Team the Amazon Robotics Challenge 1st place in stowing task
|
|
- Hollie Barker
- 6 years ago
- Views:
Transcription
1 Grasping
2 Team the Amazon Robotics Challenge 1st place in stowing task Andy Zeng Shuran Song Kuan-Ting Yu Elliott Donlon Francois Hogan Maria Bauza Daolin Ma Orion Taylor Melody Liu Eudald Romo Nima Fazeli Ferran Alet Nikhil Dafle Rachel Holladay Isabella Morona Prem Qu Nair Druck Green Ian Taylor Weber Liu Thomas Funkhouser Alberto Rodriguez
3 From model-based to model-free Model-based grasping Pose estimation Grasp planning Works well with known objects in structured environments Can t handle novel objects in unstructured environments (due to pose estimation)
4 From model-based to model-free Model-based grasping Pose estimation Grasp planning Works well with known objects in structured environments Can t handle novel objects in unstructured environments (due to pose estimation) Model-free grasping Visual data Grasp planning Use local geometric features Ignore object identity End-to-end Motivated by industry
5 Recent work on model-free grasping Grasp Pose Detection M. Gualtieri et al., 17 Supersizing Self-Supervision L. Pinto and A. Gupta, 16 Handles clutter and novel objects DexNet J. Mahler et al., 17
6 Recent work on model-free grasping Grasp Pose Detection M. Gualtieri et al., 17 Supersizing Self-Supervision L. Pinto and A. Gupta, 16 DexNet J. Mahler et al., 17 Handles clutter on tabletop scenarios and novel objects selected beforehand
7 Recent work on model-free grasping Grasp Pose Detection M. Gualtieri et al., 17 Supersizing Self-Supervision L. Pinto and A. Gupta, 16 DexNet J. Mahler et al., 17 Common limitations: low grasp sample density, small neural network sizes
8 In this talk A model-free grasping method
9 In this talk A model-free grasping method Handles dense clutter in tabletop bin/box scenario Rethink dense clutter: Objects not only tightly packed, but also tossed and stacked on top of each other Objects in corners and on bin edges
10 In this talk A model-free grasping method Handles dense clutter in tabletop bin/box scenario Works for novel objects of all kinds (i.e. any household object should be fair game) 90-95% grasping accuracy is not enough Objects without depth data...
11 In this talk A model-free grasping method Handles dense clutter in tabletop bin/box scenario Works for novel objects of all kinds (i.e. any household object should be fair game) Fast and efficient Standard: Grasp sampling Ours: Grasp ranking Dense pixel-wise predictions
12 In this talk A model-free grasping method Handles dense clutter in tabletop bin/box scenario Works for novel objects of all kinds (i.e. any household object should be fair game) Fast and efficient 1st place stowing task at Amazon Robotics Challenge 17 (i.e. it works) The Beast from the East setup competition footage
13 Overview: multi-affordance grasping Input: multi-view RGB-D images
14 Overview: multi-affordance grasping Input: multi-view RGB-D images Output: dense grasp proposals and affordance scores for 4 primitive grasping behaviors: suction down suction side grasp down flush grasp
15 Dense pixel-wise affordances with FCNs Input RGB-D images fully convolutional ResNet-50
16 Dense pixel-wise affordances with FCNs Input RGB-D images suction down suction side fully convolutional ResNet-50
17 Dense pixel-wise affordances with FCNs Input RGB-D images suction down suction side fully convolutional ResNet-50
18 Dense pixel-wise affordances with FCNs Input RGB-D images suction down suction side fully convolutional ResNet-50 What about grasping?
