3-D Point Clouds Cluster

Slides:



Advertisements
Similar presentations
Coherent Laplacian 3D protrusion segmentation Oxford Brookes Vision Group Queen Mary, University of London, 11/12/2009 Fabio Cuzzolin.
Advertisements

3D Model Matching with Viewpoint-Invariant Patches(VIP) Reporter :鄒嘉恆 Date : 10/06/2009.
1 Manifold Alignment for Multitemporal Hyperspectral Image Classification H. Lexie Yang 1, Melba M. Crawford 2 School of Civil Engineering, Purdue University.
Computer Graphics Lecture 4 Geometry & Transformations.
Ongoing Challenges in Face Recognition Peter Belhumeur Columbia University New York City.
Mapping: Scaling Rotation Translation Warp
Localization of Piled Boxes by Means of the Hough Transform Dimitrios Katsoulas Institute for Pattern Recognition and Image Processing University of Freiburg.
Reflective Symmetry Detection in 3 Dimensions
A Study of Approaches for Object Recognition
Pattern Recognition Topic 1: Principle Component Analysis Shapiro chap
Correspondence & Symmetry
3-D Object Recognition From Shape Salvador Ruiz Correa Department of Electrical Engineering.
1 Numerical geometry of non-rigid shapes Spectral Methods Tutorial. Spectral Methods Tutorial 6 © Maks Ovsjanikov tosca.cs.technion.ac.il/book Numerical.
3-D Geometry.
1 Bronstein, Bronstein, and Kimmel Joint extrinsic and intrinsic similarity of non-rigid shapes Rock, paper, and scissors Joint extrinsic and intrinsic.
Object Recognition Using Geometric Hashing
MSU CSE 803 Stockman CV: Matching in 2D Matching 2D images to 2D images; Matching 2D images to 2D maps or 2D models; Matching 2D maps to 2D maps.
The Terrapins Computer Vision Laboratory University of Maryland.
Geometrically overlaying di ff erent representations of an object in a scene By: Senate Taka CS 104 Final Project.
Atul Singh Junior Undergraduate CSE, IIT Kanpur.  Dimension reduction is a technique which is used to represent a high dimensional data in a more compact.
1 Numerical geometry of non-rigid shapes A journey to non-rigid world objects Introduction non-rigid Alexander Bronstein Michael Bronstein Numerical geometry.
Nonlinear Dimensionality Reduction by Locally Linear Embedding Sam T. Roweis and Lawrence K. Saul Reference: "Nonlinear dimensionality reduction by locally.
Lijuan Zhao Advisors: Prof. Fatima Merchant Prof. Shishir Shah.
Nonlinear Dimensionality Reduction Approaches. Dimensionality Reduction The goal: The meaningful low-dimensional structures hidden in their high-dimensional.
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Manifold learning: Locally Linear Embedding Jieping Ye Department of Computer Science and Engineering Arizona State University
Principle Component Analysis Presented by: Sabbir Ahmed Roll: FH-227.
Out-of-plane Rotations Environment constraints ● Surveillance systems ● Car driver images ASM: ● Similarity does not remove 3D pose ● Multiple-view database.
Final Exam Review CS485/685 Computer Vision Prof. Bebis.
Recognizing Deformable Shapes Salvador Ruiz Correa Ph.D. Thesis, Electrical Engineering.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
Expression-invariant Face Recognition using Geodesic Distance Isometries Kerry Widder A Review of ‘Robust expression-invariant face recognition from partially.
Axial Flip Invariance and Fast Exhaustive Searching with Wavelets Matthew Bolitho.
Recognizing Deformable Shapes Salvador Ruiz Correa UW Ph.D. Graduate Researcher at Children’s Hospital.
Object Recognition in Images Slides originally created by Bernd Heisele.
Non-Euclidean Example: The Unit Sphere. Differential Geometry Formal mathematical theory Work with small ‘patches’ –the ‘patches’ look Euclidean Do calculus.
Geometric Hashing: A General and Efficient Model-Based Recognition Scheme Yehezkel Lamdan and Haim J. Wolfson ICCV 1988 Presented by Budi Purnomo Nov 23rd.
Histograms of Oriented Gradients for Human Detection(HOG)
H. Lexie Yang1, Dr. Melba M. Crawford2
J. Flusser, T. Suk, and B. Zitová Moments and Moment Invariants in Pattern Recognition The slides accompanying.
J. Flusser, T. Suk, and B. Zitová Moments and Moment Invariants in Pattern Recognition The slides accompanying.
Recognizing Deformable Shapes Salvador Ruiz Correa (CSE/EE576 Computer Vision I)
J. Flusser, T. Suk, and B. Zitová Moments and Moment Invariants in Pattern Recognition The slides accompanying.
J. Flusser, T. Suk, and B. Zitová Moments and Moment Invariants in Pattern Recognition
9.913 Pattern Recognition for Vision Class9 - Object Detection and Recognition Bernd Heisele.
Affine Registration in R m 5. The matching function allows to define tentative correspondences and a RANSAC-like algorithm can be used to estimate the.
J. Flusser, T. Suk, and B. Zitová Moments and Moment Invariants in Pattern Recognition The slides accompanying.
3D Face Recognition Using Range Images Literature Survey Joonsoo Lee 3/10/05.
1 Review and Summary We have covered a LOT of material, spending more time and more detail on 2D image segmentation and analysis, but hopefully giving.
Rongjie Lai University of Southern California Joint work with: Jian Liang, Alvin Wong, Hongkai Zhao 1 Geometric Understanding of Point Clouds using Laplace-Beltrami.
A. M. R. R. Bandara & L. Ranathunga
CSSE463: Image Recognition Day 26
Intrinsic Data Geometry from a Training Set
Recognizing Deformable Shapes
Comparing NARF and SIFT Key Point Extraction Algorithms
Unsupervised Riemannian Clustering of Probability Density Functions
Principal Component Analysis (PCA)
Principal Components Analysis
Parts of these slides are based on
Paper Presentation: Shape and Matching
Spectral Methods Tutorial 6 1 © Maks Ovsjanikov
Outline Nonlinear Dimension Reduction Brief introduction Isomap LLE
Shape matching and object recognition using shape contexts
CV: Matching in 2D Matching 2D images to 2D images; Matching 2D images to 2D maps or 2D models; Matching 2D maps to 2D maps MSU CSE 803 Stockman.
Brief Review of Recognition + Context
3-D Point Clouds Cluster
Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
Liyuan Li, Jerry Kah Eng Hoe, Xinguo Yu, Li Dong, and Xinqi Chu
Recognizing Deformable Shapes
NON-NEGATIVE COMPONENT PARTS OF SOUND FOR CLASSIFICATION Yong-Choon Cho, Seungjin Choi, Sung-Yang Bang Wen-Yi Chu Department of Computer Science &
Presentation transcript:

