Computer Vision. From traditional approaches to deep neural networks. Stanislav Frolov München,

Size: px
Start display at page:

Download "Computer Vision. From traditional approaches to deep neural networks. Stanislav Frolov München,"

Transcription

1 Computer Vision From traditional approaches to deep neural networks Stanislav Frolov München,

2 Outline of this talk What we are going to talk about Computer vision Human vision Traditional approaches and methods Artificial neural networks Summary 2

3 Stanislav Frolov Big Data trained deep neural networks for object detection during master thesis still fascinated and interested 3

4 What is computer vision General Teach computers how to see Automatic extraction, analysis and understanding of images Infer useful information, interpret and make decisions Automate tasks that human visual system can do One of the most exciting fields in AI and ML 4

5 What is computer vision Motivation Era of pixels Internet consists mostly of images Explosion of visual data Cannot be labeled by humans 5

6 What is computer vision Drivers Two drivers for computer vision explosion Compute (faster and cheaper) Data (more data > algorithms) 6

7 What is computer vision Interdisciplinary field Computer Science Graphs, Algorithms Systems Architecture Engineering Speech, NLP Image Processing Robotics Machine Learning Mathematics Information Retrieval Biology Optics Biological vision Physics Solid-State Physics Neuroscience Psychology Cognitive Sciences 7

8 Synonyms? 8

9 What is computer vision Related fields - image processing Imaging for statistical pattern recognition Image transformations such as pixel-by-pixel operations Contrast enhancement Edge extraction Noise reduction Geometrical and spatial operations (i.e rotations) 9

10 What is computer vision Related fields - computer graphics Creates new images from scene descriptions Produces image data from 3D models Inverse of computer vision AR as a combination of both 10

11 What is computer vision Related fields - machine vision Mainly manufacturing applications Image-based automatic inspection, process control, robot guidance Usually employs strong assumptions (colour, shape, light, structure, orientation,...) -> works very well Output often pass/fail or good/bad Additionally numerical/measurement data, counts 11

12 What is computer vision Related fields - AI Create intelligent systems Studying computational aspects of intelligence Make computers do things at which, at the moment, people are better Many techniques play an important role (ML, ANNs) Currently does a few things better/faster at scale than humans can Ability to do anything human is not answered 12

13 What is computer vision Related fields- summary Related fields have a large intersection Basic techniques used, developed and studied are very similar 13

14 Short trip to human vision 14

15 What is human vision General Two stage process Eyes take in light reflected off the objects and retina converts 3D objects into 2D images Brain s visual system interprets 2D images and rebuilds a 3D model 15

16 What is human vision Stereoscopic vision Pair of 2D images with slightly different view allows to infer depth Position of nearby objects will vary more across the two images than the position of more distant objects 16

17 What is human vision Prior knowledge Prior knowledge of relative sizes and depths is often key for understanding and interpretation 17

18 What is human vision Texture pattern Texture and texture change helps solving depth perception 18

19 What is human vision Biases and illusions in human perception Shadows make all the difference in interpretation Gradual changes in light ignored to not be misled by shadow 19

20 What is human vision A few more illusions Two arrows with different orientations have the same length 20

21 What is human vision Biases and illusions in human perception Assumptions and familiarity (distorted room) Face recognition bias Up-down orientation bias 21

22 What is human vision Summary Illusions are fun, but the complete puzzle to understand human vision is far from being complete 22

23 Back to computer vision 23

24 What is computer vision Typical tasks Recognition Localization Detection Segmentation 24

25 What is computer vision Typical tasks Part-based detection Deformable parts model Pose estimation and poselets 25

26 What is computer vision Typical tasks Image captioning (actions, attributes) 26

27 What is computer vision Typical tasks Motion analysis Egomotion (camera) Optical flow (pixels) 27

28 What is computer vision Typical tasks Scene understanding and reconstruction 28

29 What is computer vision Typical tasks Image restoration Colouring black & white photos 29

30 Solving this is useful for many applications 30

31 What is computer vision Typical applications Assistance systems for cars and people Surveillance Navigation (obstacle avoidance, road following, path planning) Photo interpretation Military ( smart weapons) Manufacturing (inspection, identification) Robotics Autonomous vehicles (dangerous zones) 31

32 What is computer vision Typical applications Recognition and tracking Event detection Interaction (man-machine interfaces) Modeling (medical, manufacturing, training, education) Organizing (database index, sorting/clustering) Fingerprint and biometrics 32

33 Why so difficult? 33

34 What is computer vision Why it is difficult Occlusion Deformation Scale Clutter Illumination Viewpoint Object pose Tons of classes and variants Often n:1 mapping Computationally expensive Full understanding of biological vision is missing 34