19 Dense pixel-wise affordances with FCNs Input RGB-D images suction down suction side fully convolutional ResNet-50 RGB-D heightmaps
20 Dense pixel-wise affordances with FCNs Input RGB-D images suction down suction side fully convolutional ResNet-50 RGB-D heightmaps grasp down flush grasp
21 Dense pixel-wise affordances with FCNs Input RGB-D images suction down suction side fully convolutional ResNet-50 RGB-D heightmaps grasp down flush grasp predicts horizontal grasp affordances
22 Training data Manual labeling ~100 different household/office objects Suctionable areas Parallel-jaw grasps
23 Generalization from hardware capabilities High-powered deployable suction Actuated spatula
24 Pros and cons Advantages: Fast runtime speeds from efficient convolution
25 Pros and cons Advantages: Fast runtime speeds from efficient convolution Uses both color and depth information
26 Pros and cons Advantages: Fast runtime speeds from efficient convolution Uses both color and depth information Can leverage fat pre-trained networks Higher good grasp recall Standard: Grasp sampling Ours: Grasp ranking
27 Pros and cons Advantages: Fast runtime speeds from efficient convolution Uses both color and depth information Can leverage fat pre-trained networks Higher good grasp recall Limitations: Considers only top-down parallel-jaw grasps Can trivially extend to more grasp angles Limited to grasping behaviors for which you can define affordances (no real planning) Open-loop
28 Future work Model-based grasping Pose estimation Grasp planning Model-free grasping Visual data Grasp planning
29 Future work Model-based grasping Pose estimation Grasp planning Model-free grasping Visual data Grasp planning How can we improve model-free by making it more like model-based?
30 Future work Model-based grasping Model-free grasping Semantic Scene Completion from a Single Depth Image [Song et al., CVPR 17]
31 Takeaways A model-free grasping method FCNs to compute dense affordance predictions for multiple grasping behaviors (suction, parallel-jaw) Multiple grasping primitive behaviors dense clutter in bin/box scenario Multi-view color and depth + diverse training data + robust hardware handle novel objects of all kinds FCNs for grasping affordance predictions efficiency and high grasp recall
32 Takeaways A model-free grasping method FCNs to compute dense affordance predictions for multiple grasping behaviors (suction, parallel-jaw) Multiple grasping primitive behaviors dense clutter in bin/box scenario Multi-view color and depth + diverse training data + robust hardware handle novel objects of all kinds FCNs for grasping affordance predictions efficiency and high grasp recall Paper and code are available: arc.cs.princeton.edu
33 Recognition of novel objects without retraining Match real images of novel objects to their product images (available at test time) After isolating object from clutter with model-free grasping, perform recognition
34 Cross domain image matching (training) product images observed images ℓ2 distance ratio loss match?
35 Cross domain image matching (training) product images observed images ℓ2 distance ratio loss match? softmax loss for K-Net only
36 Cross domain image matching (testing) feature embedding known novel
37 Cross domain image matching (testing) input feature embedding known novel
38 Cross domain image matching (testing) input feature embedding known novel match!
39 Cross domain image matching (testing) input feature embedding known novel match! Pre-trained ImageNet features
arxiv: v3 [cs.ro] 20 Feb 2018
Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching arxiv:1710.01330v3 [cs.ro] 20 Feb 2018 Andy Zeng1, Shuran Song1, Kuan-Ting Yu2, Elliott
More informationRobotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching Andy Zeng1, Shuran Song1, Kuan-Ting Yu2, Elliott Donlon2, Francois R. Hogan2, Maria Bauza2,
More informationCombining RGB and Points to Predict Grasping Region for Robotic Bin-Picking
Combining RGB and Points to Predict Grasping Region for Robotic Bin-Picking Quanquan Shao a, Jie Hu Shanghai Jiao Tong University Shanghai, China e-mail: a sjtudq@qq.com Abstract This paper focuses on
