CS131 Panoramic Image Stitching - Stanford Computer Vision Lab

PA1 Session 18-Oct-13Jiayuan Ma

CS131Panoramic Image Stitching

Jiayuan Ma18-Oct-13

1

Thursday, October 17, 13


Agenda• Objective• Main flow• Skeleton code• Results

2



Objective

3

Multiple images into one panorama!



Main Flow

• Detect key points

4



Detect Key Points

5



Skeleton Code• Detect key points (Done for you!)– Under KeypointDetect

6

[feature, DoG pyr, Gaussian pyr] = detect_features(input image)



Main Flow

• Detect key points• Build the SIFT descriptors

7

(v1, v2, . . . , v128)(u1, u2, . . . , u128)



Build the SIFT Descriptors

8

This is just an illustration!



Skeleton Code• Build the SIFT descriptors– Read this paper http://www.cs.ubc.ca/~lowe/papers/

ijcv04.pdf first! • Input– Gaussian pyramid– key point location– key point scale index

• Output– A set of 128-dim vectors

9


http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf





Skeleton Code• Build the SIFT descriptors (30 lines of code)– Compute gradient magnitude and orientation– For each key point• Find a patch (tricky round-off)• Compute orientation of the patch• Build the histogram (edge case)

10



Main Flow

• Detect key points• Build the SIFT descriptors• Match SIFT descriptors

11

(v1, v2, . . . , v128)(u1, u2, . . . , u128)



Match SIFT Descriptors• Euclidean distance between descriptors

12



Skeleton Code• Match SIFT descriptors (6 lines of code)– Input: D1, D2, thresh (default 0.7)– Output: match [D1’s index, D2’s index]– Try to use one for loop– Useful command• repmat• sort

13



Main Flow

• Detect key points• Build the SIFT descriptors• Match SIFT descriptors• Fitting the transformation

14

(v1, v2, . . . , v128)(u1, u2, . . . , u128)

T =

2

4t11 t12 t13t21 t22 t230 0 1

3

5



Fitting the transformation• 2D transformations

15



Skeleton Code• Fit the transformation matrix

• Six variables– each point give two equations– at least three points

• Least squares

16

H =

2

4h11 h12 h13

h21 h22 h23

0 0 1

3

5



Main Flow

• Detect key points• Build the SIFT descriptors• Match SIFT descriptors• Fitting the transformation• RANSAC

17

(v1, v2, . . . , v128)(u1, u2, . . . , u128)



RANSAC• A further refinement of matches

18



Skeleton Code• RANSAC– ComputeError

19

��

2

4x2

y21

3

5�H

2

4x1

y11

3

5��2



Main Flow

• Detect key points• Build the SIFT descriptors• Match SIFT descriptors• Fitting the transformation• RANSAC

20

(v1, v2, . . . , v128)(u1, u2, . . . , u128)



Image Stitching• Almost done for you

• Recall from PS0– imtransform–maketform

21



Skeleton Code• Multiple Stitch (2 lines of code)– A simplified case of real-world scenario– Transformation is associative and invertible– Useful command• pinv

22



Skeleton Code• Tester.m– Scripts that help you to get started

• Evaluate.m– Scripts that tests your solution• Load fixed input from checkpoint• Run your implementation• Compare results with reference solution

23



Requirement• Due Date: 5pm Oct 28, 2013• Electronic submission only– [email protected]

• Code + Report– SIFT invariance and why it helps– DoG v.s. Dense SIFT– Why RANSAC– Your own stitches– Error discussion

24


mailto:[email protected]

mailto:[email protected]


Results

25



Results

26



Some Advice• About choosing your own images

• Questions?

27


Date post:	12-Feb-2022
Category:	Documents
Upload:	others
View:	5 times
Download:	0 times

CS131 Panoramic Image Stitching - Stanford Computer Vision Lab

Documents