35 System overview 35

36 What is computer vision System overview Input: image(s) + labels Output: Semantic data, labels Digital image pixels usually have three channels [R,G,B] each [ ] + Location[x,y] Digital images are just vectors 36

37 What is computer vision System overview 1. Image acquisition (camera, sensors) 2. Pre-processing (sampling, noise reduction, augmentation) 3. Feature extraction (lines, edges, regions, points) 4. Detection and segmentation 5. Post-processing (verification, estimation, recognition) 6. Decision making -> Ability of a machine to step back and interpret the big picture of those pixels 37

38 Some history 38

39 What is computer vision History 1950s 2D imaging for statistical pattern recognition Theory of optical flow based on a fixed point towards which one moves 39

40 What is computer vision Traditional approaches Image processing Histograms Filtering Stitching Thresholding... 40

41 What is computer vision History 1960s Desire to extract 3D structure from 2D images for scene understanding Began at pioneering AI universities to mimic human visual system as stepping stone for intelligent robots Summer vision project at MIT: attach camera to computer and having it describe what it saw 41

42 What is computer vision History: summer vision 1966 Given to 10 undergraduate students an attempt to use our summer workers effectively construction of a significant part of a visual system task can be segmented into sub-problems participate in the construction of a system complex enough to be a real landmark in the development of pattern recognition 42

43 What is computer vision History: summer vision 1966 Goal: analyse scenes and identify objects Structure of system: Region proposal Property lists for regions Boundary construction Match with properties Segment Basic foreground/background segmentation with simple objects (cubes, cylinders,.) 43

44 What is computer vision History: summer vision 1966 Unlike general intelligence, computer vision seemed tractable Amusing anecdote, but it did never aimed to solve computer vision Computer vision today differs from what it was thought to be in

45 What is computer vision History 1970s Formed many algorithms that exist today Edges, lines and objects as interconnected structures 45

46 What is computer vision Traditional approaches Edge detection based on Brightness Gradients Geometry Illumination 46

47 What is computer vision Traditional approaches - part based detector Objects composed of features of parts and their spatial relationship Challenge: how to define and combine 47

48 What is computer vision History 1980s More rigorous mathematical analysis and quantitative aspects Optical character recognition Sliding window approaches Usage of artificial neural networks 48

49 What is computer vision Traditional approaches - HOG detection (histogram of oriented gradients) Concept in 80s but used only in 2005 Create HOG descriptors (object generalizations) One feature vector per object Train with SVM Sliding scales 49

50 What is computer vision Traditional approaches - HOG detection (histogram of oriented gradients) Computation of HOG descriptors: 1. Compute gradients 2. Compute histograms on cells 3. Normalize histograms 4. Concatenate histograms Requires a lot of engineering Must build ensembles of feature descriptors 50

51 What is computer vision History 1990s Significant interaction with computer graphics (rendering, morphing, stitching) Approaches using statistical learning Eigenface (Ghostfaces) through principal component analysis (PCA) 51

52 What is computer vision Traditional approaches - deformable parts model (DPM) Objects constructed by its parts First match whole object, then refine on the parts HOG + part-based + modern features Slow but good at difficult objects Involves many heuristics 52

53 What is computer vision Features Feature points Small area of pixels with certain properties Feature detection Use features for identification Activate if object present Examples: Lines, edges, colours, blobs, Animals, faces, cars,... 53

54 What is computer vision Traditional approaches - classical recognition Init: extract features for objects in different scales, colours, orientations, rotations, occlusion levels Inference: extract features from query image and find closest match in database or train a classifier Computationally expensive (hundreds of features in image, millions in database) and complex due to errors and mismatches 54

55 What is computer vision History Before the new era Bags of features Handcrafted ensembles Feat. 1 Input Feat. 2 Final Decision Feat. n Feature Extraction 55

56 The new era of computer vision 56

57 Artificial neural networks Fundamentals - artificial neuron Elementary building block Inspired by biological neurons Mathematical function y=f(wx+b) Learnable weights 57

58 Artificial neural networks Fundamentals - artificial neural networks Collection of neurons organized in layers Universal approximators Fully-connected network here 58

59 Artificial neural networks Fundamentals - training Basically an optimization problem Find minimum of a loss function by an iterative process (training) Designing the loss function is sometimes tricky 59

60 Artificial neural networks Fundamentals - training Simple optimizer algorithm: 1. Forward pass with a batch of data 2. Calculate error between actual and wanted output 3. Nudge weights in proportion to error into the right direction (same data would result in smaller error) 4. Repeat until convergence 60

61 Artificial neural networks Fundamentals - CNN Local neighborhood contributes to activation Exploit spatial information Hierarchical feature extractors Less parameters input filters receptive field activation 61

