Visuelle Perzeption für Mensch- Maschine Schnittstellen

Size: px
Start display at page:

Download "Visuelle Perzeption für Mensch- Maschine Schnittstellen"

Transcription

1 Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) Edgar Seemann,

2 Computer Vision: People Detection IV WS 2009/10 Dr. Edgar Seemann Edgar Seemann,

3 Termine (1) Termine Thema Introduction, Applications Basics: Cameras, Transformations, Color Basics: Image Processing Basics: Pattern recognition Computer Vision: Tasks, Challenges, Learning, Performance measures Face Detection I: Color, Edges (Birchfield) Project 1: Intro + Programming tips Face Detection II: ANNs, SVM, Viola & Jones Project 1: Questions Face Recognition I: Traditional Approaches, Eigenfaces, Fisherfaces, EBGM Face Recognition II Head Pose Estimation: Model-based, NN, Texture Mapping, Focus of Attention People Detection I People Detection II Project 1: Student Presentations, Project 2: Intro People Detection III (Part-Based Models) People Detection IV Scene Context, Geometry, Stereo and Optical Flow TBA Edgar Seemann,

4 Local Features Edgar Seemann,

5 So far Parts were defined manually Parts represented the semantic structure i.e. face, leg etc. Questions: Do these parts decompose the variability in an optimal way? Must the parts have a semantic meaning Should we use smaller/larger parts? Can we find parts automatically? Edgar Seemann,

6 Requirements for part decomposition Repeatable i.e. we should be able to find the part despite articulation or image transformations (e.g. rotation, perspective, lighting) Distinctive Part should not be confounded with other parts The regions should contain an interesting structure Compact Typically no lengthy or strangely shaped parts Efficient It should be computationally inexpensive to detect or represent part Cover parts need to sufficiently cover the object Edgar Seemann,

7 N pixels A 1 N pixels A 2 A 3 f A e.g. color Similarity measure d( f A, f B ) < T Approach B 1 B 2 f B e.g. color Edgar Seemann, B 3 1. Find a set of distinctive keypoints 2. Define a region around each keypoint 3. Extract and normalize the region content 4. Compute a local descriptor from the normalized region 5. Match local descriptors

8 Hessian Detector [Beaudet78] Hessian determinant I xx Hessian ( I ) = I I xx xy I I xy yy I xy I yy 2 det( Hessian ( I )) = I xx I yy I xy In Matlab: I I xx. yy ( I xy )^2 Edgar Seemann,

9 Automatic Scale Selection Function responses for increasing scale (scale signature) ( I i 1 K i ( x, σ )) I i Ki (, )) f m f m ( 1 x σ Edgar Seemann,

10 Results: Laplacian-of-Gaussian Edgar Seemann,

11 Implicit Shape Model Edgar Seemann,

12 Implicit Shape Model (ISM) Basic ideas 1. Automatically learn a large number of local parts that occur on the object Also referred to as visual vocabulary or appearance codebook 2. Learn a star-topology structural model Features are considered independent given obj. center x 6 x 5 x 1 x 4 x 2 x 3 Edgar Seemann, K. Grauman, B. Leibe 13

13 Visual Vocabulary / Appearance Codebook Edgar Seemann,

14 Visual Vocabulary Detect keypoints on all training examples Extract feature descriptions around keypoints Result: A large set of local image descriptors occurring on people Edgar Seemann,

15 Visual Vocabulary Group visually similar local descriptors i.e. parts that are reoccurring Parts, that occur only once are discarded (they could result from noise or unusual structures) Edgar Seemann,

16 Side Note: Grouping Algorithms Partitional Clustering K-Means Gaussian Mixture Clustering (EM) Hierarchical or Agglomerative Clustering Single-Link Group Average Ward s method (minimum variance) Edgar Seemann,

17 Complexity Standard Approach: Time complexity: O(n 2 logn) Compute distance matrix Consecutively merge the two most similar clusters Space complexity: O(n 2 ) Edgar Seemann,

18 Reciprocal Nearest Neighbor (RNN) RNN Algorithm [de Rham 80, Benzecri 82] Time complexity: O(n 2 ) Space complexity: O(n) Requirement: reducibility property [Bruynooghe 77] Edgar Seemann,

19 Space Complexity Note, that space complexity is quite important for clustering large data sets Example: data points Standard distance matrix contains: 10 5 *10 5 =10 10 entries -> ~40 GB if one entry has 32bit -> Does your PC have enough RAM? Edgar Seemann,

20 Clustering Hierarchy Agglomerative clustering produces a hierarchy Difficult question: where to stop? But Ideally, clusters should be visually compact. Distance value depends on feature dimensionality. Appropriate ratio #features/#clusters depends on data set and interest point detector. Needs to be selected for each detector/descriptor combination! Edgar Seemann,

21 Visual Vocabulary Vocabulary size ~10000 clusters Probabilistic votes decide, whether part is important or not Edgar Seemann,

