Group Meeting Presented by Wyman 10/14/2006

Slides:



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

Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Object Recognition from Local Scale-Invariant Features David G. Lowe Presented by Ashley L. Kapron.
BRISK (Presented by Josh Gleason)
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
TP14 - Local features: detection and description Computer Vision, FCUP, 2014 Miguel Coimbra Slides by Prof. Kristen Grauman.
CSE 473/573 Computer Vision and Image Processing (CVIP)
Instructor: Mircea Nicolescu Lecture 15 CS 485 / 685 Computer Vision.
Matching with Invariant Features
SURF: Speeded-Up Robust Features
Patch Descriptors CSE P 576 Larry Zitnick
Interest points CSE P 576 Larry Zitnick Many slides courtesy of Steve Seitz.
Lecture 6: Feature matching CS4670: Computer Vision Noah Snavely.
Lecture 4: Feature matching
Scale Invariant Feature Transform
Distinctive Image Feature from Scale-Invariant KeyPoints
Feature extraction: Corners and blobs
Scale Invariant Feature Transform (SIFT)
Representation, Description and Matching
Automatic Matching of Multi-View Images
Blob detection.
1 Invariant Local Feature for Object Recognition Presented by Wyman 2/05/2006.
Special Topic on Image Retrieval
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
Overview Introduction to local features
Interest Point Descriptors
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Computer vision.
05 - Feature Detection Overview Feature Detection –Intensity Extrema –Blob Detection –Corner Detection Feature Descriptors Feature Matching Conclusion.
Overview Harris interest points Comparing interest points (SSD, ZNCC, SIFT) Scale & affine invariant interest points Evaluation and comparison of different.
Reporter: Fei-Fei Chen. Wide-baseline matching Object recognition Texture recognition Scene classification Robot wandering Motion tracking.
776 Computer Vision Jan-Michael Frahm Fall SIFT-detector Problem: want to detect features at different scales (sizes) and with different orientations!
CSE 185 Introduction to Computer Vision Local Invariant Features.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Distinctive Image Features from Scale-Invariant Keypoints Ronnie Bajwa Sameer Pawar * * Adapted from slides found online by Michael Kowalski, Lehigh University.
Harris Corner Detector & Scale Invariant Feature Transform (SIFT)
Overview Introduction to local features Harris interest points + SSD, ZNCC, SIFT Scale & affine invariant interest point detectors Evaluation and comparison.
Feature extraction: Corners and blobs. Why extract features? Motivation: panorama stitching We have two images – how do we combine them?
A Tutorial on using SIFT Presented by Jimmy Huff (Slightly modified by Josiah Yoder for Winter )
Local features: detection and description
CS654: Digital Image Analysis
SURF: Speeded Up Robust Features
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Frank Bergschneider February 21, 2014 Presented to National Instruments.
CSE 185 Introduction to Computer Vision Local Invariant Features.
Recognizing specific objects Matching with SIFT Original suggestion Lowe, 1999,2004.
Blob detection.
CS262: Computer Vision Lect 09: SIFT Descriptors
Interest Points EE/CSE 576 Linda Shapiro.
Distinctive Image Features from Scale-Invariant Keypoints
Scale Invariant Feature Transform (SIFT)
TP12 - Local features: detection and description
SURF detectors and descriptors
Scale and interest point descriptors
Local features: detection and description May 11th, 2017
Homework| Homework: Derive the following expression for the derivative of the inverse mapping Arun Das | Waterloo Autonomous Vehicles Lab.
SURF: Speeded-Up Robust Features
Feature description and matching
From a presentation by Jimmy Huff Modified by Josiah Yoder
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
Edge detection f(x,y) viewed as a smooth function
Lecture VI: Corner and Blob Detection
Feature descriptors and matching
Lecture 5: Feature invariance
Presented by Xu Miao April 20, 2005
Presentation transcript:

Group Meeting Presented by Wyman 10/14/2006 SURF: Speeded Up Robust Features, ECCV 2006. Herbert Bay, Tinne Tuytelaars, and Luc Van Gool Group Meeting Presented by Wyman 10/14/2006