62 Artificial neural networks Fundamentals - CNN Filter of size 3x3 applied to an input of 7x7 62

63 Artificial neural networks Fundamentals - pooling Max-pooling Dimension reduction/adaption Existence is more important than location 63

64 Artificial neural networks Fundamentals - pooling Zero-padding Controlling dimensions 64

65 Artificial neural networks Fundamentals - general network architecture Input image... Final decision convolutional layers 65

66 Artificial neural networks Fundamentals - hierarchical feature extractors First layers Deeper layers Activations for: Lines, edges, blobs, colours,... Parts of abstract objects Abstract objects 66

67 Modern history of object recognition 67

68 Benchmark Datasets - PASCAL VOC Classification and detection 27k images 20 classes person, bird, cat, cow, dog, horse, sheep, aeroplane, bicycle, boat, bus, car, motorbike, train, bottle, chair, dining table, potted plant, sofa, tv/ monitor 68

69 Benchmark Datasets - ImageNet Challenges on a subset of ImageNet 14kk labeled images 20k object categories ILSVRC* usually on 10k categories including 90 out of 120 dog breeds *ImageNet Large Scale Visual Recognition Challenge 69

70 Artificial neural networks Roadmap - AlexNet ILSVRC 2012 winner by a large margin from 25% to 16% Proved effectiveness of CNNs and kicked of a new era 8 layers, 650k neurons, 60kk parameters 70

71 Artificial neural networks Roadmap - ZFNet ILSVRC 2013 winner with a best top-5 error of 11.6% AlexNet but using smaller 7x7 kernels to keep more information in deeper layers 71

72 Artificial neural networks Roadmap - OverFeat ILSVRC 2013 localization winner Uses AlexNet on multi-scale input images with sliding window approach Accumulates bounding boxes for final detection (instead of non-max suppression) 72

73 Artificial neural networks Roadmap - RCNN (region based CNN) 2k proposals generated by selective search SVM trained for classification Multi-stage pipeline 73

74 Artificial neural networks Roadmap - VGGNet Not a winner but famous due to simplicity and effectiveness Replace large-kernel convolutions by stacking several small-kernel convolutions 74

75 Artificial neural networks Roadmap - InceptionNet (GoogleNet) ILSVRC 2014 winner Stacks up inception modules 22 layers, 5kk parameters 75

76 Artificial neural networks Roadmap - Fast RCNN Jointly learns region proposal and detection Employs a region of interest (RoI) that allows to reuse the computations 76

77 Artificial neural networks Roadmap - YOLO (you only look once) Directly predicts all objects and classes in one shot Very fast Processes images at ~40 FPS on a Titan X GPU First real-time state-of-the-art detector Divides input images into multiple grid cells which are then classified 77

78 Artificial neural networks Roadmap - ResNet (Microsoft) ILSVRC 2015 winner with a 3.6% error rate (human performance is 5-10%) Employs residual blocks which allows to build deep networks (hundreds of layers) Additional identity mapping 78

79 Artificial neural networks Roadmap - MultiBox Not a recognition network A region proposal network Popularized prior/anchor boxes (found through clustering) to predict offsets Much better strategy than starting the predictions with random coordinates Since then heuristic approaches have been gradually fading out and replaced 79

80 Artificial neural networks Roadmap - Faster RCNN Fast RCNN with heuristic region proposal replaced by region proposal network (RPN) inspired by MultiBox RPN shares full-image convolutional features with the detection network (cost-free region proposal) RPN uses attention mechanism to tell where to look ~5 FPS on a Titan K40 GPU End-to-end training 80

81 Artificial neural networks Roadmap - SSD (single shot multibox detector) SSD leverages the Faster RCNN s RPN to directly classify objects inside each prior box (similar to YOLO) Predicts category scores and box offsets for a fixed set of default bounding boxes Fixes the predefined grid cells used in YOLO by using multiple aspect ratios Produces predictions of different scales ~59 FPS 81

82 Artificial neural networks TensorFlow object detection API Open-source software library for machine learning applications Tensorflow Object Detection API A collection of pretrained models construct, train and deploy object detection models 82

83 Summary 83

84 Summary Human vs machine Humans are good at understanding the big picture Neural networks are good at details But they can be fooled... 84

85 Summary Computer vision is still difficult Need a large amount data Lots of engineering Trial and error Long training time Still lots of hyperparameter parameter tuning No general network (generalization not answered) Little mathematical foundation 85

86 Summary Computer vision is hard Despite all of these advances, the dream of having a computer interpret an image at the same level as a human remains unrealized 86

87 Thank You Stanislav Frolov Big Data Engineer inovex GmbH Lindberghstraße München

Object Detection Based on Deep Learning

Object 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 information

Spatial Localization and Detection. Lecture 8-1

Spatial Localization and Detection. Lecture 8-1 Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday

More information

Yiqi Yan. May 10, 2017

Yiqi Yan. May 10, 2017 Yiqi Yan May 10, 2017 P a r t I F u n d a m e n t a l B a c k g r o u n d s Convolution Single Filter Multiple Filters 3 Convolution: case study, 2 filters 4 Convolution: receptive field receptive field

More information

Unified, real-time object detection

Unified, real-time object detection Unified, real-time object detection Final Project Report, Group 02, 8 Nov 2016 Akshat Agarwal (13068), Siddharth Tanwar (13699) CS698N: Recent Advances in Computer Vision, Jul Nov 2016 Instructor: Gaurav

More information

CPSC340. State-of-the-art Neural Networks. Nando de Freitas November, 2012 University of British Columbia

CPSC340. State-of-the-art Neural Networks. Nando de Freitas November, 2012 University of British Columbia CPSC340 State-of-the-art Neural Networks Nando de Freitas November, 2012 University of British Columbia Outline of the lecture This lecture provides an overview of two state-of-the-art neural networks:

More information

Object Detection. CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR

Object 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 information

Category-level localization

Category-level localization Category-level localization Cordelia Schmid Recognition Classification Object present/absent in an image Often presence of a significant amount of background clutter Localization / Detection Localize object

More information

INTRODUCTION TO DEEP LEARNING

INTRODUCTION TO DEEP LEARNING INTRODUCTION TO DEEP LEARNING CONTENTS Introduction to deep learning Contents 1. Examples 2. Machine learning 3. Neural networks 4. Deep learning 5. Convolutional neural networks 6. Conclusion 7. Additional

More information

Classification of objects from Video Data (Group 30)

Classification 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 information

Object Detection on Self-Driving Cars in China. Lingyun Li

Object Detection on Self-Driving Cars in China. Lingyun Li Object Detection on Self-Driving Cars in China Lingyun Li Introduction Motivation: Perception is the key of self-driving cars Data set: 10000 images with annotation 2000 images without annotation (not

More information

DEEP NEURAL NETWORKS FOR OBJECT DETECTION

DEEP NEURAL NETWORKS FOR OBJECT DETECTION DEEP NEURAL NETWORKS FOR OBJECT DETECTION Sergey Nikolenko Steklov Institute of Mathematics at St. Petersburg October 21, 2017, St. Petersburg, Russia Outline Bird s eye overview of deep learning Convolutional

More information

Extend the shallow part of Single Shot MultiBox Detector via Convolutional Neural Network

Extend the shallow part of Single Shot MultiBox Detector via Convolutional Neural Network Extend the shallow part of Single Shot MultiBox Detector via Convolutional Neural Network Liwen Zheng, Canmiao Fu, Yong Zhao * School of Electronic and Computer Engineering, Shenzhen Graduate School of

More information

Lecture 5: Object Detection

Lecture 5: Object Detection Object Detection CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 5: Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 Traditional Object Detection Algorithms Region-based

More information

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Kyunghee Kim Stanford University 353 Serra Mall Stanford, CA 94305 kyunghee.kim@stanford.edu Abstract We use a

More information

Know your data - many types of networks

Know your data - many types of networks Architectures Know your data - many types of networks Fixed length representation Variable length representation Online video sequences, or samples of different sizes Images Specific architectures for

More information

Deep 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 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 information

Analysis: TextonBoost and Semantic Texton Forests. Daniel Munoz Februrary 9, 2009

Analysis: 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 information

Photo-realistic Renderings for Machines Seong-heum Kim

Photo-realistic Renderings for Machines Seong-heum Kim Photo-realistic Renderings for Machines 20105034 Seong-heum Kim CS580 Student Presentations 2016.04.28 Photo-realistic Renderings for Machines Scene radiances Model descriptions (Light, Shape, Material,

More information

Fuzzy Set Theory in Computer Vision: Example 3

Fuzzy 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 information

Real-time Object Detection CS 229 Course Project

Real-time Object Detection CS 229 Course Project Real-time Object Detection CS 229 Course Project Zibo Gong 1, Tianchang He 1, and Ziyi Yang 1 1 Department of Electrical Engineering, Stanford University December 17, 2016 Abstract Objection detection

More information

YOLO9000: Better, Faster, Stronger

YOLO9000: Better, Faster, Stronger YOLO9000: Better, Faster, Stronger Date: January 24, 2018 Prepared by Haris Khan (University of Toronto) Haris Khan CSC2548: Machine Learning in Computer Vision 1 Overview 1. Motivation for one-shot object

More information

Deformable Part Models

Deformable Part Models CS 1674: Intro to Computer Vision Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 9, 2016 Today: Object category detection Window-based approaches: Last time: Viola-Jones