22 Learning Spatial Structure: Star -Model Edgar Seemann,

23 Implicit Shape Model - Representation 1. Learn appearance codebook Extract local features at interest points Agglomerative clustering codebook 2. Learn spatial distributions Match codebook to training images Record matching positions on object Sparse representation of the object appearance Edgar Seemann,

24 Training: Spatial Occurrence (Star-Model) 1. Record spatial occurrence Match codebook to training images Record occurrence distributions with respect to object center Location (x, y) and scale y y s x y y s x Star-Model s s x x Spatial occurrence distributions Edgar Seemann,

25 Occurrence Distribution For each codebook entry, we obtain a nonparametric probability distribution of its position relative to the object center With c i a codebook entry λ=(λ x, λ y, λ s ) the relative position and scale Edgar Seemann,

26 Remember: Generalized Hough Transform [Ballard81] Choose reference point for the contour (e.g. center) For each point on the contour remember where it is located w.r.t. to the reference point Remember radius r and angle φ relative to the contour tangent Recognition: whenever you find a contour point, calculate the tangent angle and vote for all possible reference points Instead of reference point, can also vote for transformation The same idea can be used with local features! Edgar Seemann, Slide credit: Bernt Schiele

27 Generalized Hough Transform For every feature, store possible occurrences For new image, let the matched features vote for possible object positions Object identity Pose Relative position Edgar Seemann,

28 Probabilistic Gen. Hough Transform Exact correspondences Prob. match to object part NN matching Soft matching Feature location on obj. Part location distribution Uniform votes Probabilistic vote weighting Quantized Hough array Continuous Hough space Edgar Seemann,

29 Detection Procedure Edgar Seemann,

30 Recognition: ISM Detection Procedure Image Probabilistic Voting y 3D Voting Space s Detection Confidences Segmentation Back-Projection Edgar Seemann, x

31 Probabilistic Formulation Descriptor contribution: With e an extracted image descriptor l the position of the descriptor in the image Marginalization over all found descriptors: Edgar Seemann,

32 Scale Voting: Efficient Computation s y Scale votes s y Binned accum. array Mean-Shift formulation for refinement Scale-adaptive balloon density estimator s y x Candidate maxima s y x Refinement (MSME) Edgar Seemann,

33 Figure-Ground Segmentation Edgar Seemann,

34 Occurrence distributions Adding local segmentation masks y y s s x x y y s s x x Spatial occurrence distributions + local figure-ground labels Edgar Seemann,

35 Figure-Ground Segmentation Influence of descriptor on an object hypotheses: Figure probability for a hypothesis: Segmentation information Influence on object hypothesis Edgar Seemann,

36 Figure-Ground Segmentation Final segmentation value: Edgar Seemann,

37 Overlapping hypotheses Edgar Seemann,

38 Minimum Description Length (MDL) Reasoning Savings term: S area : #pixels N in segmentation S model : model cost, assumed constant S error : estimate of error Error term: Overlapping hypotheses: Edgar Seemann,

39 MDL based Verification Secondary hypotheses Desired property of algorithm! robustness to occlusion Standard solution: reject based on bounding box Problematic - may lead to missing detections! Use segmentations to resolve ambiguities instead Edgar Seemann, Leibe, Leonardis, Schiele, 04

40 Extensions and Evaluation Edgar Seemann,

41 Outline 1. Image Descriptors and Interest Points 2. Body Articulations 3. Cross-Articulation Learning 4. Discriminative Hypothesis Verification 5. Instance-Specific Models Edgar Seemann,

42 Star-Model and Body Articulations Flexibility of star-model has several drawbacks Hypotheses may contain superfluous body parts Score of neighboring hypotheses may be reduced False alarms may occur on background clutter Idea: Use global constraints to remove inconsistent features 1. Silhouette verification 2. 4D-ISM Edgar Seemann,

43 1. Chamfer Verification Candidate silhouettes Match to image 1. Rescale image region 2. Distance transform 3. Chamfer matching Problem Chamfer matching not robust enough! Edgar Seemann,

44 Chamfer Verification (2) Candidate silhouettes Match to segmentation 1. Rescale segmentation 2. Bhattacharyya coefficient Combined match Weighted sum Edgar Seemann,

45 Effect of the Verification Stage Edgar Seemann,

46 Demo Edgar Seemann,

47 2. 4D-ISM - Learning Occurrences 1. Identify typical articulations by silhouettes clustering 2. Add silhouette information to occurrences 3D Occurrence Distributions 4D Occurrence Distributions y y Resulting articulation clusters s Vote v = (x, y, scale) x Pedestrian silhouettes Vote v = (x, y, scale, articulation) Edgar Seemann, s x

48 Recognition: 4D-ISM Voting Procedure Silhouette Clustering 4D Voting Space y s Articulation 1 x y Resulting hypotheses are consistent w.r.t body articulations s Articulation N x Edgar Seemann,

49 Results 4D-ISM Silhouette verification 4D-ISM 6% improvement 20% better precision at 80% recall Purely global constraints are often too strict Edgar Seemann,