Background Local invariant Interest point detector-descriptor For finding correspondences between two images of the same scene or object Many applications, including 3D reconstruction, image retrieval and object recognition SIFT is one of the best but slow Image of size 1000 x 700 described in around 6 seconds (actual cost depends on the # features generated, 4000 in this case) 128-D feature vectors

Motivation Fast interest point detection Distinctive interest point description Speeded-up descriptor matching Invariant to common image transformations: Image rotation Scale changes Illumination change Small change in Viewpoint

Methodology Using integral images for major speed up Integral Image (summed area tables) is an intermediate representation for the image and contains the sum of gray scale pixel values of image Second order derivative and Haar-wavelet response Cost four additions operation only

Detection Hessian-based interest point localization Lxx(x,y,σ) is the Laplacian of Gaussian of the image It is the convolution of the Gaussian second order derivative with the image Lindeberg showed Gaussian function is optimal for scale-space analysis This paper argues that Gaussian is overrated since the property that no new structures can appear while going to lower resolution is not proven in 2D case

Detection Approximated second order derivatives with box filters (mean/average filter)

Detection Scale analysis with constant image size Scale spaces are usually implemented as image pyramids. The images are repeatedly smoothed with a Gaussian and subsequently sub-sampled in order to achieve a higher level of the pyramid. Due to the use of box filters and integral images, we do not have to iteratively apply the same filter to the output of a previously filtered layer, but instead can apply such filters of any size at exactly the same speed directly on the original image. 9 x 9, 15 x 15, 21 x 21, 27 x 27  39 x 39, 51 x 51 … 1st octave 2nd octave

Detection Non-maximum suppression and interpolation Blob-like feature detector

Description Orientation Assignment Circular neighborhood of radius 6s around the interest point (s = the scale at which the point was detected) x response y response Side length = 4s Cost 6 operation to compute the response

Description Dominant orientation The Haar wavelet responses are represented as vectors Sum all responses within a sliding orientation window covering an angle of 60 degree The two summed response yield a new vector The longest vector is the dominant orientation Second longest is … ignored

Description Split the interest region up into 4 x 4 square sub-regions with 5 x 5 regularly spaced sample points inside Calculate Haar wavelet response dx and dy Weight the response with a Gaussian kernel centered at the interest point Sum the response over each sub-region for dx and dy separately  feature vector of length 32 In order to bring in information about the polarity of the intensity changes, extract the sum of absolute value of the responses  feature vector of length 64 Normalize the vector into unit length

Description

Description SURF-128 The sum of dx and |dx| are computed separately for dy < 0 and dy >0 Similarly for the sum of dy and |dy| This doubles the length of a feature vector

Matching Fast indexing through the sign of the Laplacian for the underlying interest point The sign of trace of the Hessian matrix Trace = Lxx + Lyy Either 0 or 1 (Hard thresholding, may have boundary effect …) In the matching stage, compare features if they have the same type of contrast (sign)

Experimental Results

Experimental Results Viewpoint change of 30 degrees

Experimental Results

Experimental Results 1. Wall 2. Boat 3. Bikes 4. Trees

Analysis I have carried out a benchmark on SURF and SIFT using the Visual Geometry Group Dataset SURF: Fast-Hessian detector + SURF descriptor SIFT: DOG detector + SIFT descriptor SURF SIFT Memory Cost SURF: 64 floats SURF-128: 128 floats 128 bytes Speed (Time to detect and describe 4000 features) SURF: 2.4 seconds 6 seconds # Features detected in 1024x768 image (Default threshold) ~ 1000 > 3000

Analysis img# bikes boat graf leuven wall 2 o ++ -- - --- 3 ---- 4 + Legend + SURF better by 0.1 recall rate - SIFT better by 0.1 recall rate o Draw img# bikes boat graf leuven wall 2 o ++ -- - --- 3 ---- 4 + +++ 5 6

Analysis SURF is good at SURF is poor at handling serious blurring handling image rotation SURF is poor at handling viewpoint change handling illumination change SURF is always better than the SIFT implemented by VGG but not the original SIFT img# Bikes Boat graf leuven wall 2 o ++ -- - --- 3 ---- 4 + +++ 5 6

Conclusion SURF describes image faster than SIFT by 3 times SURF is not as well as SIFT on invariance to illumination change and viewpoint change