More information

OBJECT DETECTION HYUNG IL KOO

OBJECT DETECTION HYUNG IL KOO OBJECT DETECTION HYUNG IL KOO INTRODUCTION Computer Vision Tasks Classification + Localization Classification: C-classes Input: image Output: class label Evaluation metric: accuracy Localization Input:

More information

An Exploration of Computer Vision Techniques for Bird Species Classification

An Exploration of Computer Vision Techniques for Bird Species Classification An Exploration of Computer Vision Techniques for Bird Species Classification Anne L. Alter, Karen M. Wang December 15, 2017 Abstract Bird classification, a fine-grained categorization task, is a complex

More information

Inception Network Overview. David White CS793

Inception Network Overview. David White CS793 Inception Network Overview David White CS793 So, Leonardo DiCaprio dreams about dreaming... https://m.media-amazon.com/images/m/mv5bmjaxmzy3njcxnf5bml5banbnxkftztcwnti5otm0mw@@._v1_sy1000_cr0,0,675,1 000_AL_.jpg

More information

Beyond Sliding Windows: Object Localization by Efficient Subwindow Search

Beyond Sliding Windows: Object Localization by Efficient Subwindow Search Beyond Sliding Windows: Object Localization by Efficient Subwindow Search Christoph H. Lampert, Matthew B. Blaschko, & Thomas Hofmann Max Planck Institute for Biological Cybernetics Tübingen, Germany Google,

More information

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation

Object 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 information

Yield Estimation using faster R-CNN

Yield Estimation using faster R-CNN Yield Estimation using faster R-CNN 1 Vidhya Sagar, 2 Sailesh J.Jain and 2 Arjun P. 1 Assistant Professor, 2 UG Scholar, Department of Computer Engineering and Science SRM Institute of Science and Technology,Chennai,

More information

Optimizing Object Detection:

Optimizing Object Detection: Lecture 10: Optimizing Object Detection: A Case Study of R-CNN, Fast R-CNN, and Faster R-CNN Visual Computing Systems Today s task: object detection Image classification: what is the object in this image?

More information

Object detection with CNNs

Object 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

Computer Vision: Making machines see

Computer Vision: Making machines see Computer Vision: Making machines see Roberto Cipolla Department of Engineering http://www.eng.cam.ac.uk/~cipolla/people.html http://www.toshiba.eu/eu/cambridge-research- Laboratory/ Vision: what is where

More information

Advanced Video Analysis & Imaging

Advanced Video Analysis & Imaging Advanced Video Analysis & Imaging (5LSH0), Module 09B Machine Learning with Convolutional Neural Networks (CNNs) - Workout Farhad G. Zanjani, Clint Sebastian, Egor Bondarev, Peter H.N. de With ( p.h.n.de.with@tue.nl

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

Computer Vision. Introduction

Computer Vision. Introduction Computer Vision Introduction Filippo Bergamasco (filippo.bergamasco@unive.it) http://www.dais.unive.it/~bergamasco DAIS, Ca Foscari University of Venice Academic year 2016/2017 About this course Official

More information

Attributes. Computer Vision. James Hays. Many slides from Derek Hoiem

Attributes. Computer Vision. James Hays. Many slides from Derek Hoiem Many slides from Derek Hoiem Attributes Computer Vision James Hays Recap: Human Computation Active Learning: Let the classifier tell you where more annotation is needed. Human-in-the-loop recognition:

More information

Detection III: Analyzing and Debugging Detection Methods

Detection III: Analyzing and Debugging Detection Methods CS 1699: Intro to Computer Vision Detection III: Analyzing and Debugging Detection Methods Prof. Adriana Kovashka University of Pittsburgh November 17, 2015 Today Review: Deformable part models How can

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech

Convolutional 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 information

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren Kaiming He Ross Girshick Jian Sun Present by: Yixin Yang Mingdong Wang 1 Object Detection 2 1 Applications Basic

More information

Deep Learning for Object detection & localization

Deep Learning for Object detection & localization Deep Learning for Object detection & localization RCNN, Fast RCNN, Faster RCNN, YOLO, GAP, CAM, MSROI Aaditya Prakash Sep 25, 2018 Image classification Image classification Whole of image is classified

More information

Object Recognition II

Object Recognition II Object Recognition II Linda Shapiro EE/CSE 576 with CNN slides from Ross Girshick 1 Outline Object detection the task, evaluation, datasets Convolutional Neural Networks (CNNs) overview and history Region-based

More information

CS231N Section. Video Understanding 6/1/2018

CS231N 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 information

Semantic Pooling for Image Categorization using Multiple Kernel Learning

Semantic Pooling for Image Categorization using Multiple Kernel Learning Semantic Pooling for Image Categorization using Multiple Kernel Learning Thibaut Durand (1,2), Nicolas Thome (1), Matthieu Cord (1), David Picard (2) (1) Sorbonne Universités, UPMC Univ Paris 06, UMR 7606,

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning for Object Categorization 14.01.2016 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period

More information

PSU Student Research Symposium 2017 Bayesian Optimization for Refining Object Proposals, with an Application to Pedestrian Detection Anthony D.

