Indexing 3D Scenes Using the Interaction Bisector Surface Xi Zhao He Wang Taku Komura University of Edinburgh.

Slides:



Advertisements
Similar presentations
Shape Matching and Object Recognition using Low Distortion Correspondence Alexander C. Berg, Tamara L. Berg, Jitendra Malik U.C. Berkeley.
Advertisements

Image Retrieval with Geometry-Preserving Visual Phrases
Office of SA to CNS GeoIntelligence Introduction Data Mining vs Image Mining Image Mining - Issues and Challenges CBIR Image Mining Process Ontology.
Relevance Feedback and User Interaction for CBIR Hai Le Supervisor: Dr. Sid Ray.
Image Retrieval: Current Techniques, Promising Directions, and Open Issues Yong Rui, Thomas Huang and Shih-Fu Chang Published in the Journal of Visual.
Evaluating Sketch Query Interfaces for a 3D Model Search Engine Patrick Min Joyce Chen, Tom Funkhouser Princeton Workshop on Shape-Based Retrieval and.
Chapter 8 Content-Based Image Retrieval. Query By Keyword: Some textual attributes (keywords) should be maintained for each image. The image can be indexed.
ARNOLD SMEULDERS MARCEL WORRING SIMONE SANTINI AMARNATH GUPTA RAMESH JAIN PRESENTERS FATIH CAKIR MELIHCAN TURK Content-Based Image Retrieval at the End.
Discrete Geometry Tutorial 2 1
Computing Stable and Compact Representation of Medial Axis Wenping Wang The University of Hong Kong.
Copyright, © Qiming Zhou GEOG3600. Geographical Information Systems Geographical Query.
Daozheng Chen 1, Mustafa Bilgic 2, Lise Getoor 1, David Jacobs 1, Lilyana Mihalkova 1, Tom Yeh 1 1 Department of Computer Science, University of Maryland,
Optimal invariant metrics for shape retrieval
Interactive Generation of Integrated Schemas Laura Chiticariu et al. Presented by: Meher Talat Shaikh.
Learning to Extract Form Labels Nguyen et al.. The Challenge We want to retrieve and integrate online databases We want to retrieve and integrate online.
Visual Querying By Color Perceptive Regions Alberto del Bimbo, M. Mugnaini, P. Pala, and F. Turco University of Florence, Italy Pattern Recognition, 1998.
Selecting Distinctive 3D Shape Descriptors for Similarity Retrieval Philip Shilane and Thomas Funkhouser.
Protein Sequence Classification Using Neighbor-Joining Method
Information retrieval Finding relevant data using irrelevant keys Example: database of photographic images sorted by number, date. DBMS: Well structured.
1 Street Generation for City Modeling Xavier Décoret, François Sillion iMAGIS GRAVIR/IMAG - INRIA.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Unsupervised Category Modeling, Recognition and Segmentation Sinisa Todorovic and Narendra Ahuja.
3D Thinning on Cell Complexes for Computing Curve and Surface Skeletons Lu Liu Advisor: Tao Ju Master Thesis Defense Dec 18 th, 2008.
Longbiao Kang, Baotian Hu, Xiangping Wu, Qingcai Chen, and Yan He Intelligent Computing Research Center, School of Computer Science and Technology, Harbin.
Dobrina Boltcheva, Mariette Yvinec, Jean-Daniel Boissonnat INRIA – Sophia Antipolis, France 1. Initialization Use the.
Nearest Neighbor Searching Under Uncertainty
Glasgow 02/02/04 NN k networks for content-based image retrieval Daniel Heesch.
Shape Analysis and Retrieval Structural Shape Descriptors Notes courtesy of Funk et al., SIGGRAPH 2004.
Organizing Heterogeneous Scene Collections through Contextual Focal Points Kai Xu, Rui Ma, Hao Zhang, Chenyang Zhu, Ariel Shamir, Daniel Cohen-Or, Hui.
Style Compatibility For 3D Furniture Models Tianqiang Liu 1 Aaron Hertzmann 2 Wilmot Li 2 Thomas Funkhouser 1 1 Princeton University 2 Adobe Research.
Axial Flip Invariance and Fast Exhaustive Searching with Wavelets Matthew Bolitho.
1 Multiple Classifier Based on Fuzzy C-Means for a Flower Image Retrieval Keita Fukuda, Tetsuya Takiguchi, Yasuo Ariki Graduate School of Engineering,
IEEE Int'l Symposium on Signal Processing and its Applications 1 An Unsupervised Learning Approach to Content-Based Image Retrieval Yixin Chen & James.
Chapter 4: Pattern Recognition. Classification is a process that assigns a label to an object according to some representation of the object’s properties.
Automated Critique of Sketched Mechanisms Jon Wetzel and Ken Forbus Qualitative Reasoning Group Northwestern University.
Dengsheng Zhang and Melissa Chen Yi Lim
INTERACTIVELY BROWSING LARGE IMAGE DATABASES Ronald Richter, Mathias Eitz and Marc Alexa.
1 A Compact Feature Representation and Image Indexing in Content- Based Image Retrieval A presentation by Gita Das PhD Candidate 29 Nov 2005 Supervisor:
Image Classification for Automatic Annotation
Category Independent Region Proposals Ian Endres and Derek Hoiem University of Illinois at Urbana-Champaign.
Content-Based Image Retrieval QBIC Homepage The State Hermitage Museum db2www/qbicSearch.mac/qbic?selLang=English.
9 of 18 Introduction to medial axis transforms and their computation Outline DefinitionsMAS PropertiesMAS CAD modelsTJC The challenges for computingTJC.
Dense Color Moment: A New Discriminative Color Descriptor Kylie Gorman, Mentor: Yang Zhang University of Central Florida I.Problem:  Create Robust Discriminative.
Methods for 3D Shape Matching and Retrieval
+ Speed Up Texture Classification in Clothing Retrieval System 電機三 吳瑋凌.
Yixin Chen and James Z. Wang The Pennsylvania State University
A Tutorial of the PrePPI Database Presenters: Gabriel Leis and Katrina Sherbina Loyola Marymount University Departments of Biology and Computer Science.
What is GIS? “A powerful set of tools for collecting, storing, retrieving, transforming and displaying spatial data”
1 Faculty of Information Technology Enhanced Generic Fourier Descriptor for Object-Based Image Retrieval Dengsheng Zhang, Guojun Lu Gippsland School of.
CENG 789 – Digital Geometry Processing 10- Data-Driven Shape Analysis
1 A Methodology for automatic retrieval of similarly shaped machinable components Mark Ascher - Dept of ECE.
Feature-sensitive 3D Shape Matching Andrei Sharf Tel-Aviv University Ariel Shamir IDC Hertzliya.
A Methodology for automatic retrieval of similarly shaped machinable components Mark Ascher - Dept of ECE.
1 A Methodology for automatic retrieval of similarly shaped machinable components Mark Ascher - Dept of ECE.
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
Recognizing Deformable Shapes
Self-Organizing Maps for Content-Based Image Database Retrieval
By Pradeep C.Venkat Srinath Srinivasan
Benchmarking CAD Search Techniques
Local Feature Extraction Using Scale-Space Decomposition
Content-Based Image Retrieval
Content-Based Image Retrieval
Section 3-4 Constructing Angle Bisectors
Scale-Space Representation of 3D Models and Topological Matching
Ying Dai Faculty of software and information science,
Improving Retrieval Performance of Zernike Moment Descriptor on Affined Shapes Dengsheng Zhang, Guojun Lu Gippsland School of Comp. & Info Tech Monash.
Scale-Space Representation for Matching of 3D Models
Scale-Space Representation for Matching of 3D Models
Objective- To graph a relationship in a table.
Relationship Template for Creating Scene Variations
Presentation transcript:

Indexing 3D Scenes Using the Interaction Bisector Surface Xi Zhao He Wang Taku Komura University of Edinburgh

How do we describe the spatial relationships between these pairs of objects? “surround” “tucked under” “hook on”

? “surround” “tuck under” “hook on” How can we quantify these spatial relationships?

d 2. Distance [Fisher et al. 2010] Previous Representations of Spatial Relationships 1.Contact [Fisher et al. 2011] 3. Relative direction [Fisher et al. 2010]

Limitation of Previous Presentations Distances between object centres for these two scenes are quite similar:

Objective Quantify spatial relationships by Interaction Bisector Surface (IBS)

Medial Axis and IBS IBS Medial Axis 2D Medial Axis [Shapiro. 2011] 3D Medial Axis [Sud et al. 2004]

Previous Representation vs IBS Distance between object centres: Interaction Bisector Surface (IBS):

Objective Apply our new representation IBS to 3D scenes analysis Scene classification Scene structure construction Retrieval

Basics of IBS Computation Features Applications Scene classification Scene structure analysis Spatial relationship based retrieval Overview

Computation of IBS Input Voronoi Diagram Select Voronoi edges between two parts Resulting IBS

IBS Between Two Objects

IBS Between Multiple Objects

IBS Features Features of IBS which are useful for scene analysis: Topological features (Betti numbers) Geometric features (distance, direction, PFH)

Topological Features: Betti Numbers b 1: number of loops b 2: number of closed surfaces b 1 = 1 b 2 = 0 b 1 = 0 b 2 = 1 b 1 = 2 b 2 = 1

b 1 = 0 b 2 = 0 b 1 = 0 b 2 = 1 b 1 = 1 b 2 = 0 b 1 = 2 b 2 = 0 b 1 = 3 b 2 = 0 b 1 = 4 b 2 = 0 Topological Features

Geometric Features dis dir PFH* *PFH: Point Feature Histogram [Rusu et al. 2008] Distance Direction Shape

Basics of IBS Computation Features Applications Scene classification Scene structure analysis Spatial relationship based retrieval Overview

Classification Database Resulting confusion matrix Our methodPrevious method

Building Scene Structure Build scene structure by HAC method Compute closeness matrix based on IBS

Retrieval of Object in the Scene Level 1Level 2 Level 3

Results: Query : Retrieval of Object in the Scene

Results: Query : level = 1

Retrieval of Object in the Scene Results: Query: level = 3

Evaluation of Retrieval Results Our method Previous method Precision Recall

Conclusion IBS is a rich representation of spatial relationships between objects in 3d scenes Classification Structure construction Retrieval

Limitations and Future Work Limitations The computational cost is higher Only focus on spatial relationship Future work Extra features (labels, object geometry) Whole scene retrieval Character-object interaction

Acknowledgement Anonymous reviewers CGVU group Shin Yoshizawa Attendees of user study China Scholarship Council EPSRC Standard Grant EU FP7/TOMSY