carnegie
More informationPerformance Evaluation Metrics and Statistics for Positional Tracker Evaluation
Performance Evaluation Metrics and Statistics for Positional Tracker Evaluation Chris J. Needham and Roger D. Boyle School of Computing, The University of Leeds, Leeds, LS2 9JT, UK {chrisn,roger}@comp.leeds.ac.uk
More informationTask selection for control of active vision systems
The 29 IEEE/RSJ International Conference on Intelligent Robots and Systems October -5, 29 St. Louis, USA Task selection for control of active vision systems Yasushi Iwatani Abstract This paper discusses
More informationMysteries of Parameterizing Camera Motion - Part 1
Mysteries of Parameterizing Camera Motion - Part 1 Instructor - Simon Lucey 16-623 - Advanced Computer Vision Apps Today Motivation SO(3) Convex? Exponential Maps SL(3) Group. Adapted from: Computer vision:
More informationLimited View Angle Iterative CT Reconstruction
Limited View Angle Iterative CT Reconstruction Sherman J. Kisner 1, Eri Haneda 1, Charles A. Bouman 1, Sondre Skatter 2, Mikhail Kourinny 2, Simon Bedford 3 1 Purdue University, West Lafayette, IN, USA
More informationINTRODUCTION TO IMAGE PROCESSING (COMPUTER VISION)
INTRODUCTION TO IMAGE PROCESSING (COMPUTER VISION) Revision: 1.4, dated: November 10, 2005 Tomáš Svoboda Czech Technical University, Faculty of Electrical Engineering Center for Machine Perception, Prague,
More information3D Convolutional Neural Networks for Landing Zone Detection from LiDAR
3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping
More informationColour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation
ÖGAI Journal 24/1 11 Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation Michael Bleyer, Margrit Gelautz, Christoph Rhemann Vienna University of Technology
More informationOpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps
OpenStreetSLAM: Global Vehicle Localization using OpenStreetMaps Georgios Floros, Benito van der Zander and Bastian Leibe RWTH Aachen University, Germany http://www.vision.rwth-aachen.de floros@vision.rwth-aachen.de
More informationAutomotive 3D Object Detection Without Target Domain Annotations
Master of Science Thesis in Electrical Engineering Department of Electrical Engineering, Linköping University, 2018 Automotive 3D Object Detection Without Target Domain Annotations Erik Linder-Norén and
More informationAnnouncements. CS 188: Artificial Intelligence Spring Advanced Applications. Robot folds towels. Robotic Control Tasks
CS 188: Artificial Intelligence Spring 2011 Advanced Applications: Robotics Announcements Practice Final Out (optional) Similar extra credit system as practice midterm Contest (optional): Tomorrow night
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2011 Advanced Applications: Robotics Pieter Abbeel UC Berkeley A few slides from Sebastian Thrun, Dan Klein 1 Announcements Practice Final Out (optional) Similar
More informationComputer Vision and Virtual Reality. Introduction
Computer Vision and Virtual Reality Introduction Tomáš Svoboda, svoboda@cmp.felk.cvut.cz Czech Technical University in Prague, Center for Machine Perception http://cmp.felk.cvut.cz Last update: October
More informationMulti-view stereo. Many slides adapted from S. Seitz
Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window
More informationSolid-State Hybrid LiDAR for Autonomous Driving Product Description
Solid-State Hybrid LiDAR for Autonomous Driving Product Description What is LiDAR Sensor Who is Using LiDARs How does LiDAR Work Hesai LiDAR Demo Features Terminologies Specifications What is LiDAR A LiDAR
More information(Deep) Learning for Robot Perception and Navigation. Wolfram Burgard
(Deep) Learning for Robot Perception and Navigation Wolfram Burgard Deep Learning for Robot Perception (and Navigation) Lifeng Bo, Claas Bollen, Thomas Brox, Andreas Eitel, Dieter Fox, Gabriel L. Oliveira,
More informationMidterm Examination CS 534: Computational Photography
Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)
More informationFast Local Planner for Autonomous Helicopter
Fast Local Planner for Autonomous Helicopter Alexander Washburn talexan@seas.upenn.edu Faculty advisor: Maxim Likhachev April 22, 2008 Abstract: One challenge of autonomous flight is creating a system
More informationGrid-Based Models for Dynamic Environments
Grid-Based Models for Dynamic Environments Daniel Meyer-Delius Maximilian Beinhofer Wolfram Burgard Abstract The majority of existing approaches to mobile robot mapping assume that the world is, an assumption
More information