PSU Student Research Symposium 2017 Bayesian Optimization for Refining Object Proposals, with an Application to Pedestrian Detection Anthony D. PSU Student Research Symposium 2017 Bayesian Optimization for Refining Object Proposals, with an Application to Pedestrian Detection Anthony D. Rhodes 5/10/17 What is Machine Learning? Machine learning

More information

Linear combinations of simple classifiers for the PASCAL challenge

Linear combinations of simple classifiers for the PASCAL challenge Linear combinations of simple classifiers for the PASCAL challenge Nik A. Melchior and David Lee 16 721 Advanced Perception The Robotics Institute Carnegie Mellon University Email: melchior@cmu.edu, dlee1@andrew.cmu.edu

More information

A THREE LAYERED MODEL TO PERFORM CHARACTER RECOGNITION FOR NOISY IMAGES

A THREE LAYERED MODEL TO PERFORM CHARACTER RECOGNITION FOR NOISY IMAGES INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONSAND ROBOTICS ISSN 2320-7345 A THREE LAYERED MODEL TO PERFORM CHARACTER RECOGNITION FOR NOISY IMAGES 1 Neha, 2 Anil Saroliya, 3 Varun Sharma 1,

More information

Image Processing (IP)

Image Processing (IP) Image Processing Pattern Recognition Computer Vision Xiaojun Qi Utah State University Image Processing (IP) Manipulate and analyze digital images (pictorial information) by computer. Applications: The

More information

LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH

LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH Università degli Studi dell'insubria Varese, Italy LEARNING OBJECT SEGMENTATION USING A MULTI NETWORK SEGMENT CLASSIFICATION APPROACH Simone Albertini Ignazio Gallo, Angelo Nodari, Marco Vanetti albertini.simone@gmail.com

More information

Structured Prediction using Convolutional Neural Networks

Structured 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 information

LEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS

LEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS LEARNING TO GENERATE CHAIRS WITH CONVOLUTIONAL NEURAL NETWORKS Alexey Dosovitskiy, Jost Tobias Springenberg and Thomas Brox University of Freiburg Presented by: Shreyansh Daftry Visual Learning and Recognition

More information

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the

More information

Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation Rich feature hierarchies for accurate object detection and semantic segmentation BY; ROSS GIRSHICK, JEFF DONAHUE, TREVOR DARRELL AND JITENDRA MALIK PRESENTER; MUHAMMAD OSAMA Object detection vs. classification

More information

Su et al. Shape Descriptors - III

Su et al. Shape Descriptors - III Su et al. Shape Descriptors - III Siddhartha Chaudhuri http://www.cse.iitb.ac.in/~cs749 Funkhouser; Feng, Liu, Gong Recap Global A shape descriptor is a set of numbers that describes a shape in a way that

More information

DeepLab: 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 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 information

Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network

Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network Anurag Arnab and Philip H.S. Torr University of Oxford {anurag.arnab, philip.torr}@eng.ox.ac.uk 1. Introduction

More information

Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation

Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation APPEARING IN IEEE TRANSACTIONS ON IMAGE PROCESSING, OCTOBER 2016 1 Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation Yuanzhouhan Cao, Chunhua Shen, Heng Tao Shen

More information

An Object Detection Algorithm based on Deformable Part Models with Bing Features Chunwei Li1, a and Youjun Bu1, b

An Object Detection Algorithm based on Deformable Part Models with Bing Features Chunwei Li1, a and Youjun Bu1, b 5th International Conference on Advanced Materials and Computer Science (ICAMCS 2016) An Object Detection Algorithm based on Deformable Part Models with Bing Features Chunwei Li1, a and Youjun Bu1, b 1

More information

Does the Brain do Inverse Graphics?

