The Terrapins Computer Vision Laboratory University of Maryland.

Slides:



Advertisements
Similar presentations
Feature Detection. Description Localization More Points Robust to occlusion Works with less texture More Repeatable Robust detection Precise localization.
Advertisements

Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Presented by Xinyu Chang
1 Challenge the future HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences Omar Oreifej Zicheng Liu CVPR 2013.
Geometry 2: A taste of projective geometry Introduction to Computer Vision Ronen Basri Weizmann Institute of Science.
Image alignment Image from
Matching with Invariant Features
Image alignment Image from
Affine Linear Transformations Prof. Graeme Bailey (notes modified from Noah Snavely, Spring 2009)
Image alignment.
A Study of Approaches for Object Recognition
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Object Recognition Using Distinctive Image Feature From Scale-Invariant Key point D. Lowe, IJCV 2004 Presenting – Anat Kaspi.
Object Class Recognition Using Discriminative Local Features Gyuri Dorko and Cordelia Schmid.
Scale Invariant Feature Transform (SIFT)
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from:  David Lowe, UBC  Jiri Matas, CMP Prague
Evaluation of features detectors and descriptors based on 3D objects P. Moreels - P. Perona California Institute of Technology.
Image Matching via Saliency Region Correspondences Alexander Toshev Jianbo Shi Kostas Daniilidis IEEE Conference on Computer Vision and Pattern Recognition.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Visual Screen: Transforming an Ordinary Screen into a Touch Screen Zhengyou Zhang & Ying Shan Vision Technology Group Microsoft Research
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2006 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography.
Image alignment.
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
AdvisorStudent Dr. Jia Li Shaojun Liu Dept. of Computer Science and Engineering, Oakland University 3D Shape Classification Using Conformal Mapping In.
CSE 473/573 Computer Vision and Image Processing (CVIP) Ifeoma Nwogu Lecture 35 – Review for midterm.
Final Exam Review CS485/685 Computer Vision Prof. Bebis.
Action recognition with improved trajectories
Internet-scale Imagery for Graphics and Vision James Hays cs195g Computational Photography Brown University, Spring 2010.
Object Tracking/Recognition using Invariant Local Features Applications l Mobile robots, driver assistance l Cell phone location or object recognition.
The Brightness Constraint
Metrology 1.Perspective distortion. 2.Depth is lost.
Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.
Single View Geometry Course web page: vision.cis.udel.edu/cv April 9, 2003  Lecture 20.
Computer Vision 776 Jan-Michael Frahm 12/05/2011 Many slides from Derek Hoiem, James Hays.
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Puzzle Solver Sravan Bhagavatula EE 638 Project Stanford ECE.
Kylie Gorman WEEK 1-2 REVIEW. CONVERTING AN IMAGE FROM RGB TO HSV AND DISPLAY CHANNELS.
1 Image Matching using Local Symmetry Features Daniel Cabrini Hauagge Noah Snavely Cornell University.
Final Review Course web page: vision.cis.udel.edu/~cv May 21, 2003  Lecture 37.
Line Matching Jonghee Park GIST CV-Lab..  Lines –Fundamental feature in many computer vision fields 3D reconstruction, SLAM, motion estimation –Useful.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Image features and properties. Image content representation The simplest representation of an image pattern is to list image pixels, one after the other.
Linearizing (assuming small (u,v)): Brightness Constancy Equation: The Brightness Constraint Where:),(),(yxJyxII t  Each pixel provides 1 equation in.
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.
CSE 185 Introduction to Computer Vision Local Invariant Features.
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
Recognizing specific objects Matching with SIFT Original suggestion Lowe, 1999,2004.
SIFT.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Active Flattening of Curved Document Images via Two Structured Beams
A Plane-Based Approach to Mondrian Stereo Matching
SIFT Scale-Invariant Feature Transform David Lowe
Action-Grounded Push Affordance Bootstrapping of Unknown Objects
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
The Brightness Constraint
Feature description and matching
Homography From Wikipedia In the field of computer vision, any
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Brief Review of Recognition + Context
Large Scale Image Deduplication
Filtering Things to take away from this lecture An image as a function
Announcements Final is Thursday, March 16, 10:30-12:20
SIFT.
Feature descriptors and matching
Filtering An image as a function Digital vs. continuous images
Presented by Xu Miao April 20, 2005
Presentation transcript:

The Terrapins Computer Vision Laboratory University of Maryland

Justin Domke Yi Li Michi Nishigaki Xiaodong Yu Alap Karapurkar Kostas Bitsakos Cornelia Fermüller Yiannis Aloimonos and some others

A challenge for Understanding Vision Navigation Recognition Memory Active Vision

The approach Navigation Recognition

Navigation Build map using SLAM from laser Set way points

Recognition Strategy Proper Nouns: discriminative features and geometric transform very few internet images (3) General Nouns: shape descriptor internet images

SIFT Dense feature points Usually correct matches Poor at too much distortion

MSERs Sparse keypoints Usually correct matches Great at affine invariance

Recognition Strategy for Proper Nouns Image Compute Homography Feature matching using SIFT Examples Match with MSER (affine invariant) Unwarp using Edges

The matching Process Homography Initial matches Final matches

Another Example Initial matches Homography Final matches

Matches of planar objects

General nouns Segmentation for the ground from trinocular stereo for the upper camera from color Shape description using adjacent line segments

Segmentation from depth information Estimate the transformation of the ground plane between the different cameras

Estimation of the ground plane homography

The descriptor Fit edges to small lines Adjacent lines: encode the relative coordinates w.r.t pivot point. –C / Z shape –Y shape

The codebook for the descriptor The advantage of the codebook –Generic –Quantization -> fast generate the codebook –A large dataset –Extract descriptor –Cluster the descriptor

Classifier: Support Vector Machine Suppose we have N classes For each class, we train 1 SVM using images from this class vs other classes. Result: N SVM classifiers (linear classifier in high dimensional space)

Example: Apply this descriptor to natural images

Future steps Taking images: Segmentation into surfaces. Combine geometry (local occlusion information from motion and/or stereo) with edge information Recognition: surface boundaries, symmetry information