50 Advantages and Disadvantages 4D- Successfully removes false alarms Estimates body articulation ISM 4D-ISM can handle partial occlusions better (compared to silhouette verification) Each training image contributes only to one articulation Number of required training images increases linearly with the number of articulations Edgar Seemann,

51 Outline 1. Image Descriptors and Interest Points 2. Body Articulations 3. Cross-Articulation Learning Transfer knowledge between articulations 4. Discriminative Hypothesis Verification 5. Instance-Specific Models Edgar Seemann,

52 Cross-Articulation Learning Share descriptor occurrences across articulations Less training data needed Better generalization Need to learn for each observed feature, on which articulations it could occur Edgar Seemann,

53 Training: Sharing Features Idea: Look at a larger local context around features Retrieve silhouettes which are locally similar Share corresponding feature between silhouettes For context radius r=object size we obtain 4D-ISM as a special case Edgar Seemann,

54 Model Comparison Standard ISM 4D-ISM Cross-Articulation Shape Occurrences Shape distribution Occurrence distribution (x, y, scale) Codebook Edgar Seemann,

55 Results Cross-Articulation Sharing features can improve performance by up to 10% Tested different context descriptors and sizes Edgar Seemann,

56 Advantages Cross-Articulation Available training data used more effectively Local context size and representation is independent of feature descriptor Edgar Seemann,

57 Outline 1. Image Descriptors and Interest Points 2. Body Articulations 3. Cross-Articulation Learning 4. Discriminative Hypothesis Verification Verify pedestrian hypothesis with a discriminative classifier 5. Instance-Specific Models Edgar Seemann,

58 Support Vector Machine (SVM) Verification Extract correct and false detections of the ISM Discriminate between correct and false examples Use an SVM with a Local Kernel [Wallraven et al. 03, Fritz et al. 05] ISM False Alarms Correct Pedestrians Edgar Seemann,

59 Results SVM Verification Precision of 98.6% at 80% recall At 80% recall: 1 false alarm in 90 images Compared to 528 false alarms for the standard approach Edgar Seemann,

60 Advantages SVM Verification Increased detection precision SVM has to solve an easier problem than actual detection Common representation for generative and discriminative model Detection works best for relatively high-resolution pedestrians Edgar Seemann,

61 Multi-Viewpoint Detections Edgar Seemann,

62 Example Detections and Articulations Detections Corresponding articulations Edgar Seemann,

63 Crowded Scene Movie Single frame detection! No temporal information used! Edgar Seemann,

64 Outline 1. Image Descriptors and Interest Points 2. Body Articulations 3. Cross-Articulation Learning 4. Discriminative Hypothesis Verification 5. Instance-Specific Models Facilitate detection in video sequences Adapt general model to a specific pedestrian appearance General model Instance model Edgar Seemann,

65 Instance-Specific models Learn the specific appearance of a person in the first frames of a sequence Model is build from the results of the general person detector Use a specialized model in subsequent frames General model Instance model Edgar Seemann,

66 Instance-Specific models and articulation Edgar Seemann,

67 Evaluation Results Requires appropriate normalization of the specific models I.e. ensure comparability of models Edgar Seemann,

68 Instance-Specific Models Learn the appearances of pedestrians in a video sequence from detections of the general model Follow pedestrians even through longer periods of occlusion No background subtraction used! Edgar Seemann,

69 Summary Many factors influence the performance of a detection algorithm Interest Point Detector Feature Descriptor Verification stages Non-Maximum Suppression Using a flexible and powerful object model enables many improvement, which could not be applied as easily to standard discriminative methods Edgar Seemann,

70 End of Lecture Edgar Seemann,

Visuelle Perzeption für Mensch- Maschine Schnittstellen

Visuelle Perzeption für Mensch- Maschine Schnittstellen Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de

More information

Visuelle Perzeption für Mensch- Maschine Schnittstellen

Visuelle Perzeption für Mensch- Maschine Schnittstellen Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de

More information

Patch-based Object Recognition. Basic Idea

Patch-based Object Recognition. Basic Idea Patch-based Object Recognition 1! Basic Idea Determine interest points in image Determine local image properties around interest points Use local image properties for object classification Example: Interest

More information

Previously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011

Previously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011 Previously Part-based and local feature models for generic object recognition Wed, April 20 UT-Austin Discriminative classifiers Boosting Nearest neighbors Support vector machines Useful for object recognition

More information

Part-based and local feature models for generic object recognition

Part-based and local feature models for generic object recognition Part-based and local feature models for generic object recognition May 28 th, 2015 Yong Jae Lee UC Davis Announcements PS2 grades up on SmartSite PS2 stats: Mean: 80.15 Standard Dev: 22.77 Vote on piazza

More information

Object Detection. Sanja Fidler CSC420: Intro to Image Understanding 1/ 1

Object Detection. Sanja Fidler CSC420: Intro to Image Understanding 1/ 1 Object Detection Sanja Fidler CSC420: Intro to Image Understanding 1/ 1 Object Detection The goal of object detection is to localize objects in an image and tell their class Localization: place a tight

