Homography and image alignment in Computer Vision - Model Pipeline Trace

Model Pipeline - Homography and image alignment

This pipeline aligns two images by finding a transformation called homography. It matches points between images, calculates the homography matrix, and warps one image to align with the other.

Data Flow - 5 Stages

1Input Images

2 images of size 800 x 600 pixels→Load two images to be aligned→2 images of size 800 x 600 pixels

Image1: photo of a building, Image2: photo of the same building from a different angle

↓

2Feature Detection

2 images of size 800 x 600 pixels→Detect keypoints and extract descriptors using SIFT→Keypoints: ~1500 points per image, Descriptors: 1500 x 128 per image

Keypoints: corners of windows, edges; Descriptors: 128-length vectors describing local patches

↓

3Feature Matching

Descriptors from both images (1500 x 128 each)→Match descriptors using FLANN matcher and filter with Lowe's ratio test→Matched points: ~300 pairs of keypoints

Matched points: (x1,y1) in Image1 matches (x2,y2) in Image2

↓

4Homography Estimation

~300 matched point pairs→Estimate homography matrix using RANSAC to remove outliers→3 x 3 homography matrix

Matrix H that maps points from Image2 to Image1 coordinates

↓

5Image Warping

Image2 (800 x 600), homography matrix (3 x 3)→Warp Image2 to align with Image1 using homography→Warped Image2 of size 800 x 600 pixels aligned to Image1

Warped Image2 shows building aligned with Image1

Training Trace - Epoch by Epoch

Loss
0.5 |****
0.4 |*** 
0.3 |**  
0.2 |*   
0.1 |*   
0.0 +----
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.45	0.60	Initial homography estimation with many outliers
2	0.30	0.75	RANSAC removes outliers, homography improves
3	0.15	0.90	Stable homography with good alignment
4	0.10	0.93	Fine tuning improves alignment slightly
5	0.08	0.95	Converged homography with minimal error

Prediction Trace - 4 Layers

Layer 1: Feature Detection

Layer 2: Feature Matching

Layer 3: Homography Estimation

Layer 4: Image Warping

Model Quiz - 3 Questions

What is the main purpose of the homography matrix in image alignment?

A To extract descriptors from image patches

B To detect keypoints in the images

C To map points from one image to corresponding points in another image

D To crop the images to the same size

Key Insight

Homography and image alignment rely on detecting and matching keypoints between images, then estimating a transformation matrix that aligns one image to another. Using RANSAC helps remove bad matches, improving the accuracy of the alignment.

Practice

1. What is the main purpose of computing a homography matrix in image alignment?

easy

A. To increase the brightness of an image

B. To detect edges in an image

C. To segment objects in an image

D. To find a transformation that maps points from one image to another

Solution

1. Step 1: Understand homography concept

   Homography is a matrix that relates points between two images taken from different views.

2. Step 2: Identify its use in image alignment

   It helps to map points from one image to corresponding points in another to align them.

3. Final Answer:

   To find a transformation that maps points from one image to another -> Option D

4. Quick Check:

   Homography = Point mapping [OK]

Hint: Homography maps points between images [OK]

Common Mistakes:

• Confusing homography with edge detection
• Thinking homography changes image brightness
• Mixing homography with image segmentation

2. Which OpenCV function is used to compute the homography matrix from matched points?

easy

A. cv2.warpPerspective()

B. cv2.findHomography()

C. cv2.matchTemplate()

D. cv2.resize()

Solution

1. Step 1: Identify function for homography calculation

   cv2.findHomography() computes the homography matrix from matched point sets.

2. Step 2: Differentiate from other functions

   cv2.warpPerspective applies the homography, matchTemplate finds template matches, resize changes image size.

3. Final Answer:

   cv2.findHomography() -> Option B

4. Quick Check:

   Compute homography = findHomography [OK]

Hint: Find homography matrix with cv2.findHomography() [OK]

Common Mistakes:

• Using warpPerspective to compute homography
• Confusing template matching with homography calculation
• Trying to resize image to get homography

3. Given the following code snippet, what will be the shape of aligned_img after applying homography?

import cv2
import numpy as np
img1 = cv2.imread('img1.jpg')
img2 = cv2.imread('img2.jpg')
pts1 = np.array([[10,10],[100,10],[100,100],[10,100]])
pts2 = np.array([[12,14],[102,12],[98,110],[14,108]])
H, _ = cv2.findHomography(pts1, pts2)
aligned_img = cv2.warpPerspective(img1, H, (img2.shape[1], img2.shape[0]))

medium

A. Same height and width as img1

B. Shape is (4, 2) because of points

C. Same height and width as img2

D. Shape depends on H matrix size

Solution

1. Step 1: Understand warpPerspective parameters

   The third parameter in warpPerspective sets output image size as (width, height).

2. Step 2: Check given size argument

   It uses (img2.shape[1], img2.shape[0]) which is width and height of img2.

3. Final Answer:

   Same height and width as img2 -> Option C

4. Quick Check:

   Output size = img2.shape [OK]

Hint: warpPerspective size param sets output image shape [OK]

Common Mistakes:

• Assuming output shape matches img1
• Thinking homography matrix size affects output shape
• Confusing point arrays with image shape

4. You wrote this code to align two images but get a distorted output. What is the likely error?

H, status = cv2.findHomography(pts1, pts2)
aligned = cv2.warpPerspective(img1, pts1, (img2.shape[1], img2.shape[0]))

medium

A. Using pts1 instead of H in warpPerspective

B. Swapping pts1 and pts2 in findHomography

C. Not converting points to float32

D. Missing cv2.imshow to display image

Solution

1. Step 1: Check warpPerspective arguments

   warpPerspective expects the homography matrix as the second argument, not point arrays.

2. Step 2: Identify incorrect argument usage

   Code passes pts1 (points) instead of H (homography matrix), causing distortion.

3. Final Answer:

   Using pts1 instead of H in warpPerspective -> Option A

4. Quick Check:

   warpPerspective needs homography matrix [OK]

Hint: Pass homography matrix, not points, to warpPerspective [OK]

Common Mistakes:

• Passing points instead of homography matrix
• Swapping source and destination points in findHomography
• Ignoring data type requirements for points

5. You want to stitch two images taken from different angles into a panorama. Which sequence of steps correctly uses homography for alignment?

hard

A. Detect keypoints -> Match points -> Compute homography -> Warp one image -> Blend images

B. Resize images -> Compute homography -> Detect edges -> Warp images -> Blend images

C. Match points -> Resize images -> Compute homography -> Warp images -> Detect keypoints

D. Warp images -> Detect keypoints -> Compute homography -> Match points -> Blend images

Solution

1. Step 1: Detect and match keypoints

   First, find keypoints in both images and match them to get corresponding points.

2. Step 2: Compute homography and warp image

   Use matched points to compute homography, then warp one image to align with the other.

3. Step 3: Blend images to create panorama

   Finally, blend the aligned images smoothly to form a panorama.

4. Final Answer:

   Detect keypoints -> Match points -> Compute homography -> Warp one image -> Blend images -> Option A

5. Quick Check:

   Correct panorama steps = Detect keypoints -> Match points -> Compute homography -> Warp one image -> Blend images [OK]

Hint: Detect -> Match -> Compute -> Warp -> Blend for panorama [OK]

Common Mistakes:

• Resizing images before matching points
• Warping images before computing homography
• Detecting keypoints after warping images