linear solution to scale and rotation invariant object matching
DESCRIPTION
Linear Solution to Scale and Rotation Invariant Object Matching. Professor: 王聖智 教授 Student : 周 節. Outline. Introduction Method Result Conclusion Reference. Problem. Template image Target image. Problem. Template image and mesh. Target image. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/1.jpg)
Linear Solution to Scale and Rotation Invariant Object Matching
Professor: 王聖智 教授 Student : 周 節
![Page 2: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/2.jpg)
Outline Introduction Method Result Conclusion Reference
![Page 3: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/3.jpg)
Problem
Template image Target image
3
![Page 4: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/4.jpg)
Problem
Template image and mesh
Target image
Matching
Target Mesh
![Page 5: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/5.jpg)
Challenges
Template Image
Target Images
![Page 6: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/6.jpg)
Challenges
Template Image
Target Images
![Page 7: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/7.jpg)
:wRelated Works
Hough Transform and RANSAC Graph matching
Dynamic Programming Max flow – min cut [Ishikawa 2000, Roy 98] Greedy schemes (ICM [Besag 86], Relaxation
Labeling [Rosenfeld 76]) Back tracking with heuristics [Grimson 1988] Graph Cuts [Boykov & Zabih 2001] Belief Propagation [Pearl 88, Weiss 2001]
Convex approximation [Berg 2005, Jiang 2007, etc.]
![Page 8: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/8.jpg)
Method
1. A linear method to optimize the matching from template to target
2. The linear approximation is simplified so that its size is largely decoupled from the number of target candidate features points
3. Successive refinement for accurate matching
![Page 9: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/9.jpg)
Method
1. A linear method to optimize the matching from template to target
2. The linear approximation is simplified so that its size is largely decoupled from the number of target candidate features points
3. Successive refinement for accurate matching
![Page 10: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/10.jpg)
The Optimization Problem
![Page 11: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/11.jpg)
The Optimization Problem
Matching cost Pairwise consistency
![Page 12: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/12.jpg)
In Compact Matrix Form
Matching cost Pairwise consistency
![Page 13: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/13.jpg)
In Compact Matrix Form
We will turn the terms in circles to linear approximations
Matching cost Pairwise consistency
![Page 14: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/14.jpg)
The L1 Norm Linearization
It is well known that L1 norm is “linear”
min |x| min (y + z)Subject to x = y - z y, z >= 0
![Page 15: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/15.jpg)
The L1 Norm Linearization
It is well known that L1 norm is “linear”
By using two auxiliary matrices Y and Z,
| EMR – sEXT | 1’ne ( Y + Z ) 12
subject to Y – Z = EMR – sEXT Y, Z >= 0
Consistency term
Consistency term
min |x| min (y + z)Subject to x = y - z y, z >= 0
![Page 16: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/16.jpg)
Linearize the Scale Term
For any given sCut into Ns part 0 <S1<. . .< Sns
![Page 17: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/17.jpg)
Linearize the Scale Term
For any given sCut into Ns part 0 <S1<. . .< Sns
For any given XX1, X2…Xns
![Page 18: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/18.jpg)
Linearize the Scale Term
For any given sCut into Ns part 0 <S1<. . .< Sns
For any given XX1, X2…Xns
![Page 19: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/19.jpg)
Linearize the Scale Term
For any given sCut into Ns part 0 <S1<. . .< Sns
For any given XX1, X2…Xns
![Page 20: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/20.jpg)
Linearize the Scale Term
All sites select the same scale
![Page 21: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/21.jpg)
Linearize Rotation Matrix
In graphics:
![Page 22: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/22.jpg)
The Linear Optimization
T* = XT
Target point estimation:
![Page 23: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/23.jpg)
Method
1. A linear method to optimize the matching from template to target
2. The linear approximation is simplified so that its size is largely decoupled from the number of target candidate features points
3. Successive refinement for accurate matching
![Page 24: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/24.jpg)
Convex optimization problem
24
Reference:http://www.stanford.edu/class/ee364a/lectures/problems.pdf
![Page 25: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/25.jpg)
The Lower Convex Hull Property Cost surfaces can be replaced by their lower convex
hulls without changing the LP solution
A cost “surface” for one point on the template
The lower convex hull
![Page 26: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/26.jpg)
Removing Unnecessary Variables Only the variables that correspond to the lower convex
hull vertices need to be involved in the optimization
# of original target candidates: 2500
# of effective target candidates: 19
![Page 27: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/27.jpg)
Complexity of the LP
28 effective target candidates 1034 effective target candidates
10,000 target candidates 1 million target candidates
The size of the LP is largely decoupled from the number of target candidates
![Page 28: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/28.jpg)
Method
1. A linear method to optimize the matching from template to target
2. The linear approximation is simplified so that its size is largely decoupled from the number of target candidate features points
3. Successive refinement for accurate matching
![Page 29: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/29.jpg)
Successive Refinement
![Page 30: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/30.jpg)
Result
![Page 31: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/31.jpg)
Matching Objects in Real Images
![Page 32: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/32.jpg)
Result Videos
![Page 33: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/33.jpg)
Statistics
book magazine bear butterfly bee fish
#frames 856 601 601 771 101 131
#model 151 409 235 124 206 130
#target 2143 1724 1683 1405 1029 7316
time 1.6s 11s 2.2s 1s 2s 0.9s
accuracy 99% 97% 88% 95% 79% 95%
![Page 34: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/34.jpg)
Results Comparison
![Page 35: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/35.jpg)
Accuracy and Efficiency
![Page 36: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/36.jpg)
Experiments on Ground Truth Data
Error distributions for fish dataset
The proposed method
Othermethods
![Page 37: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/37.jpg)
Experiments on Ground Truth Data
Error distributions for random dot dataset
The proposed method
Othermethods
![Page 38: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/38.jpg)
Conclusion
A linear method to solve scale and rotation invariant matching problems accurately and efficiently The proposed method is flexible and can be used to
match images using different features It is useful for many applications including object
detection, tracking and activity recognition
![Page 39: Linear Solution to Scale and Rotation Invariant Object Matching](https://reader035.vdocuments.net/reader035/viewer/2022062321/56813714550346895d9e9dd6/html5/thumbnails/39.jpg)
Reference
Hao Jiang and Stella X. Yu, “Linear Solution to Scale and Rotation Invariant Object Matching”, IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR'09)
http://www.stanford.edu/class/ee364a/lectures.html