Limitations window-based detection.
|
|
- Egbert Shepherd
- 7 years ago
- Views:
Transcription
1 BAG-OF-WORDS MODEL The slides are from several sources through James Hays (Brown); Silvio Savarese (U. of Michigan); Bill Freeman and Antonio Torralba (MIT), including their own slides.
2 Visual Perceptual Object and Recognition Sensory Augmented Tutorial Computing Kristen Grauman Limitations window-based detection. Not all objects are box shaped.
3 Kristen Grauman Visual Perceptual Object and Recognition Sensory Augmented Tutorial Computing Non-rigid, deformable objects not captured well with representations assuming a fixed 2 structure; or must assume fixed viewpoint Objects with less-regular textures not captured well with holistic appearance-based descriptions
4 If considering windows in isolation, context is lost Visual Perceptual Object and Recognition Sensory Augmented Tutorial Computing Sliding window Detector s view Often entails large cropped training sets, which is expensive. Figure credit: Derek Hoiem Kristen Grauman
5 Object Bag of words
6 Definition of the Bag of 'Words' Independent features face bike violin which are parts of an object. See examples above.
7 Definition of the Bag of 'Words' The independent features are shown in a histogram representation. codewords dictionary
8 Representation Recognition feature detection & representation codewords dictionary image representation learning category models (and/or) classifiers category decision
9 Bag-of-words (features) learning steps 1. Extract features 2. Learn visual vocabulary 3. Quantize features using visual vocabulary 4. Represent images by frequencies of visual words
10 1. Feature extraction Compute descriptor Normalize patch Detect patches Slide credit: Josef Sivic
11 2. Learning the visual vocabulary Slide credit: Josef Sivic
12 2. Learning the visual vocabulary Clustering Slide credit: Josef Sivic
13 2. Learning the visual vocabulary Visual vocabulary Clustering Slide credit: Josef Sivic
14 Example codebook K-means clustering the value K is given = visual vocabulary Appearance codebook Source: B. Leibe
15 Another codebook Appearance codebook Source: B. Leibe
16 3. Bag of word representation frequency. codewords Codewords dictionary
17 ...gives the category models Class 1 Class N
18 Representation 1. feature detection & representation 2. codewords dictionary 3. image representation category models
19 Learning and Recognition codewords dictionary category models (and/or) classifiers category decision
20 Visual vocabularies: Issues How to choose vocabulary size? Too small: visual words not representative of all patches. Too large: quantization artifacts, overfitting. Computational efficiency use: Vocabulary trees Nister & Stewenius, 2006
21 Vocabulary Trees D. Nistér and H. Stewénius. Scalable recognition with a vocabulary tree. CVPR, , SIFT descriptors. Moving into the feature space...
22 ...moving into the feature space etc.
23 Points in a region are the closest to the cluster center. Hierarchial clustering. The training data is divided in the closest k clusters. Each cell is then split into k new parts are the process is applied recursively.
24 Hierarchial clustering. k = 3 and two layers here. black 1 green 3 blue 9
25 The feature space. Smaller "dots" are deeper.
26 In reality! Six levels of hierarchy. k = 10 nodes at every branch. Each point 128 vector (SIFT). 1M leaf nodes needs 143MB of memory.
27 The image database was created in a hierarchical manner. Recovery (testing) is also hierarchical. A descriptor (SIFT) is propagated down the tree. At each layer the closest cluster is selected from the k candidated. The tree defines the vocabulary tree hierarchically. A descriptor gets a score in every layer relative to the closest training descriptor. The final scoring is the sum of all the layers of the vocabulary tree.
28 A few SIFT-s in four images. Two descriptors, give other images, not the right ones... The whole image is shown for the illustration not the descriptor.
29 Scoring three instances.
30 If we can get repeatable, discriminative features, then recognition can scale to very large databases using the vocabulary tree and indexing approach. Database creation 2-3 days. Test about 1 second per image. Searching for face images is much less reliable...
31 Performance red - target with ground truth blue - independent from database 1 million images <==(from 7 movies) plus 6376 images with ground truth==>
32 6376 ground truth image Size Matters Improves Retrieval Improves Speed Leaf nodes with branch factor 8...