Does the Brain do Inverse Graphics? Does the Brain do Inverse Graphics? Geoffrey Hinton, Alex Krizhevsky, Navdeep Jaitly, Tijmen Tieleman & Yichuan Tang Department of Computer Science University of Toronto How to learn many layers of features

More information

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU, Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image

More information

Characterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager

Characterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager Characterization and Benchmarking of Deep Learning Natalia Vassilieva, PhD Sr. Research Manager Deep learning applications Vision Speech Text Other Search & information extraction Security/Video surveillance

More information

Visual features detection based on deep neural network in autonomous driving tasks

Visual features detection based on deep neural network in autonomous driving tasks 430 Fomin I., Gromoshinskii D., Stepanov D. Visual features detection based on deep neural network in autonomous driving tasks Ivan Fomin, Dmitrii Gromoshinskii, Dmitry Stepanov Computer vision lab Russian

More information

Dynamic Routing Between Capsules

Dynamic 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 information

CAP 6412 Advanced Computer Vision

CAP 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 information

CS 523: Multimedia Systems

CS 523: Multimedia Systems CS 523: Multimedia Systems Angus Forbes creativecoding.evl.uic.edu/courses/cs523 Today - Convolutional Neural Networks - Work on Project 1 http://playground.tensorflow.org/ Convolutional Neural Networks

More information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 551 Applied Machine Learning Lecture 16: Deep Learning COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all

More information

Overview of Computer Vision. CS308 Data Structures

Overview of Computer Vision. CS308 Data Structures Overview of Computer Vision CS308 Data Structures What is Computer Vision? Deals with the development of the theoretical and algorithmic basis by which useful information about the 3D world can be automatically

More information

24 hours of Photo Sharing. installation by Erik Kessels

24 hours of Photo Sharing. installation by Erik Kessels 24 hours of Photo Sharing installation by Erik Kessels And sometimes Internet photos have useful labels Im2gps. Hays and Efros. CVPR 2008 But what if we want more? Image Categorization Training Images

More information

Learning Representations for Visual Object Class Recognition

Learning Representations for Visual Object Class Recognition Learning Representations for Visual Object Class Recognition Marcin Marszałek Cordelia Schmid Hedi Harzallah Joost van de Weijer LEAR, INRIA Grenoble, Rhône-Alpes, France October 15th, 2007 Bag-of-Features

More information

Optimizing Object Detection:

Optimizing Object Detection: Lecture 10: Optimizing Object Detection: A Case Study of R-CNN, Fast R-CNN, and Faster R-CNN and Single Shot Detection Visual Computing Systems Today s task: object detection Image classification: what

More information

Chapter 9 Object Tracking an Overview

Chapter 9 Object Tracking an Overview Chapter 9 Object Tracking an Overview The output of the background subtraction algorithm, described in the previous chapter, is a classification (segmentation) of pixels into foreground pixels (those belonging

More information

Using Machine Learning for Classification of Cancer Cells

Using Machine Learning for Classification of Cancer Cells Using Machine Learning for Classification of Cancer Cells Camille Biscarrat University of California, Berkeley I Introduction Cell screening is a commonly used technique in the development of new drugs.

More information

When Big Datasets are Not Enough: The need for visual virtual worlds.

When Big Datasets are Not Enough: The need for visual virtual worlds. When Big Datasets are Not Enough: The need for visual virtual worlds. Alan Yuille Bloomberg Distinguished Professor Departments of Cognitive Science and Computer Science Johns Hopkins University Computational

More information

Object Detection. Part1. Presenter: Dae-Yong

Object Detection. Part1. Presenter: Dae-Yong Object Part1 Presenter: Dae-Yong Contents 1. What is an Object? 2. Traditional Object Detector 3. Deep Learning-based Object Detector What is an Object? Subset of Object Recognition What is an Object?

More information

Object Category Detection. Slides mostly from Derek Hoiem

Object Category Detection. Slides mostly from Derek Hoiem Object Category Detection Slides mostly from Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical template matching with sliding window Part-based Models

More information

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep 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 information

Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014

Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014 Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars BMVC 2014 Problem Definition Viewpoint estimation: Given an image, predicting viewpoint for object of

More information

Classification and Detection in Images. D.A. Forsyth

Classification and Detection in Images. D.A. Forsyth Classification and Detection in Images D.A. Forsyth Classifying Images Motivating problems detecting explicit images classifying materials classifying scenes Strategy build appropriate image features train

More information

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro CMU 15-781 Lecture 18: Deep learning and Vision: Convolutional neural networks Teacher: Gianni A. Di Caro DEEP, SHALLOW, CONNECTED, SPARSE? Fully connected multi-layer feed-forward perceptrons: More powerful

More information

The Hilbert Problems of Computer Vision. Jitendra Malik UC Berkeley & Google, Inc.

The Hilbert Problems of Computer Vision. Jitendra Malik UC Berkeley & Google, Inc. The Hilbert Problems of Computer Vision Jitendra Malik UC Berkeley & Google, Inc. This talk The computational power of the human brain Research is the art of the soluble Hilbert problems, circa 2004 Hilbert

More information

COMP 102: Computers and Computing

COMP 102: Computers and Computing COMP 102: Computers and Computing Lecture 23: Computer Vision Instructor: Kaleem Siddiqi (siddiqi@cim.mcgill.ca) Class web page: www.cim.mcgill.ca/~siddiqi/102.html What is computer vision? Broadly speaking,

More information

Deep Learning for Computer Vision II

Deep Learning for Computer Vision II IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L

More information

Why study Computer Vision?