More information

Computer Vision for HCI. Topics of This Lecture

Computer Vision for HCI. Topics of This Lecture Computer Vision for HCI Interest Points Topics of This Lecture Local Invariant Features Motivation Requirements, Invariances Keypoint Localization Features from Accelerated Segment Test (FAST) Harris Shi-Tomasi

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 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

Part based models for recognition. Kristen Grauman

Part based models for recognition. Kristen Grauman Part based models for recognition Kristen Grauman UT Austin Limitations of window-based models Not all objects are box-shaped Assuming specific 2d view of object Local components themselves do not necessarily

More information

Beyond Bags of features Spatial information & Shape models

Beyond Bags of features Spatial information & Shape models Beyond Bags of features Spatial information & Shape models Jana Kosecka Many slides adapted from S. Lazebnik, FeiFei Li, Rob Fergus, and Antonio Torralba Detection, recognition (so far )! Bags of features

More information

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014

SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image

More information

Part-Based Models for Object Class Recognition Part 2

Part-Based Models for Object Class Recognition Part 2 High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object

More information

Part-Based Models for Object Class Recognition Part 2

Part-Based Models for Object Class Recognition Part 2 High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object

More information

Visuelle Perzeption für Mensch- Maschine Schnittstellen

Visuelle Perzeption für Mensch- Maschine Schnittstellen Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2008 Dr. Rainer Stiefelhagen Dr. Edgar Seemann Interactive Systems Laboratories Universität Karlsruhe (TH) http://isl.ira.uka.de/msmmi/teaching/visionhci

More information

Object Category Detection: Sliding Windows

Object Category Detection: Sliding Windows 04/10/12 Object Category Detection: Sliding Windows Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Today s class: Object Category Detection Overview of object category detection Statistical

More information

Outline 7/2/201011/6/

Outline 7/2/201011/6/ Outline Pattern recognition in computer vision Background on the development of SIFT SIFT algorithm and some of its variations Computational considerations (SURF) Potential improvement Summary 01 2 Pattern

More information

Category vs. instance recognition

Category vs. instance recognition Category vs. instance recognition Category: Find all the people Find all the buildings Often within a single image Often sliding window Instance: Is this face James? Find this specific famous building

More information

Multiple-Choice Questionnaire Group C

Multiple-Choice Questionnaire Group C Family name: Vision and Machine-Learning Given name: 1/28/2011 Multiple-Choice naire Group C No documents authorized. There can be several right answers to a question. Marking-scheme: 2 points if all right

More information

SCALE INVARIANT FEATURE TRANSFORM (SIFT)

SCALE INVARIANT FEATURE TRANSFORM (SIFT) 1 SCALE INVARIANT FEATURE TRANSFORM (SIFT) OUTLINE SIFT Background SIFT Extraction Application in Content Based Image Search Conclusion 2 SIFT BACKGROUND Scale-invariant feature transform SIFT: to detect

More information

CAP 5415 Computer Vision Fall 2012

CAP 5415 Computer Vision Fall 2012 CAP 5415 Computer Vision Fall 01 Dr. Mubarak Shah Univ. of Central Florida Office 47-F HEC Lecture-5 SIFT: David Lowe, UBC SIFT - Key Point Extraction Stands for scale invariant feature transform Patented

More information

Person Detection in Images using HoG + Gentleboost. Rahul Rajan June 1st July 15th CMU Q Robotics Lab

Person Detection in Images using HoG + Gentleboost. Rahul Rajan June 1st July 15th CMU Q Robotics Lab Person Detection in Images using HoG + Gentleboost Rahul Rajan June 1st July 15th CMU Q Robotics Lab 1 Introduction One of the goals of computer vision Object class detection car, animal, humans Human

More information

Object detection using non-redundant local Binary Patterns

Object detection using non-redundant local Binary Patterns University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2010 Object detection using non-redundant local Binary Patterns Duc Thanh

More information

Introduction. Introduction. Related Research. SIFT method. SIFT method. Distinctive Image Features from Scale-Invariant. Scale.

Introduction. Introduction. Related Research. SIFT method. SIFT method. Distinctive Image Features from Scale-Invariant. Scale. Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe presented by, Sudheendra Invariance Intensity Scale Rotation Affine View point Introduction Introduction SIFT (Scale Invariant Feature

More information

Local features: detection and description. Local invariant features

Local features: detection and description. Local invariant features Local features: detection and description Local invariant features Detection of interest points Harris corner detection Scale invariant blob detection: LoG Description of local patches SIFT : Histograms

More information

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)

More information

Detecting and Segmenting Humans in Crowded Scenes

Detecting and Segmenting Humans in Crowded Scenes Detecting and Segmenting Humans in Crowded Scenes Mikel D. Rodriguez University of Central Florida 4000 Central Florida Blvd Orlando, Florida, 32816 mikel@cs.ucf.edu Mubarak Shah University of Central