More informationLearning from 3D Data
Learning from 3D Data Thomas Funkhouser Princeton University* * On sabbatical at Stanford and Google Disclaimer: I am talking about the work of these people Shuran Song Andy Zeng Fisher Yu Yinda Zhang
More informationarxiv: v2 [cs.cv] 2 Oct 2016
Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge Andy Zeng 1 Kuan-Ting Yu 2 Shuran Song 1 Daniel Suo 1 Ed Walker Jr. 3 Alberto Rodriguez 2 Jianxiong Xiao
More information3D Scene Understanding from RGB-D Images. Thomas Funkhouser
3D Scene Understanding from RGB-D Images Thomas Funkhouser Recent Ph.D. Student Current Postdocs Current Ph.D. Students Disclaimer: I am talking about the work of these people Shuran Song Yinda Zhang Andy
More informationDeep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia
Deep learning for dense per-pixel prediction Chunhua Shen The University of Adelaide, Australia Image understanding Classification error Convolution Neural Networks 0.3 0.2 0.1 Image Classification [Krizhevsky
More informationLearning Semantic Environment Perception for Cognitive Robots
Learning Semantic Environment Perception for Cognitive Robots Sven Behnke University of Bonn, Germany Computer Science Institute VI Autonomous Intelligent Systems Some of Our Cognitive Robots Equipped
More informationEnsembleNet: Improving Grasp Detection using an Ensemble of Convolutional Neural Networks
U. ASIF et al.: GRASP DETECTION USING AN ENSEMBLE OF CNN MODELS 1 EnsembleNet: Improving Grasp Detection using an Ensemble of Convolutional Neural Networks Umar Asif umarasif@au1.ibm.com Jianbin Tang jbtang@au1.ibm.com
More informationEncoder-Decoder Networks for Semantic Segmentation. Sachin Mehta
Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:
More informationSemantic RGB-D Perception for Cognitive Robots
Semantic RGB-D Perception for Cognitive Robots Sven Behnke Computer Science Institute VI Autonomous Intelligent Systems Our Domestic Service Robots Dynamaid Cosero Size: 100-180 cm, weight: 30-35 kg 36
More informationPlaces Challenge 2017
Places Challenge 2017 Scene Parsing Task CASIA_IVA_JD Jun Fu, Jing Liu, Longteng Guo, Haijie Tian, Fei Liu, Hanqing Lu Yong Li, Yongjun Bao, Weipeng Yan National Laboratory of Pattern Recognition, Institute
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 informationComputer Vision Lecture 16
Announcements Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Seminar registration period starts on Friday We will offer a lab course in the summer semester Deep Robot Learning Topic:
More informationLearning from Successes and Failures to Grasp Objects with a Vacuum Gripper
Learning from Successes and Failures to Grasp Objects with a Vacuum Gripper Luca Monorchio, Daniele Evangelista, Marco Imperoli, and Alberto Pretto Abstract In this work we present an empirical approach
More informationComputer Vision Lecture 16
Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts
More informationTowards Grasp Transfer using Shape Deformation
Towards Grasp Transfer using Shape Deformation Andrey Kurenkov, Viraj Mehta, Jingwei Ji, Animesh Garg, Silvio Savarese Stanford Vision and Learning Lab Abstract: Grasping has recently seen a quanta of
More informationR-FCN: Object Detection with Really - Friggin Convolutional Networks
R-FCN: Object Detection with Really - Friggin Convolutional Networks Jifeng Dai Microsoft Research Li Yi Tsinghua Univ. Kaiming He FAIR Jian Sun Microsoft Research NIPS, 2016 Or Region-based Fully Convolutional
More informationManipulating a Large Variety of Objects and Tool Use in Domestic Service, Industrial Automation, Search and Rescue, and Space Exploration
Manipulating a Large Variety of Objects and Tool Use in Domestic Service, Industrial Automation, Search and Rescue, and Space Exploration Sven Behnke Computer Science Institute VI Autonomous Intelligent
More informationPhoto OCR ( )
Photo OCR (2017-2018) Xiang Bai Huazhong University of Science and Technology Outline VALSE2018, DaLian Xiang Bai 2 Deep Direct Regression for Multi-Oriented Scene Text Detection [He et al., ICCV, 2017.]