33 But what about layout? All of these images have the same color histogram.
34 Spatial pyramid Compute histogram in each spatial bin.
35 Spatial pyramid representation Extension of a bag of features. Locally orderless representation at several levels of resolution. level 0 Lazebnik, Schmid & Ponce (CVPR 2006)
36 Spatial pyramid representation Extension of a bag of features Locally orderless representation at several levels of resolution level 0 level 1 Lazebnik, Schmid & Ponce (CVPR 2006)
37 Spatial pyramid representation Extension of a bag of features Locally orderless representation at several levels of resolution level 0 level 1 level 2 Lazebnik, Schmid & Ponce (CVPR 2006)
38 Feature extraction with SIFT in dense regular grid (8 pixel aside). Images are 300x250 pixels. Vocabulary sizes 200. Each of the 15 categories has 200 to 400 images. Training: 100 images per class. Testing: all the remaning images. Number of pyramid levels = L. Also independently in a given "l" level.
39 Scene category dataset Multi-class classification results (100 training images per class)
40 Weakness of Bag of Words models No rigorous geometric information of the object components. All have equal probability. Not extensively tested yet for view point invariance scale invariance. Segmentation and localization is unclear. Location information is also important.
41 Invariance issues Scale rotation view point - occlusions Implicitly taken only. The right detectors and descriptors may improve. Kadir and Brady. 2003
42 Slide credit: Ondrej Chum Spatial Verification... Real objects have consistent geometry. Query Query image with high BoW similarity other image with high BoW similarity Both image pairs have many visual words in common.
43 Slide credit: Ondrej Chum...can work many times. Query Query after robust matching high BoW similarity after robust matching low BoW similarity Only some of the matches are mutually consistent.
Recognition. Sanja Fidler CSC420: Intro to Image Understanding 1 / 28
Recognition Topics that we will try to cover: Indexing for fast retrieval (we still owe this one) History of recognition techniques Object classification Bag-of-words Spatial pyramids Neural Networks Object
More informationLocal features and matching. Image classification & object localization
Overview Instance level search Local features and matching Efficient visual recognition Image classification & object localization Category recognition Image classification: assigning a class label to
More informationCees Snoek. Machine. Humans. Multimedia Archives. Euvision Technologies The Netherlands. University of Amsterdam The Netherlands. Tree.
Visual search: what's next? Cees Snoek University of Amsterdam The Netherlands Euvision Technologies The Netherlands Problem statement US flag Tree Aircraft Humans Dog Smoking Building Basketball Table
More informationObject Recognition. Selim Aksoy. Bilkent University saksoy@cs.bilkent.edu.tr
Image Classification and Object Recognition Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Image classification Image (scene) classification is a fundamental
More informationProbabilistic Latent Semantic Analysis (plsa)
Probabilistic Latent Semantic Analysis (plsa) SS 2008 Bayesian Networks Multimedia Computing, Universität Augsburg Rainer.Lienhart@informatik.uni-augsburg.de www.multimedia-computing.{de,org} References
More informationGPS-aided Recognition-based User Tracking System with Augmented Reality in Extreme Large-scale Areas
GPS-aided Recognition-based User Tracking System with Augmented Reality in Extreme Large-scale Areas Wei Guan Computer Graphics and Immersive Technologies Computer Science, USC wguan@usc.edu Suya You Computer
More informationRecognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang
Recognizing Cats and Dogs with Shape and Appearance based Models Group Member: Chu Wang, Landu Jiang Abstract Recognizing cats and dogs from images is a challenging competition raised by Kaggle platform