More information

Object Recognition with Invariant Features

Object Recognition with Invariant Features Object Recognition with Invariant Features Definition: Identify objects or scenes and determine their pose and model parameters Applications Industrial automation and inspection Mobile robots, toys, user

More information

Lecture 8: Fitting. Tuesday, Sept 25

Lecture 8: Fitting. Tuesday, Sept 25 Lecture 8: Fitting Tuesday, Sept 25 Announcements, schedule Grad student extensions Due end of term Data sets, suggestions Reminder: Midterm Tuesday 10/9 Problem set 2 out Thursday, due 10/11 Outline Review

More information

Local Features Tutorial: Nov. 8, 04

Local Features Tutorial: Nov. 8, 04 Local Features Tutorial: Nov. 8, 04 Local Features Tutorial References: Matlab SIFT tutorial (from course webpage) Lowe, David G. Distinctive Image Features from Scale Invariant Features, International

More information

Local features: detection and description May 12 th, 2015

Local features: detection and description May 12 th, 2015 Local features: detection and description May 12 th, 2015 Yong Jae Lee UC Davis Announcements PS1 grades up on SmartSite PS1 stats: Mean: 83.26 Standard Dev: 28.51 PS2 deadline extended to Saturday, 11:59

More information

Model Fitting: The Hough transform II

Model Fitting: The Hough transform II Model Fitting: The Hough transform II Guido Gerig, CS6640 Image Processing, Utah Theory: See handwritten notes GG: HT-notes-GG-II.pdf Credits: S. Narasimhan, CMU, Spring 2006 15-385,-685, Link Svetlana

More information

Local features and image matching. Prof. Xin Yang HUST

Local features and image matching. Prof. Xin Yang HUST Local features and image matching Prof. Xin Yang HUST Last time RANSAC for robust geometric transformation estimation Translation, Affine, Homography Image warping Given a 2D transformation T and a source

More information

Fitting: The Hough transform

Fitting: The Hough transform Fitting: The Hough transform Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not vote consistently for any single model Missing data

More information

Feature Matching and Robust Fitting

Feature Matching and Robust Fitting Feature Matching and Robust Fitting Computer Vision CS 143, Brown Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Project 2 questions? This

More information

Recap Image Classification with Bags of Local Features

Recap Image Classification with Bags of Local Features Recap Image Classification with Bags of Local Features Bag of Feature models were the state of the art for image classification for a decade BoF may still be the state of the art for instance retrieval

More information

2D Image Processing Feature Descriptors

2D Image Processing Feature Descriptors 2D Image Processing Feature Descriptors Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Overview

More information

CS 4495 Computer Vision A. Bobick. CS 4495 Computer Vision. Features 2 SIFT descriptor. Aaron Bobick School of Interactive Computing

CS 4495 Computer Vision A. Bobick. CS 4495 Computer Vision. Features 2 SIFT descriptor. Aaron Bobick School of Interactive Computing CS 4495 Computer Vision Features 2 SIFT descriptor Aaron Bobick School of Interactive Computing Administrivia PS 3: Out due Oct 6 th. Features recap: Goal is to find corresponding locations in two images.

More information

Instance-level recognition part 2

Instance-level recognition part 2 Visual Recognition and Machine Learning Summer School Paris 2011 Instance-level recognition part 2 Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique,

More information

CS 558: Computer Vision 4 th Set of Notes

CS 558: Computer Vision 4 th Set of Notes 1 CS 558: Computer Vision 4 th Set of Notes Instructor: Philippos Mordohai Webpage: www.cs.stevens.edu/~mordohai E-mail: Philippos.Mordohai@stevens.edu Office: Lieb 215 Overview Keypoint matching Hessian

More information

Instance-level recognition II.

Instance-level recognition II. Reconnaissance d objets et vision artificielle 2010 Instance-level recognition II. Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique, Ecole Normale

More information

High Level Computer Vision

High Level Computer Vision High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de http://www.d2.mpi-inf.mpg.de/cv Please Note No

More information

Local Features: Detection, Description & Matching

Local Features: Detection, Description & Matching Local Features: Detection, Description & Matching Lecture 08 Computer Vision Material Citations Dr George Stockman Professor Emeritus, Michigan State University Dr David Lowe Professor, University of British

More information

Fitting: The Hough transform

Fitting: The Hough transform Fitting: The Hough transform Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not vote consistently for any single model Missing data

More information

Fitting: The Hough transform

Fitting: The Hough transform Fitting: The Hough transform Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not vote consistently for any single model Missing data

More information

Discriminative classifiers for image recognition

Discriminative classifiers for image recognition Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study

More information

Local invariant features

Local invariant features Local invariant features Tuesday, Oct 28 Kristen Grauman UT-Austin Today Some more Pset 2 results Pset 2 returned, pick up solutions Pset 3 is posted, due 11/11 Local invariant features Detection of interest

More information

School of Computing University of Utah

School of Computing University of Utah School of Computing University of Utah Presentation Outline 1 2 3 4 Main paper to be discussed David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, IJCV, 2004. How to find useful keypoints?