More informationDeep learning for object detection. Slides from Svetlana Lazebnik and many others
Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep
More informationSemantic Segmentation
Semantic Segmentation UCLA:https://goo.gl/images/I0VTi2 OUTLINE Semantic Segmentation Why? Paper to talk about: Fully Convolutional Networks for Semantic Segmentation. J. Long, E. Shelhamer, and T. Darrell,
More informationPerceiving the 3D World from Images and Videos. Yu Xiang Postdoctoral Researcher University of Washington
Perceiving the 3D World from Images and Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World 3 Understand
More informationarxiv: v2 [cs.ro] 7 Sep 2018
Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation Peter R. Florence*, Lucas Manuelli*, Russ Tedrake CSAIL, Massachusetts Institute of Technology {peteflo,manuelli,russt}@csail.mit.edu
More informationDetecting and Parsing of Visual Objects: Humans and Animals. Alan Yuille (UCLA)
Detecting and Parsing of Visual Objects: Humans and Animals Alan Yuille (UCLA) Summary This talk describes recent work on detection and parsing visual objects. The methods represent objects in terms of
More informationThe Crucial Components to Solve the Picking Problem
B. Scholz Common Approaches to the Picking Problem 1 / 31 MIN Faculty Department of Informatics The Crucial Components to Solve the Picking Problem Benjamin Scholz University of Hamburg Faculty of Mathematics,
More information3D Object Recognition and Scene Understanding from RGB-D Videos. Yu Xiang Postdoctoral Researcher University of Washington
3D Object Recognition and Scene Understanding from RGB-D Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World
More information3D model classification using convolutional neural network
3D model classification using convolutional neural network JunYoung Gwak Stanford jgwak@cs.stanford.edu Abstract Our goal is to classify 3D models directly using convolutional neural network. Most of existing
More informationVisual Perception for Robots
Visual Perception for Robots Sven Behnke Computer Science Institute VI Autonomous Intelligent Systems Our Cognitive Robots Complete systems for example scenarios Equipped with rich sensors Flying robot
More informationTeam G-RMI: Google Research & Machine Intelligence
Team G-RMI: Google Research & Machine Intelligence Alireza Fathi (alirezafathi@google.com) Nori Kanazawa, Kai Yang, George Papandreou, Tyler Zhu, Jonathan Huang, Vivek Rathod, Chen Sun, Kevin Murphy, et
More informationTri-modal Human Body Segmentation
Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4
More informationLearning to Singulate Objects using a Push Proposal Network
Learning to Singulate Objects using a Push Proposal Network Andreas Eitel, Nico Hauff and Wolfram Burgard Abstract Learning to act in unstructured environments such as cluttered piles of objects poses
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 informationLearning-based Localization
Learning-based Localization Eric Brachmann ECCV 2018 Tutorial on Visual Localization - Feature-based vs. Learned Approaches Torsten Sattler, Eric Brachmann Roadmap Machine Learning Basics [10min] Convolutional
More informationHand-Object Interaction Detection with Fully Convolutional Networks
Hand-Object Interaction Detection with Fully Convolutional Networks Matthias Schröder Helge Ritter Neuroinformatics Group, Bielefeld University {maschroe,helge}@techfak.uni-bielefeld.de Abstract Detecting
More informationCascade Region Regression for Robust Object Detection
Large Scale Visual Recognition Challenge 2015 (ILSVRC2015) Cascade Region Regression for Robust Object Detection Jiankang Deng, Shaoli Huang, Jing Yang, Hui Shuai, Zhengbo Yu, Zongguang Lu, Qiang Ma, Yali
More informationFuzzy Set Theory in Computer Vision: Example 3
Fuzzy Set Theory in Computer Vision: Example 3 Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Purpose of these slides are to make you aware of a few of the different CNN architectures
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 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 informationEfficient Segmentation-Aided Text Detection For Intelligent Robots
Efficient Segmentation-Aided Text Detection For Intelligent Robots Junting Zhang, Yuewei Na, Siyang Li, C.-C. Jay Kuo University of Southern California Outline Problem Definition and Motivation Related
More informationWhat are we trying to achieve? Why are we doing this? What do we learn from past history? What will we talk about today?
Introduction What are we trying to achieve? Why are we doing this? What do we learn from past history? What will we talk about today? What are we trying to achieve? Example from Scott Satkin 3D interpretation
More informationDepth from Stereo. Dominic Cheng February 7, 2018
Depth from Stereo Dominic Cheng February 7, 2018 Agenda 1. Introduction to stereo 2. Efficient Deep Learning for Stereo Matching (W. Luo, A. Schwing, and R. Urtasun. In CVPR 2016.) 3. Cascade Residual
More informationRGBd Image Semantic Labelling for Urban Driving Scenes via a DCNN
RGBd Image Semantic Labelling for Urban Driving Scenes via a DCNN Jason Bolito, Research School of Computer Science, ANU Supervisors: Yiran Zhong & Hongdong Li 2 Outline 1. Motivation and Background 2.