More informationSemantic Recognition: Object Detection and Scene Segmentation
Semantic Recognition: Object Detection and Scene Segmentation Xuming He xuming.he@nicta.com.au Computer Vision Research Group NICTA Robotic Vision Summer School 2015 Acknowledgement: Slides from Fei-Fei
More informationConvolutional Feature Maps
Convolutional Feature Maps Elements of efficient (and accurate) CNN-based object detection Kaiming He Microsoft Research Asia (MSRA) ICCV 2015 Tutorial on Tools for Efficient Object Detection Overview
More informationFast Matching of Binary Features
Fast Matching of Binary Features Marius Muja and David G. Lowe Laboratory for Computational Intelligence University of British Columbia, Vancouver, Canada {mariusm,lowe}@cs.ubc.ca Abstract There has been
More informationIMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS
IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS Alexander Velizhev 1 (presenter) Roman Shapovalov 2 Konrad Schindler 3 1 Hexagon Technology Center, Heerbrugg, Switzerland 2 Graphics & Media
More informationTouchPaper - An Augmented Reality Application with Cloud-Based Image Recognition Service
TouchPaper - An Augmented Reality Application with Cloud-Based Image Recognition Service Feng Tang, Daniel R. Tretter, Qian Lin HP Laboratories HPL-2012-131R1 Keyword(s): image recognition; cloud service;
More informationHigh Level Describable Attributes for Predicting Aesthetics and Interestingness
High Level Describable Attributes for Predicting Aesthetics and Interestingness Sagnik Dhar Vicente Ordonez Tamara L Berg Stony Brook University Stony Brook, NY 11794, USA tlberg@cs.stonybrook.edu Abstract
More information3D Model based Object Class Detection in An Arbitrary View
3D Model based Object Class Detection in An Arbitrary View Pingkun Yan, Saad M. Khan, Mubarak Shah School of Electrical Engineering and Computer Science University of Central Florida http://www.eecs.ucf.edu/
More informationFAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION
FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION Marius Muja, David G. Lowe Computer Science Department, University of British Columbia, Vancouver, B.C., Canada mariusm@cs.ubc.ca,
More informationMulti-View Object Class Detection with a 3D Geometric Model
Multi-View Object Class Detection with a 3D Geometric Model Joerg Liebelt IW-SI, EADS Innovation Works D-81663 Munich, Germany joerg.liebelt@eads.net Cordelia Schmid LEAR, INRIA Grenoble F-38330 Montbonnot,
More informationThe Delicate Art of Flower Classification
The Delicate Art of Flower Classification Paul Vicol Simon Fraser University University Burnaby, BC pvicol@sfu.ca Note: The following is my contribution to a group project for a graduate machine learning
More informationCamera geometry and image alignment
Computer Vision and Machine Learning Winter School ENS Lyon 2010 Camera geometry and image alignment Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique,
More informationPixels Description of scene contents. Rob Fergus (NYU) Antonio Torralba (MIT) Yair Weiss (Hebrew U.) William T. Freeman (MIT) Banksy, 2006
Object Recognition Large Image Databases and Small Codes for Object Recognition Pixels Description of scene contents Rob Fergus (NYU) Antonio Torralba (MIT) Yair Weiss (Hebrew U.) William T. Freeman (MIT)
More informationImage Classification for Dogs and Cats
Image Classification for Dogs and Cats Bang Liu, Yan Liu Department of Electrical and Computer Engineering {bang3,yan10}@ualberta.ca Kai Zhou Department of Computing Science kzhou3@ualberta.ca Abstract
More informationOpen issues and research trends in Content-based Image Retrieval
Open issues and research trends in Content-based Image Retrieval Raimondo Schettini DISCo Universita di Milano Bicocca schettini@disco.unimib.it www.disco.unimib.it/schettini/ IEEE Signal Processing Society
More informationGroup Sparse Coding. Fernando Pereira Google Mountain View, CA pereira@google.com. Dennis Strelow Google Mountain View, CA strelow@google.
