surf: speeded up robust features
DESCRIPTION
SURF: Speeded Up Robust Features. 授課教授 : 連震杰 教授 Group number: 20 Advisor: Tzuu-Hseng S. Li Group members: E24956552 何雅芳 E24951099 蕭信揚 N26984224 李佳樺 aiRobots Laboratory, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C. Outline. - PowerPoint PPT PresentationTRANSCRIPT
1 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
SURF: Speeded Up Robust Features
授課教授 : 連震杰 教授
Group number: 20Advisor: Tzuu-Hseng S. Li
Group members: E24956552 何雅芳E24951099 蕭信揚N26984224 李佳樺
aiRobots Laboratory, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C.
2 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
3 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
4 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Introduction
• The task of finding point correspondences between two images of the same scene or object is part of many computer vision applications.
• This article presents a novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features).
• SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
5 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Introduction (cont’d)
• The search for discrete image point correspondences can be divided into three main steps.
Step1. DetectorInterest points are selected
Step2. DescriptorExtract the vector for matching
Step3. MatchOften based on a distance
between the vector
Most valuable property:Repeatability
(whether it reliably finds the same interest points under different viewing condition.)
Focus on scale and
image rotation invariant.
6 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
7 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Related Work
• Interest Point DetectionHarris corner detector ‧most widely used
‧based on the eigenvalues
‧not scale-invariant
Automatic scale selection detector
‧experimented both the determinant of the
Hessian matrix as well as Laplacian.
Scale-invariant feature detectors
(Mikolajczyk , Schmid)
‧Harris-Laplace and Hessian-Laplace
‧The location is selected by the determinant
of Hessian matrix.
‧The scale is selected by the Laplacian.
SIFT ‧Approximated the LoG by a DoG filter.
=> (1) Using the determinant of the Hessian matrix rather than its trace (the Laplacian) seems advantageous, (2) approximations like the DoG can bring speed at a low cost in terms of lost accuracy.
8 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Related Work (cont’d)
• Interest Point DescriptionSIFT ‧computes a histogram of local oriented gradients around
the interest point and stores the bins in a 128-dimensional
vector.
PCA-SIFT ‧Yields a 36-dimensional descriptor (=>Fast)
‧To be less distinctive than SIFT
GLOH ‧More distinctive with the same number of dimensions.
‧Computationally more expensive.
=> The SIFT descriptor still seems to be the most appealing descriptor for practical uses, and hence also the most widely used nowadays.
9 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Related Work (cont’d)
• Our approach
Step1. Fast-Hessian detectorBased on the Hessian matrix but
use a very basic approximation – DoG
Step2. SURF DescriptorDescribes a distribution of Haar-wavelet
Responses within the interest point neighborhood
Step3. MatchPresent a new indexing step based on
the sign of the Laplacian(Speed up & increase the robustness)
+Integral image
(reduce the computation time)
+Integral image
(reduce the computation time)
Integral image:),(x, ),()x(
0 0yxjiII
xi
i
yj
j
★Question:Why can this
methodreduce the
computationtime?
DBCA
(1)Fast implementation of box type convolution filters(2)Independent of its size
A
B
C
DB-D
C-D Σ
Property…
(x,y)
)x(I
Answer…
10 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
11 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Fast-Hessian Detector
• Hessian matrix H( x , σ) in x at scale σ is defined as
• Approximation LoG with box filters => DoG
),x( ),x(
),x( ),x(),x(
yyxy
xyxx
LL
LLH
)x()(),x(,2
2
Igx
Lxx
Gaussian second order derivative
x-dir y-dir xy-dir
Gaussian) ofdeviation dradscale(Stan:
),(x
yx
),x(),x(
)x())()((),x(2
2
2
2
xxxx
xx
LkL
Igx
kgx
D
Box filters (instead of Gaussian)
x-dir y-dir xy-dir
9x9 box filter with σ=1.22
approx )9.0()det( xyyyxx DDDH
12 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
• The scale space is analysed by up-scaling the filter size rather than iteratively reducing the image size.
• The scale space is divided into octaves. An octave represents a series of increasing filter response maps.
Fast-Hessian Detector (cont’d)sc
ale
9 x 9 (σ=1.2)
15 x 15 (σ=2.0)
21 x 21 (σ=2.8)
27 x 27 (σ=3.6)
Octave1 (increase:6)
For each new octave, the filter size increase is doubled.(going from 6 to 12 to 24…)
It is selected as the interest point only if it is larger thanall of these neighbors.
15 x 15 (σ=2.0)
27 x 27 (σ=2.8)
39 x 39 (σ=5.2)
51 x 51 (σ=6.8)
Octave2 (increase:12)
13 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Q & A (Fast-Hessian Detector)
• Question1. 以放大 filter 的 size 代替將圖片縮小,有什麼好處 ?
• Answer1. 因為 integral image 的使用,使得計算量不會隨 filter 的 size 增加,且沒有將圖片縮小,圖片就不會失真。
14 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
15 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
SURF Descriptor
Orientation Assignment
Fixing a reproducible orientation based on information from acircular region around the interest point.
Descriptor Components
Construct a square region alignedto the selected orientation, andextract the SURF descriptor from it.
Interestpoint Features
16 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
17 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Orientation Assignment
• Haar Wavelet
• Orientation
dx
dy
4s
a-b
a
b
6s
Image
Interest point
dx
dy
π/3(dx1,dy1)
(dx2,dy2)Orientation
ABC
DEF
=A-B-D+E
=B-C-E+F
Σ=-A+2B-C+D-2E+F
18 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
19 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Descriptor Components
• Constructing a square region centered around the interest point, and oriented along the orientation.
• The region is split up regularly into smaller 4 × 4 square sub-regions.
• (4x4)x4=> a 64 dimensional vector
20s
Horizontal direction
Vertical direction
),,,(v yxyx dddd
Haar wavelet(filter size 2s)
20 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
• Question1. Why to use Σ|dx| and Σ|dy| ?• Answer1.
• Question2. Why to use Haar wavelet response?• Answer2.
Q&A(SURF Descriptor)
21 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
22 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Matching
• For fast indexing during the matching stage, the sign of the Laplacian (i.e. the trace of the Hessian matrix) for the underlying interest point is included.
• In the matching stage, we only compare features if they have the same type of contrast.
yyxx DDH )(Tr
23 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
24 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Experiments
• Scale variant + rotation
25 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Experiments (cont’d)
• Rotation
26 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Experiments (cont’d)
• Blurred
27 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Experiments (cont’d)
• Photometric deformations
28 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Outline
• Introduction• Related Work • Fast-Hessian Detector• SURF Descriptor
– Orientation Assignment– Descriptor Components
• Matching• Experiments• Conclusion
29 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
Conclusion
• SURF outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
• Future work will aim at optimizing the code for additional speed up.
30 aiRobots Lab., EE Dept., NCKUaiRobots Lab., EE Dept., NCKU
★ Thanks for your attention!!