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 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 informationA Data-Efficient Approach to Precise and Controlled Pushing
A Data-Efficient Approach to Precise and Controlled Pushing Maria Bauza, Francois R. Hogan and Alberto Rodriguez Department of Mechanical Engineering Massachusetts Institute of Technology @mit.edu
More informationChannel Locality Block: A Variant of Squeeze-and-Excitation
Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan
More informationThree-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients
ThreeDimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients Authors: Zhile Ren, Erik B. Sudderth Presented by: Shannon Kao, Max Wang October 19, 2016 Introduction Given an
More informationSemantic Segmentation from Limited Training Data
Semantic Segmentation from Limited Training Data A. Milan 1,3, T. Pham 1,3, K. Vijay 1,3, D. Morrison 1,2, A.W. Tow 1,2, L. Liu 3, J. Erskine 1,2, R. Grinover 1,2, A. Gurman 1,2, T. Hunn 1,2, N. Kelly-Boxall
More informationMulti-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 informationClassification of objects from Video Data (Group 30)
Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time
More informationSSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang
SSD: Single Shot MultiBox Detector Author: Wei Liu et al. Presenter: Siyu Jiang Outline 1. Motivations 2. Contributions 3. Methodology 4. Experiments 5. Conclusions 6. Extensions Motivation Motivation
More informationECCV Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016
ECCV 2016 Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016 Fundamental Question What is a good vector representation of an object? Something that can be easily predicted from 2D
More informationRecurrent Convolutional Neural Networks for Scene Labeling
Recurrent Convolutional Neural Networks for Scene Labeling Pedro O. Pinheiro, Ronan Collobert Reviewed by Yizhe Zhang August 14, 2015 Scene labeling task Scene labeling: assign a class label to each pixel
More informationarxiv: v1 [cs.cv] 29 Sep 2016
arxiv:1609.09545v1 [cs.cv] 29 Sep 2016 Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge Adrian Bulat and Georgios Tzimiropoulos Computer Vision
More informationJOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS. Zhao Chen Machine Learning Intern, NVIDIA
JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS Zhao Chen Machine Learning Intern, NVIDIA ABOUT ME 5th year PhD student in physics @ Stanford by day, deep learning computer vision scientist
More informationHuman Detection and Tracking for Video Surveillance: A Cognitive Science Approach
Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Vandit Gajjar gajjar.vandit.381@ldce.ac.in Ayesha Gurnani gurnani.ayesha.52@ldce.ac.in Yash Khandhediya khandhediya.yash.364@ldce.ac.in
More informationDeep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks
Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin
More informationFlow-Based Video Recognition
Flow-Based Video Recognition Jifeng Dai Visual Computing Group, Microsoft Research Asia Joint work with Xizhou Zhu*, Yuwen Xiong*, Yujie Wang*, Lu Yuan and Yichen Wei (* interns) Talk pipeline Introduction
More informationMask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma
Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left
More informationUsing RGB, Depth, and Thermal Data for Improved Hand Detection
Using RGB, Depth, and Thermal Data for Improved Hand Detection Rachel Luo, Gregory Luppescu Department of Electrical Engineering Stanford University {rsluo, gluppes}@stanford.edu Abstract Hand detection
More informationImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky Ilya Sutskever Geoffrey Hinton University of Toronto Canada Paper with same name to appear in NIPS 2012 Main idea Architecture
More informationFast Semantic Segmentation of RGB-D Scenes with GPU-Accelerated Deep Neural Networks
Fast Semantic Segmentation of RGB-D Scenes with GPU-Accelerated Deep Neural Networks Nico Höft, Hannes Schulz, and Sven Behnke Rheinische Friedrich-Wilhelms-Universität Bonn Institut für Informatik VI,
More informationMCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection
MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection ILSVRC 2016 Object Detection from Video Byungjae Lee¹, Songguo Jin¹, Enkhbayar Erdenee¹, Mi Young Nam², Young Gui Jung², Phill Kyu