More information

Designing Applications that See Lecture 7: Object Recognition

Designing Applications that See Lecture 7: Object Recognition stanford hci group / cs377s Designing Applications that See Lecture 7: Object Recognition Dan Maynes-Aminzade 29 January 2008 Designing Applications that See http://cs377s.stanford.edu Reminders Pick up

More information

Templates and Background Subtraction. Prof. D. Stricker Doz. G. Bleser

Templates and Background Subtraction. Prof. D. Stricker Doz. G. Bleser Templates and Background Subtraction Prof. D. Stricker Doz. G. Bleser 1 Surveillance Video: Example of multiple people tracking http://www.youtube.com/watch?v=inqv34bchem&feature=player_embedded As for

More information

Bus Detection and recognition for visually impaired people

Bus Detection and recognition for visually impaired people Bus Detection and recognition for visually impaired people Hangrong Pan, Chucai Yi, and Yingli Tian The City College of New York The Graduate Center The City University of New York MAP4VIP Outline Motivation

More information

Keypoint-based Recognition and Object Search

Keypoint-based Recognition and Object Search 03/08/11 Keypoint-based Recognition and Object Search Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Notices I m having trouble connecting to the web server, so can t post lecture

More information

Features Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE)

Features Points. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE) Features Points Andrea Torsello DAIS Università Ca Foscari via Torino 155, 30172 Mestre (VE) Finding Corners Edge detectors perform poorly at corners. Corners provide repeatable points for matching, so

More information

Midterm Wed. Local features: detection and description. Today. Last time. Local features: main components. Goal: interest operator repeatability

Midterm Wed. Local features: detection and description. Today. Last time. Local features: main components. Goal: interest operator repeatability Midterm Wed. Local features: detection and description Monday March 7 Prof. UT Austin Covers material up until 3/1 Solutions to practice eam handed out today Bring a 8.5 11 sheet of notes if you want Review

More information

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract

More information

Object and Class Recognition I:

Object and Class Recognition I: Object and Class Recognition I: Object Recognition Lectures 10 Sources ICCV 2005 short courses Li Fei-Fei (UIUC), Rob Fergus (Oxford-MIT), Antonio Torralba (MIT) http://people.csail.mit.edu/torralba/iccv2005

More information

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm Group 1: Mina A. Makar Stanford University mamakar@stanford.edu Abstract In this report, we investigate the application of the Scale-Invariant

More information

Detecting Object Instances Without Discriminative Features

Detecting Object Instances Without Discriminative Features Detecting Object Instances Without Discriminative Features Edward Hsiao June 19, 2013 Thesis Committee: Martial Hebert, Chair Alexei Efros Takeo Kanade Andrew Zisserman, University of Oxford 1 Object Instance

More information

Multiple-Person Tracking by Detection

Multiple-Person Tracking by Detection http://excel.fit.vutbr.cz Multiple-Person Tracking by Detection Jakub Vojvoda* Abstract Detection and tracking of multiple person is challenging problem mainly due to complexity of scene and large intra-class

More information

Local Image Features

Local Image Features Local Image Features Computer Vision CS 143, Brown Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial This section: correspondence and alignment

More information

Key properties of local features

Key properties of local features Key properties of local features Locality, robust against occlusions Must be highly distinctive, a good feature should allow for correct object identification with low probability of mismatch Easy to etract

More information

Beyond bags of features: Adding spatial information. Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba

Beyond bags of features: Adding spatial information. Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba Adding spatial information Forming vocabularies from pairs of nearby features doublets

More information

Announcements, schedule. Lecture 8: Fitting. Weighted graph representation. Outline. Segmentation by Graph Cuts. Images as graphs

Announcements, schedule. Lecture 8: Fitting. Weighted graph representation. Outline. Segmentation by Graph Cuts. Images as graphs Announcements, schedule Lecture 8: Fitting Tuesday, Sept 25 Grad student etensions Due of term Data sets, suggestions Reminder: Midterm Tuesday 10/9 Problem set 2 out Thursday, due 10/11 Outline Review

More information

Articulated Pose Estimation with Flexible Mixtures-of-Parts

Articulated Pose Estimation with Flexible Mixtures-of-Parts Articulated Pose Estimation with Flexible Mixtures-of-Parts PRESENTATION: JESSE DAVIS CS 3710 VISUAL RECOGNITION Outline Modeling Special Cases Inferences Learning Experiments Problem and Relevance Problem:

More information

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit Augmented Reality VU Computer Vision 3D Registration (2) Prof. Vincent Lepetit Feature Point-Based 3D Tracking Feature Points for 3D Tracking Much less ambiguous than edges; Point-to-point reprojection

More information

Motion illusion, rotating snakes

Motion illusion, rotating snakes Motion illusion, rotating snakes Local features: main components 1) Detection: Find a set of distinctive key points. 2) Description: Extract feature descriptor around each interest point as vector. x 1

