DIPTA 陳昱廷 Feature Detector II.

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.
BRIEF: Binary Robust Independent Elementary Features
T1.1- Analysis of acceleration opportunities and virtualization requirements in industrial applications Bologna, April 2012 UNIBO.
Presented by Xinyu Chang
BRISK (Presented by Josh Gleason)
CSE 473/573 Computer Vision and Image Processing (CVIP)
Computer Vision Lecture 18: Object Recognition II
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.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Instructor: Mircea Nicolescu Lecture 15 CS 485 / 685 Computer Vision.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Patch Descriptors CSE P 576 Larry Zitnick
Interest points CSE P 576 Larry Zitnick Many slides courtesy of Steve Seitz.
(1) Feature-point matching by D.J.Duff for CompVis Online: Feature Point Matching Detection,
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Lecture 4: Feature matching
Feature matching and tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Feature extraction: Corners and blobs
Scale Invariant Feature Transform (SIFT)
Blob detection.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
776 Computer Vision Jan-Michael Frahm, Enrique Dunn Spring 2013.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
REAL-TIME DETECTION AND TRACKING FOR AUGMENTED REALITY ON MOBILE PHONES Daniel Wagner, Member, IEEE, Gerhard Reitmayr, Member, IEEE, Alessandro Mulloni,
(Fri) Young Ki Baik Computer Vision Lab.
Computer vision.
05 - Feature Detection Overview Feature Detection –Intensity Extrema –Blob Detection –Corner Detection Feature Descriptors Feature Matching Conclusion.
1 Interest Operators Harris Corner Detector: the first and most basic interest operator Kadir Entropy Detector and its use in object recognition SIFT interest.
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.
CSCE 643 Computer Vision: Extractions of Image Features Jinxiang Chai.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
21 June 2009Robust Feature Matching in 2.3μs1 Simon Taylor Edward Rosten Tom Drummond University of Cambridge.
Feature extraction: Corners and blobs. Why extract features? Motivation: panorama stitching We have two images – how do we combine them?
Features, Feature descriptors, Matching Jana Kosecka George Mason University.
Chapter 13 (Prototype Methods and Nearest-Neighbors )
CSE 185 Introduction to Computer Vision Feature Matching.
A Tutorial on using SIFT Presented by Jimmy Huff (Slightly modified by Josiah Yoder for Winter )
Instructor: Mircea Nicolescu Lecture 10 CS 485 / 685 Computer Vision.
CSE 185 Introduction to Computer Vision Local Invariant Features.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
Advanced Science and Technology Letters Vol.43 (Multimedia 2013), pp A hardware design of optimized ORB.
Recognizing specific objects Matching with SIFT Original suggestion Lowe, 1999,2004.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
Blob detection.
Invariant Local Features Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging.
SIFT.
April 21, 2016Introduction to Artificial Intelligence Lecture 22: Computer Vision II 1 Canny Edge Detector The Canny edge detector is a good approximation.
Another Example: Circle Detection
SIFT Scale-Invariant Feature Transform David Lowe
Interest Points EE/CSE 576 Linda Shapiro.
TP12 - Local features: detection and description
Homework| Homework: Derive the following expression for the derivative of the inverse mapping Arun Das | Waterloo Autonomous Vehicles Lab.
Fitting Curve Models to Edges
Computer Vision Lecture 16: Texture II
CSE 455 – Guest Lectures 3 lectures Contact Interest points 1
From a presentation by Jimmy Huff Modified by Josiah Yoder
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
SIFT.
Fourier Transform of Boundaries
Feature descriptors and matching
Presented by Xu Miao April 20, 2005
Presentation transcript:

DIPTA 陳昱廷 Feature Detector II

Agenda FAST - E. Rosten. Machine Learning for High-speed Corner Detection, ORB - Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary R. Bradski: ORB: An efficient alternative to SIFT or SURF. ICCV 2011: BRISK - S. Leutenegger, M. Chli, and R. Siegwart, "BRISK: Binary Robust Invariant Scalable Keypoints," in IEEE International Conference on Computer Vision (ICCV), 2011

FAST Features from Accelerated Segment Test An improvement of Rosten’s previous work[1][2] The property of this detector is like it’s name -- FAST There is not any descriptor on this paper [1] Rosten, E., Drummond, T.: F using points and lines for high performance tracking. In: 10th IEEE International Conference on Computer Vision. Volume [2] Beijing, China, Springer (2005) Rosten, E., Reitmayr, G., Drummond, T.: Real-time video annotations for augmented reality. In: International Symposium on Visual Computing. (2005)

FAST - Previous Work A circle of 16 pixels around the coner candidate p p is classified as a coner if there exists more than N continuous pixels in the circle which all brighter or darker than Ip + t or Ip-t (t is a threshold) N was chosen as 12, so we exam only 1, 5, 9 and 13 to exclude very large numbers of non-corners

FAST - Previous Work Weakness: 1. The high-speed test does not generalize well for n < The choice and ordering of the fast test pixels contains implicit assumptions about the distribution of feature appearance. 3. Knowledge from the first 4 tests is discarded. 4. Multiple features are detected adjacent to one another.