More informationarxiv: v3 [cs.ro] 9 Nov 2017
End-to-End Learning of Semantic Grasping Eric Jang Google Brain ejang@google.com Sudheendra Vijayanarasimhan Google svnaras@google.com Peter Pastor X peterpastor@x.team Julian Ibarz Google Brain julianibarz@google.com
More informationEdge and corner detection
Edge and corner detection Prof. Stricker Doz. G. Bleser Computer Vision: Object and People Tracking Goals Where is the information in an image? How is an object characterized? How can I find measurements
More informationLSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University
LSTM and its variants for visual recognition Xiaodan Liang xdliang328@gmail.com Sun Yat-sen University Outline Context Modelling with CNN LSTM and its Variants LSTM Architecture Variants Application in
More information3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing
3 Object Detection BVM 2018 Tutorial: Advanced Deep Learning Methods Paul F. Jaeger, of Medical Image Computing What is object detection? classification segmentation obj. detection (1 label per pixel)
More informationSemantic Segmentation from Limited Training Data
Semantic Segmentation from Limited Training Data A. Milan 5, T. Pham 1,3, K. Vijay 1,3, D. Morrison 1,2, A.W. Tow 1,2, L. Liu 3, J. Erskine 1,2, R. Grinover 1,2, A. Gurman 1,2, T. Hunn 1,2, N. Kelly-Boxall
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 informationActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems (Supplementary Materials)
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems (Supplementary Materials) Yinda Zhang 1,2, Sameh Khamis 1, Christoph Rhemann 1, Julien Valentin 1, Adarsh Kowdle 1, Vladimir
More informationDetection and Fine 3D Pose Estimation of Texture-less Objects in RGB-D Images
Detection and Pose Estimation of Texture-less Objects in RGB-D Images Tomáš Hodaň1, Xenophon Zabulis2, Manolis Lourakis2, Šťěpán Obdržálek1, Jiří Matas1 1 Center for Machine Perception, CTU in Prague,
More informationR-FCN: OBJECT DETECTION VIA REGION-BASED FULLY CONVOLUTIONAL NETWORKS
R-FCN: OBJECT DETECTION VIA REGION-BASED FULLY CONVOLUTIONAL NETWORKS JIFENG DAI YI LI KAIMING HE JIAN SUN MICROSOFT RESEARCH TSINGHUA UNIVERSITY MICROSOFT RESEARCH MICROSOFT RESEARCH SPEED/ACCURACY TRADE-OFFS
More informationwith Deep Learning A Review of Person Re-identification Xi Li College of Computer Science, Zhejiang University
A Review of Person Re-identification with Deep Learning Xi Li College of Computer Science, Zhejiang University http://mypage.zju.edu.cn/xilics Email: xilizju@zju.edu.cn Person Re-identification Associate
More informationECE 5470 Classification, Machine Learning, and Neural Network Review
ECE 5470 Classification, Machine Learning, and Neural Network Review Due December 1. Solution set Instructions: These questions are to be answered on this document which should be submitted to blackboard
More informationReal-Time Object Pose Estimation with Pose Interpreter Networks
Real-Time Object Pose Estimation with Pose Interpreter Networks Jimmy Wu 1, Bolei Zhou 1, Rebecca Russell 2, Vincent Kee 2, Syler Wagner 3, Mitchell Hebert 2, Antonio Torralba 1, and David M.S. Johnson
More informationCS231N Section. Video Understanding 6/1/2018
CS231N Section Video Understanding 6/1/2018 Outline Background / Motivation / History Video Datasets Models Pre-deep learning CNN + RNN 3D convolution Two-stream What we ve seen in class so far... Image
More informationC-Brain: A Deep Learning Accelerator
C-Brain: A Deep Learning Accelerator that Tames the Diversity of CNNs through Adaptive Data-level Parallelization Lili Song, Ying Wang, Yinhe Han, Xin Zhao, Bosheng Liu, Xiaowei Li State Key Laboratory
More informationConvolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech
Convolutional Neural Networks Computer Vision Jia-Bin Huang, Virginia Tech Today s class Overview Convolutional Neural Network (CNN) Training CNN Understanding and Visualizing CNN Image Categorization:
More informationStructured Prediction using Convolutional Neural Networks
Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer
More informationSelf-Supervised Learning & Visual Discovery
CS 2770: Computer Vision Self-Supervised Learning & Visual Discovery Prof. Adriana Kovashka University of Pittsburgh April 10, 2017 Motivation So far we ve assumed access to plentiful labeled data How