3-D Point Clouds Cluster Yang Jiao

Outline Introduction Problem Methodology Result 3-D Point Cloud Challenge Goal Methodology Find Invariant Classify Signature Cluster Analysis Result

3-D Point Cloud data points in some coordinate system hardware sensors such as stereo cameras, 3D scanners, or time-of-flight cameras, or generated from a computer program synthetically.

Challenge “posture” recognition 3 Dimension non-rigid, non-linear transformation

Goal  3D non-rigid objects recognition

Methodology 1. Find invariants from eigenfunctions 2. Using invariants as signature to classify different group 3. Cluster based on feature vector

Find Invariant intrinsic geometric analysis of underlying manifold LB eigenfunction Information of surface geometry principal component analysis Project orthogonal axes with greatest variability

Classify Signature Moment invariant insensitive to deformations

Cluster Analysis Feature vector Combine features from multiple dimension Pairwise similarity information

Result Hierarchy cluster Point clouds group Similarity between groups and group member

Result

Result Object Poses victoria horse seahorse gorilla david dog cat 1 6 3 4 7 5 pose2 2 pose3 pose4 pose5 Image

Error switching of eigenfunction values

References [1] Yehezkel Lamdan and Haim J Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In ICCV, volume 88, pages 238–249, 1988. [2] Daniel P Huttenlocher and Shimon Ullman. Object recognition using alignment. In Proceedings of the 1st International Conference on Computer Vision, pages 102–111, 1987. [3] Rongjie Lai and Hongkai Zhao. Multi-scale non-rigid point cloud registration using robust slicedwasserstein distance via laplace-beltrami eigenmap. arXiv preprint arXiv:1406.3758, 2014. [4] Jan Flusser, Barbara Zitova, and Tomas Suk. Moments and moment invariants in pattern recognition. John Wiley & Sons, 2009. [5] Lindsay I Smith. A tutorial on principal components analysis. Cornell University, USA, 51:52, 2002. [6] Joseph B Kruskal and Myron Wish. Multidimensional scaling, volume 11. Sage, 1978.

Thank you!