More information

Geometric verifica-on of matching

Geometric verifica-on of matching Geometric verifica-on of matching The correspondence problem The correspondence problem tries to figure out which parts of an image correspond to which parts of another image, a;er the camera has moved,

More information

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

COSC160: 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 information

Instance-level recognition

Instance-level recognition Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction

More information

Bias-Variance Trade-off (cont d) + Image Representations

Bias-Variance Trade-off (cont d) + Image Representations CS 275: Machine Learning Bias-Variance Trade-off (cont d) + Image Representations Prof. Adriana Kovashka University of Pittsburgh January 2, 26 Announcement Homework now due Feb. Generalization Training

More information

Large-scale visual recognition The bag-of-words representation

Large-scale visual recognition The bag-of-words representation Large-scale visual recognition The bag-of-words representation Florent Perronnin, XRCE Hervé Jégou, INRIA CVPR tutorial June 16, 2012 Outline Bag-of-words Large or small vocabularies? Extensions for instance-level

More information

Instance-level recognition

Instance-level recognition Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction

More information

Video Google faces. Josef Sivic, Mark Everingham, Andrew Zisserman. Visual Geometry Group University of Oxford

Video Google faces. Josef Sivic, Mark Everingham, Andrew Zisserman. Visual Geometry Group University of Oxford Video Google faces Josef Sivic, Mark Everingham, Andrew Zisserman Visual Geometry Group University of Oxford The objective Retrieve all shots in a video, e.g. a feature length film, containing a particular

More information

Local Image Features

Local Image Features Local Image Features Computer Vision Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Flashed Face Distortion 2nd Place in the 8th Annual Best

More information

Finding 2D Shapes and the Hough Transform

Finding 2D Shapes and the Hough Transform CS 4495 Computer Vision Finding 2D Shapes and the Aaron Bobick School of Interactive Computing Administrivia Today: Modeling Lines and Finding them CS4495: Problem set 1 is still posted. Please read the

More information

Perception. Autonomous Mobile Robots. Sensors Vision Uncertainties, Line extraction from laser scans. Autonomous Systems Lab. Zürich.

Perception. Autonomous Mobile Robots. Sensors Vision Uncertainties, Line extraction from laser scans. Autonomous Systems Lab. Zürich. Autonomous Mobile Robots Localization "Position" Global Map Cognition Environment Model Local Map Path Perception Real World Environment Motion Control Perception Sensors Vision Uncertainties, Line extraction

More information

Efficient Kernels for Identifying Unbounded-Order Spatial Features

Efficient Kernels for Identifying Unbounded-Order Spatial Features Efficient Kernels for Identifying Unbounded-Order Spatial Features Yimeng Zhang Carnegie Mellon University yimengz@andrew.cmu.edu Tsuhan Chen Cornell University tsuhan@ece.cornell.edu Abstract Higher order

More information

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213) Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding

More information

Lecture: RANSAC and feature detectors

Lecture: RANSAC and feature detectors Lecture: RANSAC and feature detectors Juan Carlos Niebles and Ranjay Krishna Stanford Vision and Learning Lab 1 What we will learn today? A model fitting method for edge detection RANSAC Local invariant

More information

Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections

Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections Nima Razavi 1, Juergen Gall 1, and Luc Van Gool 1,2 1 Computer Vision Laboratory, ETH Zurich 2 ESAT-PSI/IBBT,

More information

Tracking People. Tracking People: Context

Tracking People. Tracking People: Context Tracking People A presentation of Deva Ramanan s Finding and Tracking People from the Bottom Up and Strike a Pose: Tracking People by Finding Stylized Poses Tracking People: Context Motion Capture Surveillance

More information

What is Computer Vision?

What is Computer Vision? Perceptual Grouping in Computer Vision Gérard Medioni University of Southern California What is Computer Vision? Computer Vision Attempt to emulate Human Visual System Perceive visual stimuli with cameras

More information

EECS 442 Computer vision. Fitting methods

EECS 442 Computer vision. Fitting methods EECS 442 Computer vision Fitting methods - Problem formulation - Least square methods - RANSAC - Hough transforms - Multi-model fitting - Fitting helps matching! Reading: [HZ] Chapters: 4, 11 [FP] Chapters:

More information

Feature Detection. Raul Queiroz Feitosa. 3/30/2017 Feature Detection 1

Feature Detection. Raul Queiroz Feitosa. 3/30/2017 Feature Detection 1 Feature Detection Raul Queiroz Feitosa 3/30/2017 Feature Detection 1 Objetive This chapter discusses the correspondence problem and presents approaches to solve it. 3/30/2017 Feature Detection 2 Outline

More information

A novel template matching method for human detection

A novel template matching method for human detection University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2009 A novel template matching method for human detection Duc Thanh Nguyen

More information

Object detection. Announcements. Last time: Mid-level cues 2/23/2016. Wed Feb 24 Kristen Grauman UT Austin