Group Sparse Coding Samy Bengio Google Mountain View, CA bengio@google.com Fernando Pereira Google Mountain View, CA pereira@google.com Yoram Singer Google Mountain View, CA singer@google.com Dennis Strelow
More informationDecision Trees from large Databases: SLIQ
Decision Trees from large Databases: SLIQ C4.5 often iterates over the training set How often? If the training set does not fit into main memory, swapping makes C4.5 unpractical! SLIQ: Sort the values
More informationDistributed Kd-Trees for Retrieval from Very Large Image Collections
ALY et al.: DISTRIBUTED KD-TREES FOR RETRIEVAL FROM LARGE IMAGE COLLECTIONS1 Distributed Kd-Trees for Retrieval from Very Large Image Collections Mohamed Aly 1 malaa@vision.caltech.edu Mario Munich 2 mario@evolution.com
More informationModelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches
Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic
More informationDiscovering objects and their location in images
Discovering objects and their location in images Josef Sivic Bryan C. Russell Alexei A. Efros Andrew Zisserman William T. Freeman Dept. of Engineering Science CS and AI Laboratory School of Computer Science
More informationJiří Matas. Hough Transform
Hough Transform Jiří Matas Center for Machine Perception Department of Cybernetics, Faculty of Electrical Engineering Czech Technical University, Prague Many slides thanks to Kristen Grauman and Bastian
More informationModule 5. Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016
Module 5 Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016 Previously, end-to-end.. Dog Slide credit: Jose M 2 Previously, end-to-end.. Dog Learned Representation Slide credit: Jose
More informationThe Scientific Data Mining Process
Chapter 4 The Scientific Data Mining Process When I use a word, Humpty Dumpty said, in rather a scornful tone, it means just what I choose it to mean neither more nor less. Lewis Carroll [87, p. 214] In
More informationA Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow
, pp.233-237 http://dx.doi.org/10.14257/astl.2014.51.53 A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow Giwoo Kim 1, Hye-Youn Lim 1 and Dae-Seong Kang 1, 1 Department of electronices
More informationSemantic Image Segmentation and Web-Supervised Visual Learning
Semantic Image Segmentation and Web-Supervised Visual Learning Florian Schroff Andrew Zisserman University of Oxford, UK Antonio Criminisi Microsoft Research Ltd, Cambridge, UK Outline Part I: Semantic
More informationCS 1699: Intro to Computer Vision. Deep Learning. Prof. Adriana Kovashka University of Pittsburgh December 1, 2015
CS 1699: Intro to Computer Vision Deep Learning Prof. Adriana Kovashka University of Pittsburgh December 1, 2015 Today: Deep neural networks Background Architectures and basic operations Applications Visualizing
More informationA Short Introduction to Computer Graphics
A Short Introduction to Computer Graphics Frédo Durand MIT Laboratory for Computer Science 1 Introduction Chapter I: Basics Although computer graphics is a vast field that encompasses almost any graphical
More informationA Comparison of Keypoint Descriptors in the Context of Pedestrian Detection: FREAK vs. SURF vs. BRISK
A Comparison of Keypoint Descriptors in the Context of Pedestrian Detection: FREAK vs. SURF vs. BRISK Cameron Schaeffer Stanford University CS Department camerons@stanford.edu Abstract The subject of keypoint
More informationBlocks that Shout: Distinctive Parts for Scene Classification
Blocks that Shout: Distinctive Parts for Scene Classification Mayank Juneja 1 Andrea Vedaldi 2 C. V. Jawahar 1 Andrew Zisserman 2 1 Center for Visual Information Technology, International Institute of
More informationMachine Learning for Medical Image Analysis. A. Criminisi & the InnerEye team @ MSRC
Machine Learning for Medical Image Analysis A. Criminisi & the InnerEye team @ MSRC Medical image analysis the goal Automatic, semantic analysis and quantification of what observed in medical scans Brain
More informationRANDOM PROJECTIONS FOR SEARCH AND MACHINE LEARNING
= + RANDOM PROJECTIONS FOR SEARCH AND MACHINE LEARNING Stefan Savev Berlin Buzzwords June 2015 KEYWORD-BASED SEARCH Document Data 300 unique words per document 300 000 words in vocabulary Data sparsity:
More informationFeature Tracking and Optical Flow
02/09/12 Feature Tracking and Optical Flow Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Many slides adapted from Lana Lazebnik, Silvio Saverse, who in turn adapted slides from Steve
More informationTopographic Change Detection Using CloudCompare Version 1.0
Topographic Change Detection Using CloudCompare Version 1.0 Emily Kleber, Arizona State University Edwin Nissen, Colorado School of Mines J Ramón Arrowsmith, Arizona State University Introduction CloudCompare
