Image stitching with OpenCV

merge_frames.py

import cv2
from PIL import Image
import numpy as np

def cv2_estimate_dx_dy(prev_filename, curr_filename):
	"""
	Calculates dx and dy using OpenCV script for two consecutive frames
	"""
	# Load the previous and current frames
	prev_frame = cv2.imread(prev_filename, cv2.IMREAD_GRAYSCALE)
	curr_frame = cv2.imread(curr_filename, cv2.IMREAD_GRAYSCALE)

	# Initialize SIFT feature detector and compute keypoints and descriptors for both frames
	sift = cv2.SIFT_create()
	kp1, des1 = sift.detectAndCompute(prev_frame, None)
	kp2, des2 = sift.detectAndCompute(curr_frame, None)

	# Initialize brute-force matcher
	bf = cv2.BFMatcher(cv2.NORM_L2, crossCheck=True)

	# Match features between the two frames
	matches = bf.match(des1, des2)

	# Sort matches by distance
	matches = sorted(matches, key=lambda x: x.distance)

	# Select the top n matches
	n = min(50, len(matches))
	matched_kp1 = [kp1[match.queryIdx] for match in matches[:n]]
	matched_kp2 = [kp2[match.trainIdx] for match in matches[:n]]

	# Estimate the affine transformation matrix between matched keypoints
	M, _ = cv2.estimateAffinePartial2D(
		np.float32([kp.pt for kp in matched_kp1]).reshape(-1, 2),
		np.float32([kp.pt for kp in matched_kp2]).reshape(-1, 2)
	)

	# Extract the translation vector from the affine matrix
	dx, dy = M[:2, 2]

	return dx, dy

# Set the width and height of the final merged image
width = 5000
height = 5000

N=125

# Find the maximum width and height of any of the frames
max_width = 0
max_height = 0

for i in range(1, N+1):
	# Open the next frame image
	filename = f"1/output_frames_{i:03d}.jpg"
	next_frame = Image.open(filename)

	# Update the maximum width and height
	max_width = max(max_width, next_frame.width)
	max_height = max(max_height, next_frame.height)

# Set the starting position of the first frame
x_offset = max_width - 1
y_offset = height - max_height  # Updated to bottom left corner

# Create a new blank image to merge the frames onto
merged_image = Image.new('RGB', (width, height))

# Initialize dx and dy
dx = 0
dy = 0

for i in range(1, N+1):
	# Open the next frame image
	filename = f"1/output_frames_{i:03d}.jpg"
	next_frame = Image.open(filename)
	print(filename)

	if i == 1:
		# For the first frame, set dx and dy according to the OpenCV script
		dx, dy = cv2_estimate_dx_dy(filename, f"1/output_frames_{i+1:03d}.jpg")
	elif i == 2:
		# For the second frame, set dx and dy according to the OpenCV script
		dx, dy = cv2_estimate_dx_dy(f"1/output_frames_{i-1:03d}.jpg", filename)
	else:
		# Calculate dx and dy based on the previous frame's position and the calculated values from the OpenCV script
		x_offset += abs(dx)
		y_offset -= abs(dy)
		dx, dy = cv2_estimate_dx_dy(f"1/output_frames_{i-1:03d}.jpg", filename)

	# Merge the next frame onto the blank image
	merged_image.paste(next_frame, (round(x_offset), round(y_offset)))

# Save the final merged image
merged_image.save("merged_image.jpg")