More informationFinding Surface Correspondences With Shape Analysis
Finding Surface Correspondences With Shape Analysis Sid Chaudhuri, Steve Diverdi, Maciej Halber, Vladimir Kim, Yaron Lipman, Tianqiang Liu, Wilmot Li, Niloy Mitra, Elena Sizikova, Thomas Funkhouser Motivation
More informationDeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs Zhipeng Yan, Moyuan Huang, Hao Jiang 5/1/2017 1 Outline Background semantic segmentation Objective,
More informationDEEP BLIND IMAGE QUALITY ASSESSMENT
DEEP BLIND IMAGE QUALITY ASSESSMENT BY LEARNING SENSITIVITY MAP Jongyoo Kim, Woojae Kim and Sanghoon Lee ICASSP 2018 Deep Learning and Convolutional Neural Networks (CNNs) SOTA in computer vision & image
More informationAUTOMATED DETECTION AND CLASSIFICATION OF CANCER METASTASES IN WHOLE-SLIDE HISTOPATHOLOGY IMAGES USING DEEP LEARNING
AUTOMATED DETECTION AND CLASSIFICATION OF CANCER METASTASES IN WHOLE-SLIDE HISTOPATHOLOGY IMAGES USING DEEP LEARNING F. Ghazvinian Zanjani, S. Zinger, P. H. N. de With Electrical Engineering Department,
More informationFinding Structure in Large Collections of 3D Models
Finding Structure in Large Collections of 3D Models Vladimir Kim Adobe Research Motivation Explore, Analyze, and Create Geometric Data Real Virtual Motivation Explore, Analyze, and Create Geometric Data
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 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 informationVisual Computing TUM
Visual Computing Group @ TUM Visual Computing Group @ TUM BundleFusion Real-time 3D Reconstruction Scalable scene representation Global alignment and re-localization TOG 17 [Dai et al.]: BundleFusion Real-time
More informationObject Detection Based on Deep Learning
Object Detection Based on Deep Learning Yurii Pashchenko AI Ukraine 2016, Kharkiv, 2016 Image classification (mostly what you ve seen) http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf
More informationAmodal and Panoptic Segmentation. Stephanie Liu, Andrew Zhou
Amodal and Panoptic Segmentation Stephanie Liu, Andrew Zhou This lecture: 1. 2. 3. 4. Semantic Amodal Segmentation Cityscapes Dataset ADE20K Dataset Panoptic Segmentation Semantic Amodal Segmentation Yan
More informationPairwise Threshold for Gaussian Mixture Classification and its Application on Human Tracking Enhancement
Pairwise Threshold for Gaussian Mixture Classification and its Application on Human Tracking Enhancement Daegeon Kim Sung Chun Lee Institute for Robotics and Intelligent Systems University of Southern
More informationClassifying a specific image region using convolutional nets with an ROI mask as input
Classifying a specific image region using convolutional nets with an ROI mask as input 1 Sagi Eppel Abstract Convolutional neural nets (CNN) are the leading computer vision method for classifying images.
More informationFitting (LMedS, RANSAC)
Fitting (LMedS, RANSAC) Thursday, 23/03/2017 Antonis Argyros e-mail: argyros@csd.uoc.gr LMedS and RANSAC What if we have very many outliers? 2 1 Least Median of Squares ri : Residuals Least Squares n 2
More informationAndrei Polzounov (Universitat Politecnica de Catalunya, Barcelona, Spain), Artsiom Ablavatski (A*STAR Institute for Infocomm Research, Singapore),
WordFences: Text Localization and Recognition ICIP 2017 Andrei Polzounov (Universitat Politecnica de Catalunya, Barcelona, Spain), Artsiom Ablavatski (A*STAR Institute for Infocomm Research, Singapore),
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 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 informationObject detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation
Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN
More informationDeep Incremental Scene Understanding. Federico Tombari & Christian Rupprecht Technical University of Munich, Germany
Deep Incremental Scene Understanding Federico Tombari & Christian Rupprecht Technical University of Munich, Germany C. Couprie et al. "Toward Real-time Indoor Semantic Segmentation Using Depth Information"
More informationObject detection with CNNs
Object detection with CNNs 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before CNNs After CNNs 0% 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 year Region proposals
More information