More informationSimilarity Search in a Very Large Scale Using Hadoop and HBase
http:/cedric.cnam.fr Similarity Search in a Very Large Scale Using Hadoop and HBase Rapport de recherche CEDRIC 2012 http://cedric.cnam.fr Stanislav Barton (CNAM), Vlastislav Dohnal (Masaryk University),
More informationSemantic Description of Humans in Images
Semantic Description of Humans in Images Gaurav Sharma To cite this version: Gaurav Sharma. Semantic Description of Humans in Images. Computer Vision and Pattern Recognition [cs.cv]. Université de Caen,
More informationPart-Based Recognition
Part-Based Recognition Benedict Brown CS597D, Fall 2003 Princeton University CS 597D, Part-Based Recognition p. 1/32 Introduction Many objects are made up of parts It s presumably easier to identify simple
More informationIntroduction. Selim Aksoy. Bilkent University saksoy@cs.bilkent.edu.tr
Introduction Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr What is computer vision? What does it mean, to see? The plain man's answer (and Aristotle's, too)
More informationRandomized Trees for Real-Time Keypoint Recognition
Randomized Trees for Real-Time Keypoint Recognition Vincent Lepetit Pascal Lagger Pascal Fua Computer Vision Laboratory École Polytechnique Fédérale de Lausanne (EPFL) 1015 Lausanne, Switzerland Email:
More informationCharacter Image Patterns as Big Data
22 International Conference on Frontiers in Handwriting Recognition Character Image Patterns as Big Data Seiichi Uchida, Ryosuke Ishida, Akira Yoshida, Wenjie Cai, Yaokai Feng Kyushu University, Fukuoka,
More informationMining Mid-level Features for Image Classification
International Journal of Computer Vision manuscript No. (will be inserted by the editor) Mining Mid-level Features for Image Classification Basura Fernando Elisa Fromont Tinne Tuytelaars Received: date
More informationIntroduction to Pattern Recognition
Introduction to Pattern Recognition Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2009 CS 551, Spring 2009 c 2009, Selim Aksoy (Bilkent University)
More informationClassifying Large Data Sets Using SVMs with Hierarchical Clusters. Presented by :Limou Wang
Classifying Large Data Sets Using SVMs with Hierarchical Clusters Presented by :Limou Wang Overview SVM Overview Motivation Hierarchical micro-clustering algorithm Clustering-Based SVM (CB-SVM) Experimental
More informationYouTube Scale, Large Vocabulary Video Annotation
YouTube Scale, Large Vocabulary Video Annotation Nicholas Morsillo, Gideon Mann and Christopher Pal Abstract As video content on the web continues to expand, it is increasingly important to properly annotate
More informationClassifying Manipulation Primitives from Visual Data
Classifying Manipulation Primitives from Visual Data Sandy Huang and Dylan Hadfield-Menell Abstract One approach to learning from demonstrations in robotics is to make use of a classifier to predict if
More informationAutomatic georeferencing of imagery from high-resolution, low-altitude, low-cost aerial platforms
Automatic georeferencing of imagery from high-resolution, low-altitude, low-cost aerial platforms Amanda Geniviva, Jason Faulring and Carl Salvaggio Rochester Institute of Technology, 54 Lomb Memorial
More informationContent-Based Image Retrieval
Content-Based Image Retrieval Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Image retrieval Searching a large database for images that match a query: What kind
More informationCombining Local Recognition Methods for Better Image Recognition
Combining Local Recognition Methods for Better Image Recognition Bart Lamiroy Patrick Gros y Sylvaine Picard INRIA CNRS DGA MOVI GRAVIR z IMAG INRIA RHÔNE-ALPES ZIRST 655, Av. de l Europe Montbonnot FRANCE
More informationA Review of Codebook Models in Patch-Based Visual Object Recognition
DOI 10.1007/s11265-011-0622-x A Review of Codebook Models in Patch-Based Visual Object Recognition Amirthalingam Ramanan Mahesan Niranjan Received: 19 July 2010 / Revised: 20 August 2011 / Accepted: 22
More informationDriver Cell Phone Usage Detection From HOV/HOT NIR Images
Driver Cell Phone Usage Detection From HOV/HOT NIR Images Yusuf Artan, Orhan Bulan, Robert P. Loce, and Peter Paul Xerox Research Center Webster 800 Phillips Rd. Webster NY 4580 yusuf.artan,orhan.bulan,robert.loce,peter.paul@xerox.com
More informationAutomatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report
Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 69 Class Project Report Junhua Mao and Lunbo Xu University of California, Los Angeles mjhustc@ucla.edu and lunbo
More informationClustering & Visualization
Chapter 5 Clustering & Visualization Clustering in high-dimensional databases is an important problem and there are a number of different clustering paradigms which are applicable to high-dimensional data.