Object detection. Announcements. Last time: Mid-level cues 2/23/2016. Wed Feb 24 Kristen Grauman UT Austin Object detection Wed Feb 24 Kristen Grauman UT Austin Announcements Reminder: Assignment 2 is due Mar 9 and Mar 10 Be ready to run your code again on a new test set on Mar 10 Vision talk next Tuesday 11

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing ECG782: Multidimensional Digital Signal Processing Object Recognition http://www.ee.unlv.edu/~b1morris/ecg782/ 2 Outline Knowledge Representation Statistical Pattern Recognition Neural Networks Boosting

More information

Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki

Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki 2011 The MathWorks, Inc. 1 Today s Topics Introduction Computer Vision Feature-based registration Automatic image registration Object recognition/rotation

More information

Human detection using local shape and nonredundant

Human detection using local shape and nonredundant University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2010 Human detection using local shape and nonredundant binary patterns

More information

Performance Evaluation of Scale-Interpolated Hessian-Laplace and Haar Descriptors for Feature Matching

Performance Evaluation of Scale-Interpolated Hessian-Laplace and Haar Descriptors for Feature Matching Performance Evaluation of Scale-Interpolated Hessian-Laplace and Haar Descriptors for Feature Matching Akshay Bhatia, Robert Laganière School of Information Technology and Engineering University of Ottawa

More information

Bridging the Gap Between Local and Global Approaches for 3D Object Recognition. Isma Hadji G. N. DeSouza

Bridging the Gap Between Local and Global Approaches for 3D Object Recognition. Isma Hadji G. N. DeSouza Bridging the Gap Between Local and Global Approaches for 3D Object Recognition Isma Hadji G. N. DeSouza Outline Introduction Motivation Proposed Methods: 1. LEFT keypoint Detector 2. LGS Feature Descriptor

More information

Building a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882

Building a Panorama. Matching features. Matching with Features. How do we build a panorama? Computational Photography, 6.882 Matching features Building a Panorama Computational Photography, 6.88 Prof. Bill Freeman April 11, 006 Image and shape descriptors: Harris corner detectors and SIFT features. Suggested readings: Mikolajczyk

More information

Prof. Feng Liu. Spring /26/2017

Prof. Feng Liu. Spring /26/2017 Prof. Feng Liu Spring 2017 http://www.cs.pdx.edu/~fliu/courses/cs510/ 04/26/2017 Last Time Re-lighting HDR 2 Today Panorama Overview Feature detection Mid-term project presentation Not real mid-term 6

More information

Automatic Image Alignment (feature-based)

Automatic Image Alignment (feature-based) Automatic Image Alignment (feature-based) Mike Nese with a lot of slides stolen from Steve Seitz and Rick Szeliski 15-463: Computational Photography Alexei Efros, CMU, Fall 2006 Today s lecture Feature

More information

Part-based models. Lecture 10

Part-based models. Lecture 10 Part-based models Lecture 10 Overview Representation Location Appearance Generative interpretation Learning Distance transforms Other approaches using parts Felzenszwalb, Girshick, McAllester, Ramanan

More information

SIFT - scale-invariant feature transform Konrad Schindler

SIFT - scale-invariant feature transform Konrad Schindler SIFT - scale-invariant feature transform Konrad Schindler Institute of Geodesy and Photogrammetry Invariant interest points Goal match points between images with very different scale, orientation, projective

More information

CS6670: Computer Vision

CS6670: Computer Vision CS6670: Computer Vision Noah Snavely Lecture 16: Bag-of-words models Object Bag of words Announcements Project 3: Eigenfaces due Wednesday, November 11 at 11:59pm solo project Final project presentations:

More information

10/03/11. Model Fitting. Computer Vision CS 143, Brown. James Hays. Slides from Silvio Savarese, Svetlana Lazebnik, and Derek Hoiem

10/03/11. Model Fitting. Computer Vision CS 143, Brown. James Hays. Slides from Silvio Savarese, Svetlana Lazebnik, and Derek Hoiem 10/03/11 Model Fitting Computer Vision CS 143, Brown James Hays Slides from Silvio Savarese, Svetlana Lazebnik, and Derek Hoiem Fitting: find the parameters of a model that best fit the data Alignment:

More information

CS231A Section 6: Problem Set 3

CS231A Section 6: Problem Set 3 CS231A Section 6: Problem Set 3 Kevin Wong Review 6 -! 1 11/09/2012 Announcements PS3 Due 2:15pm Tuesday, Nov 13 Extra Office Hours: Friday 6 8pm Huang Common Area, Basement Level. Review 6 -! 2 Topics

More information

3D Object Recognition using Multiclass SVM-KNN

3D Object Recognition using Multiclass SVM-KNN 3D Object Recognition using Multiclass SVM-KNN R. Muralidharan, C. Chandradekar April 29, 2014 Presented by: Tasadduk Chowdhury Problem We address the problem of recognizing 3D objects based on various

More information