FAST - Improvment Use decision tree to address the first three points. Each node of decision tree represents what location on the circle to compare with current point. The process of every node has 2 stages 1. Partition all pixels of current set into 3 subsets by each location on the circle. 2. Calculate entropy, which implies impurity, to choose suitable location on the circle.

FAST - Improvment

Stage 2 employs the algorithm used in ID3[1] and begins by selecting the x which yields the most information about whether the candidate pixel is a corner, measured by the entropy H(P) of Kp. [1] Quinlan, J.R.: Induction of decision trees. Machine Learning 1 (1986)

FAST - Improvment The choice of x then yields the information gain: The process is applied recursively on all three subsets (i.e. x b is selected to partition P b into P b,d, P b,s, P b,b ) until the entropy of the subset is zero. This means that all p in this subset have same value of Kp (all corner or all non-corner) This creates a decision tree which can correctly classify all corners seen in the training set and therefore (to a close approximation) correctly embodies the rules of the chosen FAST corner detector.

FAST - Improvment Use non-maximal suppression to address the last point Non-maximal suppression - find the feature of maximum score in a circle of radius r - iterative r to find enough number of feature Score function V:

ORB Oriented FAST and Rotated BRIEF[1] Use oFAST for keypoint detector and rBRIEF for decriptor The properties of this detector are rotation invariant and resistant to noise [1] M. Calonder, V. Lepetit, C. Strecha, and P. Fua. Brief: Bi­nary robust independent elementary features. In In European Conference on Computer Vision, 2010.

oFAST - FAST Use FAST-9 (circular radius of 9) Employ a Harris corner measure to order FAST keypoint

oFAST - orientation Orientation by Intensity Centroid atan2 is the quadrant-aware version of arctan P. L. Rosin. Measuring corner properties. Computer Vision and Image Understanding, 73(2): , 1999.

rBRIEF - BRIEF The BRIEF descriptor is a bit string description of an image patch constructed from a set of binary intensity tests. Consider a smoothed image patch p. A binary test T is defined by where p(x) is the intensity of p at a point x. The feature is defined as a vector of n binary tests (here n=256) Use Gaussian distribution around the center of the patch to randomly select test point pair (x, y)

rBRIEF – steered BRIEF

rBRIEF – Variance and Correlation High variance makes a feature more discriminative. Origin BRIEF has a property of a large variance but steered BRIEF lose it since the oriented corner keypoints present a more uniform appearance to binary tests Another desirable prop­erty is to have the tests uncorrelated, since then each test will contribute to the result, but steered BRIEF doesn’t has this

rBRIEF – learning good binary features Recover from the lose of variance and reduce correlation among the binary test Learning method for choosing good subset of binary tests, the algorithm is

BRISK Binary Robust Invariant Scalable Keypoints Scale-space FAST-based detector in combination with the assembly of a bit-string descriptor from intensity comparisons retrieved by dedicated sampling of each keypoint neighborhood Adaptive, high quality performance as in state-of-the-art algorithm, albeit at a dramaticlly lower computational cost The properties of this detector are rotation invariant and scale invariant

BRISK Create scale space. Compute FAST score across scale space. Pixel level non-maximal suppression. Compute sub-pixel maximum across patch. Compute continuous maximum across scales. Re-interpolate image coordinates from scale space feature point detection. ctures/BRISK.pptx

Create scale space

FAST feature detector FAST 9-16, requires at least 9 consecutive pixels in the 16- pixel circle to detect corner Special case In order to obtain FAST score of intra-octave, apply the FAST 5-8 mask on c 0

Non-maximal suppression

Subpixel maxima and scale selection Using points obtained by non- maximal suppression. 2D quadratic function is fit to the 3x3 patch surrounding the pixel and sub-pixel maximum is determined. The same is done for the layer above and below. These maxima are then interpolated using a 1D quadratic function across scale space and the local maximum is chosen as the scale for the feature is found.

Keypoint Description Sample pattern of smoothed pixels around feature. Separate pairs of pixels into two subsets, short-distance pairs and long-distance pairs. Compute local gradient between long-distance pairs. Sum gradients to determine feature orientation. Rotate short-distance pairs using orientation. Construct binary descriptor from rotated short-distance pairs.

Sampling pattern [1] E. T ola, V. Lepetit, and P. Fua. Daisy: an Efficient Dense Descriptor Applied to Wide Baseline Stereo. IEEE Transactions on P attern Analysis and Machine Intelligence (P AMI), 32(5):815– 830, 2010

Pattern pairs

Local gradient/keypoint orientation Strength of gradient between pairs is computed using Overall keypoint direction vector g is estimated by summing gradients of all pairs in long-distance set.

Building descriptor

Descriptor Matching Hamming distance computed for all pairs between images. Count matching bits between descriptors. Efficient computation because this is simply an XOR operation between two 512 bit strings. Threshold for matching is the number of bits able to be matched.