More informationFootwear Print Retrieval System for Real Crime Scene Marks
Footwear Print Retrieval System for Real Crime Scene Marks Yi Tang, Sargur N. Srihari, Harish Kasiviswanathan and Jason J. Corso Center of Excellence for Document Analysis and Recognition (CEDAR) University
More informationDiscovering objects and their location in images
Discovering objects and their location in images Josef Sivic Bryan C. Russell Alexei A. Efros Andrew Zisserman William T. Freeman Dept. of Engineering Science CS and AI Laboratory School of Computer Science
More informationAssessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall
Automatic Photo Quality Assessment Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Estimating i the photorealism of images: Distinguishing i i paintings from photographs h Florin
More informationFastKeypointRecognitioninTenLinesofCode
FastKeypointRecognitioninTenLinesofCode Mustafa Özuysal Pascal Fua Vincent Lepetit Computer Vision Laboratory École Polytechnique Fédérale de Lausanne(EPFL) 115 Lausanne, Switzerland Email: {Mustafa.Oezuysal,
More informationFace Recognition in Low-resolution Images by Using Local Zernike Moments
Proceedings of the International Conference on Machine Vision and Machine Learning Prague, Czech Republic, August14-15, 014 Paper No. 15 Face Recognition in Low-resolution Images by Using Local Zernie
More informationScale-Invariant Object Categorization using a Scale-Adaptive Mean-Shift Search
in DAGM 04 Pattern Recognition Symposium, Tübingen, Germany, Aug 2004. Scale-Invariant Object Categorization using a Scale-Adaptive Mean-Shift Search Bastian Leibe ½ and Bernt Schiele ½¾ ½ Perceptual Computing
More informationWhat is Visualization? Information Visualization An Overview. Information Visualization. Definitions
What is Visualization? Information Visualization An Overview Jonathan I. Maletic, Ph.D. Computer Science Kent State University Visualize/Visualization: To form a mental image or vision of [some
More informationBRIEF: Binary Robust Independent Elementary Features
BRIEF: Binary Robust Independent Elementary Features Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua CVLab, EPFL, Lausanne, Switzerland e-mail: firstname.lastname@epfl.ch Abstract.
More informationEnvironmental Remote Sensing GEOG 2021
Environmental Remote Sensing GEOG 2021 Lecture 4 Image classification 2 Purpose categorising data data abstraction / simplification data interpretation mapping for land cover mapping use land cover class
More informationFrom Ideas to Innovation
From Ideas to Innovation Selected Applications from the CRC Research Lab in Advanced Geomatics Image Processing Dr. Yun Zhang Canada Research Chair Laboratory in Advanced Geomatics Image Processing (CRC-AGIP
More informationScalable Object Detection by Filter Compression with Regularized Sparse Coding
Scalable Object Detection by Filter Compression with Regularized Sparse Coding Ting-Hsuan Chao, Yen-Liang Lin, Yin-Hsi Kuo, and Winston H Hsu National Taiwan University, Taipei, Taiwan Abstract For practical
More informationEFFICIENT VEHICLE TRACKING AND CLASSIFICATION FOR AN AUTOMATED TRAFFIC SURVEILLANCE SYSTEM
EFFICIENT VEHICLE TRACKING AND CLASSIFICATION FOR AN AUTOMATED TRAFFIC SURVEILLANCE SYSTEM Amol Ambardekar, Mircea Nicolescu, and George Bebis Department of Computer Science and Engineering University
More informationComparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data
CMPE 59H Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data Term Project Report Fatma Güney, Kübra Kalkan 1/15/2013 Keywords: Non-linear
More informationInteractive Offline Tracking for Color Objects
Interactive Offline Tracking for Color Objects Yichen Wei Jian Sun Xiaoou Tang Heung-Yeung Shum Microsoft Research Asia, Beijing, China {yichenw,jiansun,xitang,hshum}@microsoft.com Abstract In this paper,
More informationAvoiding confusing features in place recognition
Avoiding confusing features in place recognition Jan Knopp 1, Josef Sivic 2, Tomas Pajdla 3 1 VISICS, ESAT-PSI, K.U. Leuven, Belgium 2 INRIA, WILLOW, Laboratoire d Informatique de l Ecole Normale Superieure,
More informationBig Data: Image & Video Analytics
Big Data: Image & Video Analytics How it could support Archiving & Indexing & Searching Dieter Haas, IBM Deutschland GmbH The Big Data Wave 60% of internet traffic is multimedia content (images and videos)
More informationSZTAKI @ ImageCLEF 2011
SZTAKI @ ImageCLEF 2011 Bálint Daróczy Róbert Pethes András A. Benczúr Data Mining and Web search Research Group, Informatics Laboratory Computer and Automation Research Institute of the Hungarian Academy
More informationPractical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006
Practical Tour of Visual tracking David Fleet and Allan Jepson January, 2006 Designing a Visual Tracker: What is the state? pose and motion (position, velocity, acceleration, ) shape (size, deformation,
More informationCATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND k NEAREST NEIGHBOUR CLASSIFIER
TECHNICAL SCIENCES Abbrev.: Techn. Sc., No 15(2), Y 2012 CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND k NEAREST NEIGHBOUR CLASSIFIER Piotr Artiemjew, Przemysław Górecki, Krzysztof Sopyła
More informationG E N E R A L A P P R O A CH: LO O K I N G F O R D O M I N A N T O R I E N T A T I O N I N I M A G E P A T C H E S
G E N E R A L A P P R O A CH: LO O K I N G F O R D O M I N A N T O R I E N T A T I O N I N I M A G E P A T C H E S In object categorization applications one of the main problems is that objects can appear
More informationSection 16.2 Classifying Images of Single Objects 504
Section 16.2 Classifying Images of Single Objects 504 FIGURE 16.18: Not all scene categories are easily distinguished by humans. These are examples from the SUN dataset (Xiao et al. 2010). On the top of
More informationMusicGuide: Album Reviews on the Go Serdar Sali
MusicGuide: Album Reviews on the Go Serdar Sali Abstract The cameras on mobile phones have untapped potential as input devices. In this paper, we present MusicGuide, an application that can be used to
More informationTaking Inverse Graphics Seriously
CSC2535: 2013 Advanced Machine Learning Taking Inverse Graphics Seriously Geoffrey Hinton Department of Computer Science University of Toronto The representation used by the neural nets that work best
More informationLesson 15 - Fill Cells Plugin
15.1 Lesson 15 - Fill Cells Plugin This lesson presents the functionalities of the Fill Cells plugin. Fill Cells plugin allows the calculation of attribute values of tables associated with cell type layers.