Why study Computer Vision? Why study Computer Vision? Images and movies are everywhere Fast-growing collection of useful applications building representations of the 3D world from pictures automated surveillance (who s doing what)

More information

3 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, 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 information

Computer Vision Lecture 16

Computer 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 information

Deep Convolutional Neural Networks. Nov. 20th, 2015 Bruce Draper

Deep Convolutional Neural Networks. Nov. 20th, 2015 Bruce Draper Deep Convolutional Neural Networks Nov. 20th, 2015 Bruce Draper Background: Fully-connected single layer neural networks Feed-forward classification Trained through back-propagation Example Computer Vision

More information

CS 1674: Intro to Computer Vision. Object Recognition. Prof. Adriana Kovashka University of Pittsburgh April 3, 5, 2018

CS 1674: Intro to Computer Vision. Object Recognition. Prof. Adriana Kovashka University of Pittsburgh April 3, 5, 2018 CS 1674: Intro to Computer Vision Object Recognition Prof. Adriana Kovashka University of Pittsburgh April 3, 5, 2018 Different Flavors of Object Recognition Semantic Segmentation Classification + Localization

More information

Real Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications

Real Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications Real Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications Anand Joshi CS229-Machine Learning, Computer Science, Stanford University,

More information

The SIFT (Scale Invariant Feature

The SIFT (Scale Invariant Feature The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical

More information

Find that! Visual Object Detection Primer

Find that! Visual Object Detection Primer Find that! Visual Object Detection Primer SkTech/MIT Innovation Workshop August 16, 2012 Dr. Tomasz Malisiewicz tomasz@csail.mit.edu Find that! Your Goals...imagine one such system that drives information

More information

Feature-Fused SSD: Fast Detection for Small Objects

Feature-Fused SSD: Fast Detection for Small Objects Feature-Fused SSD: Fast Detection for Small Objects Guimei Cao, Xuemei Xie, Wenzhe Yang, Quan Liao, Guangming Shi, Jinjian Wu School of Electronic Engineering, Xidian University, China xmxie@mail.xidian.edu.cn

More information

Single-Shot Refinement Neural Network for Object Detection -Supplementary Material-

Single-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 information

What is Computer Vision? Introduction. We all make mistakes. Why is this hard? What was happening. What do you see? Intro Computer Vision

What is Computer Vision? Introduction. We all make mistakes. Why is this hard? What was happening. What do you see? Intro Computer Vision What is Computer Vision? Trucco and Verri (Text): Computing properties of the 3-D world from one or more digital images Introduction Introduction to Computer Vision CSE 152 Lecture 1 Sockman and Shapiro:

More information

Object Detection. TA : Young-geun Kim. Biostatistics Lab., Seoul National University. March-June, 2018

Object Detection. TA : Young-geun Kim. Biostatistics Lab., Seoul National University. March-June, 2018 Object Detection TA : Young-geun Kim Biostatistics Lab., Seoul National University March-June, 2018 Seoul National University Deep Learning March-June, 2018 1 / 57 Index 1 Introduction 2 R-CNN 3 YOLO 4

More information

Regionlet Object Detector with Hand-crafted and CNN Feature

Regionlet 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

Computer Vision Lecture 16

Computer 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 information

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai COMPUTER VISION Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai 600036. Email: sdas@iitm.ac.in URL: //www.cs.iitm.ernet.in/~sdas 1 INTRODUCTION 2 Human Vision System (HVS) Vs.

More information

Deep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon

Deep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon Deep Learning For Video Classification Presented by Natalie Carlebach & Gil Sharon Overview Of Presentation Motivation Challenges of video classification Common datasets 4 different methods presented in

More information

CS5670: Computer Vision

CS5670: Computer Vision CS5670: Computer Vision Noah Snavely Lecture 4: Harris corner detection Szeliski: 4.1 Reading Announcements Project 1 (Hybrid Images) code due next Wednesday, Feb 14, by 11:59pm Artifacts due Friday, Feb

More information

Artificial Intelligence Introduction Handwriting Recognition Kadir Eren Unal ( ), Jakob Heyder ( )

Artificial Intelligence Introduction Handwriting Recognition Kadir Eren Unal ( ), Jakob Heyder ( ) Structure: 1. Introduction 2. Problem 3. Neural network approach a. Architecture b. Phases of CNN c. Results 4. HTM approach a. Architecture b. Setup c. Results 5. Conclusion 1.) Introduction Artificial

More information