SIFT DESCRIPTOR K Wasif 200807007 Mrityunjay 200807009.

Slides:



Advertisements
Similar presentations
Distinctive Image Features from Scale-Invariant Keypoints
Advertisements

Feature Detection. Description Localization More Points Robust to occlusion Works with less texture More Repeatable Robust detection Precise localization.
Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Object Recognition from Local Scale-Invariant Features David G. Lowe Presented by Ashley L. Kapron.
BRIEF: Binary Robust Independent Elementary Features
3D Model Matching with Viewpoint-Invariant Patches(VIP) Reporter :鄒嘉恆 Date : 10/06/2009.
A Fast Local Descriptor for Dense Matching Engin Tola, Vincent Lepetit, Pascal Fua Computer Vision Laboratory, EPFL Reporter : Jheng-You Lin 1.
SIFT & MatLab Pier Luigi Mazzeo.
Histograms of Oriented Gradients for Human Detection
Presented by Xinyu Chang
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
Team Programming Project Byunghyun (Byung) Jang Ph.D student Northeastern University Jul CRA-W/CDC Careers in High Performance Systems (CHiPS)
Histograms of Oriented Gradients for Human Detection Navneet Dalal and Bill Triggs CVPR 2005 Another Descriptor.
Distinctive Image Features from Scale- Invariant Keypoints Mohammad-Amin Ahantab Technische Universität München, Germany.
ECE 562 Computer Architecture and Design Project: Improving Feature Extraction Using SIFT on GPU Rodrigo Savage, Wo-Tak Wu.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Patch Descriptors CSE P 576 Larry Zitnick
SIFT on GPU ( the slides are not updated for newer versions of SiftGPU ) Changchang Wu 5/8/2007.
Object Recognition Using Distinctive Image Feature From Scale-Invariant Key point D. Lowe, IJCV 2004 Presenting – Anat Kaspi.
Scale Invariant Feature Transform (SIFT)
Blob detection.
1 Invariant Local Feature for Object Recognition Presented by Wyman 2/05/2006.
Lecture 6: Feature matching and alignment CS4670: Computer Vision Noah Snavely.
Overview Introduction to local features
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Computer vision.
Internet-scale Imagery for Graphics and Vision James Hays cs195g Computational Photography Brown University, Spring 2010.
“Low-Power, Real-Time Object- Recognition Processors for Mobile Vision Systems”, IEEE Micro Jinwook Oh ; Gyeonghoon Kim ; Injoon Hong ; Junyoung.
Bag of Visual Words for Image Representation & Visual Search Jianping Fan Dept of Computer Science UNC-Charlotte.
Overview Harris interest points Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points Evaluation and comparison of different.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Reporter: Fei-Fei Chen. Wide-baseline matching Object recognition Texture recognition Scene classification Robot wandering Motion tracking.
Wenqi Zhu 3D Reconstruction From Multiple Views Based on Scale-Invariant Feature Transform.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Implementing GIST on the GPU. Refrence Original Work  Aude Oliva, Antonio Torralba  Modeling the shape of the scene: a holistic representation of the.
CSC508 Convolution Operators. CSC508 Convolution Arguably the most fundamental operation of computer vision It’s a neighborhood operator –Similar to the.
Histograms of Oriented Gradients for Human Detection Navneet Dalal and Bill Triggs CVPR 2005 Another Descriptor.
1 Image Matching using Local Symmetry Features Daniel Cabrini Hauagge Noah Snavely Cornell University.
Distinctive Image Features from Scale-Invariant Keypoints David Lowe Presented by Tony X. Han March 11, 2008.
CS654: Digital Image Analysis Lecture 36: Feature Extraction and Analysis.
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison.
CUDA Basics. Overview What is CUDA? Data Parallelism Host-Device model Thread execution Matrix-multiplication.
A Tutorial on using SIFT Presented by Jimmy Huff (Slightly modified by Josiah Yoder for Winter )
Implementation and Optimization of SIFT on a OpenCL GPU Final Project 5/5/2010 Guy-Richard Kayombya.
Scale Invariant Feature Transform (SIFT)
CS 732: Advance Machine Learning
Line Matching Jonghee Park GIST CV-Lab..  Lines –Fundamental feature in many computer vision fields 3D reconstruction, SLAM, motion estimation –Useful.
Introduction to CUDA 1 of 2 Patrick Cozzi University of Pennsylvania CIS Fall 2014.
Presented by David Lee 3/20/2006
Presentation 3 Ruben Villegas Period: 05/31/2012 – 06/03/2012.
REU Week 1 Presented by Christina Peterson. Edge Detection Sobel ◦ Convolve image with derivative masks:  x:  y: ◦ Calculate gradient magnitude ◦ Apply.
Distinctive Image Features from Scale-Invariant Keypoints Presenter :JIA-HONG,DONG Advisor : Yen- Ting, Chen 1 David G. Lowe International Journal of Computer.
 Read Distinctive Image Features from Scale- Invariant Keypoints by Lowe  Dr. Tappen also gave a presentation on SIFT.  Helped clarify, what is going.
Blob detection.
Face recognition using Histograms of Oriented Gradients
Another Example: Circle Detection
Distinctive Image Features from Scale-Invariant Keypoints
Scale Invariant Feature Transform (SIFT)
SIFT paper.
SIFT on GPU Changchang Wu 5/8/2007.
Feature description and matching
Car Recognition Through SIFT Keypoint Matching
Report 1: Optical Flow and Sift
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
Aim of the project Take your image Submit it to the search engine
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
KFC: Keypoints, Features and Correspondences
Visualization of computational image feature descriptors.
Feature descriptors and matching
Presented by Xu Miao April 20, 2005
Presentation transcript:

SIFT DESCRIPTOR K Wasif Mrityunjay

INTRODUCTION SIFT features are local and based on the appearance of the object at interesting points, and are invariant to image scale and rotation Aim: Evaluate descriptors for each key point Achieve fast computation performance on GPU

INPUT OUTPUT Input: Key point, Orientation, Sigma, Gradient Magnitude (16*16), Gradient Orientation(16*16)‏ Output: Key point, Orientation, Sigma, Descriptors

GPU Implementation Each key point's descriptor evaluation is independent of other key points Pass gradient magnitude, gradient orientation, sigma for all key points in one pass Every row of blocks in a grid corresponds to a key point Every block in a row corresponds to 4*4 subregion of that row key point

FLOW 1) Grid Dimension (1024*16)‏ 2) Block Dimension (4*4)‏ 3) Gaussian Weight evaluation for each thread 4) Product of Gradient magnitude with weights 5) For each block create 8 orientation bins 6) Add the weighted magnitudes to bins based on gradient orientation. 7) Normalize the descriptor values when every block on the grid has finished its execution

ISSUES Divergence of threads Less Threads per block are being utilized Generalizing will effect the performance Shared Memory Expensive Operations used

RESULTS Key Points Time (ms) V340 Our Code 1) ) ) )

GRAPHS

REFRENCES 1) 2) 3) 4)

THANK YOU