More informationBig Data: Rethinking Text Visualization
Big Data: Rethinking Text Visualization Dr. Anton Heijs anton.heijs@treparel.com Treparel April 8, 2013 Abstract In this white paper we discuss text visualization approaches and how these are important
More informationObject Categorization using Co-Occurrence, Location and Appearance
Object Categorization using Co-Occurrence, Location and Appearance Carolina Galleguillos Andrew Rabinovich Serge Belongie Department of Computer Science and Engineering University of California, San Diego
More informationSegmentation as Selective Search for Object Recognition
Segmentation as Selective Search for Object Recognition Koen E. A. van de Sande Jasper R. R. Uijlings Theo Gevers Arnold W. M. Smeulders University of Amsterdam University of Trento Amsterdam, The Netherlands
More informationSupervised Classification workflow in ENVI 4.8 using WorldView-2 imagery
Supervised Classification workflow in ENVI 4.8 using WorldView-2 imagery WorldView-2 is the first commercial high-resolution satellite to provide eight spectral sensors in the visible to near-infrared
More informationT O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN
T O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN Goal is to process 360 degree images and detect two object categories 1. Pedestrians,
More informationVisual Categorization with Bags of Keypoints
Visual Categorization with Bags of Keypoints Gabriella Csurka, Christopher R. Dance, Lixin Fan, Jutta Willamowski, Cédric Bray Xerox Research Centre Europe 6, chemin de Maupertuis 38240 Meylan, France
More informationMultiscale Object-Based Classification of Satellite Images Merging Multispectral Information with Panchromatic Textural Features
Remote Sensing and Geoinformation Lena Halounová, Editor not only for Scientific Cooperation EARSeL, 2011 Multiscale Object-Based Classification of Satellite Images Merging Multispectral Information with
More informationMetropoGIS: A City Modeling System DI Dr. Konrad KARNER, DI Andreas KLAUS, DI Joachim BAUER, DI Christopher ZACH
MetropoGIS: A City Modeling System DI Dr. Konrad KARNER, DI Andreas KLAUS, DI Joachim BAUER, DI Christopher ZACH VRVis Research Center for Virtual Reality and Visualization, Virtual Habitat, Inffeldgasse
More informationLecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection
CSED703R: Deep Learning for Visual Recognition (206S) Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 3 Object detection
More informationPerception of Light and Color
Perception of Light and Color Theory and Practice Trichromacy Three cones types in retina a b G+B +R Cone sensitivity functions 100 80 60 40 20 400 500 600 700 Wavelength (nm) Short wavelength sensitive
More informationSignature Segmentation and Recognition from Scanned Documents
Signature Segmentation and Recognition from Scanned Documents Ranju Mandal, Partha Pratim Roy, Umapada Pal and Michael Blumenstein School of Information and Communication Technology, Griffith University,
More informationImage Segmentation and Registration
Image Segmentation and Registration Dr. Christine Tanner (tanner@vision.ee.ethz.ch) Computer Vision Laboratory, ETH Zürich Dr. Verena Kaynig, Machine Learning Laboratory, ETH Zürich Outline Segmentation
More informationView-Invariant Dynamic Texture Recognition using a Bag of Dynamical Systems
View-Invariant Dynamic Texture Recognition using a Bag of Dynamical Systems Avinash Ravichandran, Rizwan Chaudhry and René Vidal Center for Imaging Science, Johns Hopkins University, Baltimore, MD 21218,
More informationFirst-Person Activity Recognition: What Are They Doing to Me?
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 23 First-Person Activity Recognition: What Are They Doing to Me? M. S. Ryoo and Larry Matthies Jet Propulsion Laboratory,
More informationData Mining Algorithms Part 1. Dejan Sarka
Data Mining Algorithms Part 1 Dejan Sarka Join the conversation on Twitter: @DevWeek #DW2015 Instructor Bio Dejan Sarka (dsarka@solidq.com) 30 years of experience SQL Server MVP, MCT, 13 books 7+ courses
More informationSegmentation & Clustering
EECS 442 Computer vision Segmentation & Clustering Segmentation in human vision K-mean clustering Mean-shift Graph-cut Reading: Chapters 14 [FP] Some slides of this lectures are courtesy of prof F. Li,
More informationWho are you? Learning person specific classifiers from video
Who are you? Learning person specific classifiers from video Josef Sivic, Mark Everingham 2 and Andrew Zisserman 3 INRIA, WILLOW Project, Laboratoire d Informatique de l Ecole Normale Superieure, Paris,
More informationVEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS
VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS Norbert Buch 1, Mark Cracknell 2, James Orwell 1 and Sergio A. Velastin 1 1. Kingston University, Penrhyn Road, Kingston upon Thames, KT1 2EE,
More informationMIFT: A Mirror Reflection Invariant Feature Descriptor
MIFT: A Mirror Reflection Invariant Feature Descriptor Xiaojie Guo, Xiaochun Cao, Jiawan Zhang, and Xuewei Li School of Computer Science and Technology Tianjin University, China {xguo,xcao,jwzhang,lixuewei}@tju.edu.cn
More information