question:okay well there are couple things to consider, my images are different sized and first image is reference so it won't have a homogprahy. Also since the initial images are different sized the morphed images might be different sized as well. The final panorama image must not lose image data and get as much as it can, what I mean is if final image cuts, disregards parts one of the warped images because it is too big we don't want that, instead the panorama image should adjust in size to fit all the warped images.

question:I am having error in image_merging(images, homographies) 195 y_offset, x_offset = max(0, -min_y), max(0, -min_x) 196 merged_image_slice = merged_image[y_offset:y_offset + img.shape[0], x_offset:x_offset + img.shape[1]] --> 197 merged_image_slice[~mask] = img[~mask] 198 199 return merged_image IndexError: boolean index did not match indexed array along dimension 1; dimension is 1067 but corresponding boolean dimension is 1068

question:something is wrong with height and width, for some reason panorama image is vertically got bigger instead of horizontally. I am displaying using matplotlib. And I see an image what has blackness underneath

question:ok look I fixed the problem and it was irrelevant but now I have a new problem, in my warp perspective function when I warp the image, the image gets aligned to left side from the interest point, what I mean is from the middle of the image however there is content on the left, so content is missing. Can you make sure there is no content missing ? Also this might have something to do with how homography is calculated, since warp_perspective only warps perspective according to already calculated homography. Here is my full code: "import numpy as np import cv2 import os import glob import matplotlib.pyplot as plt import time from kayla_tools import * def compute_homography_matrix(src_pts, dst_pts): def normalize_points(pts): pts_homogeneous = np.hstack((pts, np.ones((pts.shape[0], 1)))) centroid = np.mean(pts, axis=0) scale = np.sqrt(2) / np.mean(np.linalg.norm(pts - centroid, axis=1)) T = np.array([[scale, 0, -scale * centroid[0]], [0, scale, -scale * centroid[1]], [0, 0, 1]]) normalized_pts = (T @ pts_homogeneous.T).T return normalized_pts[:, :2], T src_pts_normalized, T1 = normalize_points(src_pts) dst_pts_normalized, T2 = normalize_points(dst_pts) A = [] for p1, p2 in zip(src_pts_normalized, dst_pts_normalized): x1, y1 = p1 x2, y2 = p2 A.append([0, 0, 0, -x1, -y1, -1, y2 * x1, y2 * y1, y2]) A.append([x1, y1, 1, 0, 0, 0, -x2 * x1, -x2 * y1, -x2]) A = np.array(A) try: _, _, VT = np.linalg.svd(A) except np.linalg.LinAlgError: return None h = VT[-1] H_normalized = h.reshape(3, 3) H = np.linalg.inv(T2) @ H_normalized @ T1 if np.abs(H[-1, -1]) > 1e-6: H = H / H[-1, -1] else: return None return H def filter_matches(matches, ratio_thres=0.7): filtered_matches = [] for match in matches: good_match = [] for m, n in match: if m.distance < ratio_thres * n.distance: good_match.append(m) filtered_matches.append(good_match) return filtered_matches def find_homography(keypoints, filtered_matches): homographies = [] skipped_indices = [] # Keep track of skipped images and their indices for i, matches in enumerate(filtered_matches): src_pts = np.float32([keypoints[0][m.queryIdx].pt for m in matches]).reshape(-1, 1, 2) dst_pts = np.float32([keypoints[i + 1][m.trainIdx].pt for m in matches]).reshape(-1, 1, 2) H = ransac_homography(src_pts, dst_pts) if H is not None: H = H.astype(np.float32) homographies.append(H) else: print(f"Warning: Homography computation failed for image pair (0, {i + 1}). Skipping.") skipped_indices.append(i + 1) # Add indices of skipped images to the list continue return homographies, skipped_indices def ransac_homography(src_pts, dst_pts, iterations=2000, threshold=3): best_inlier_count = 0 best_homography = None if len(src_pts) != len(dst_pts) or len(src_pts) < 4: raise ValueError("The number of source and destination points must be equal and at least 4.") src_pts = np.array(src_pts) dst_pts = np.array(dst_pts) for _ in range(iterations): indices = np.random.choice(len(src_pts), 4, replace=False) src_subset = src_pts[indices].reshape(-1, 2) dst_subset = dst_pts[indices].reshape(-1, 2) homography = compute_homography_matrix(src_subset, dst_subset) if homography is None: continue inliers = 0 for i in range(len(src_pts)): projected_point = np.dot(homography, np.append(src_pts[i], 1)) if np.abs(projected_point[-1]) > 1e-6: projected_point = projected_point / projected_point[-1] else: continue distance = np.linalg.norm(projected_point[:2] - dst_pts[i]) if distance < threshold: inliers += 1 if inliers > best_inlier_count: best_inlier_count = inliers best_homography = homography if best_homography is None: raise RuntimeError("Failed to find a valid homography matrix.") return best_homography def read_ground_truth_homographies(dataset_path): H_files = sorted(glob.glob(os.path.join(dataset_path, "H_*"))) ground_truth_homographies = [] for filename in H_files: H = np.loadtxt(filename) ground_truth_homographies.append(H) return ground_truth_homographies def warp_perspective(img, H, reverse=False): # Apply homography matrix to the source image corners print(img.shape) display_image(img) if reverse: H = np.linalg.inv(H) h, w = img.shape[0], img.shape[1] corners = np.array([[0, 0, 1], [w-1, 0, 1], [0, h-1, 1], [w-1, h-1, 1]]) transformed_corners = np.dot(H, corners.T).T transformed_corners /= transformed_corners[:, 2].reshape((-1, 1)) # Compute the bounding box of the transformed corners and # define the target_shape as the (height, width) of the bounding box min_x, min_y = transformed_corners.min(axis=0)[:2] max_x, max_y = transformed_corners.max(axis=0)[:2] target_shape = (int(np.round(max_y - min_y)), int(np.round(max_x - min_x))) h, w = target_shape target_y, target_x = np.meshgrid(np.arange(h), np.arange(w)) target_coordinates = np.stack([target_x.ravel(), target_y.ravel(), np.ones(target_x.size)]) source_coordinates = np.dot(np.linalg.inv(H), target_coordinates) source_coordinates /= source_coordinates[2, :] valid = np.logical_and(np.logical_and(0 <= source_coordinates[0, :], source_coordinates[0, :] < img.shape[1] - 1), np.logical_and(0 <= source_coordinates[1, :], source_coordinates[1, :] < img.shape[0] - 1)) # Change the dtype to int instead of float64 to save memory valid_source_coordinates = np.round(source_coordinates[:, valid].astype(np.float32)[:2]).astype(int) valid_target_coordinates = target_coordinates[:, valid].astype(int)[:2] valid_source_coordinates[0] = np.clip(valid_source_coordinates[0], 0, img.shape[1] - 1) valid_source_coordinates[1] = np.clip(valid_source_coordinates[1], 0, img.shape[0] - 1) valid_target_coordinates[0] = np.clip(valid_target_coordinates[0], 0, w - 1) valid_target_coordinates[1] = np.clip(valid_target_coordinates[1], 0, h - 1) warped_image = np.zeros((h, w, 3), dtype=np.uint8) for i in range(3): warped_image[..., i][valid_target_coordinates[1], valid_target_coordinates[0]] = img[..., i][valid_source_coordinates[1], valid_source_coordinates[0]] print(warped_image.shape) display_image(warped_image) return warped_image def image_merging(images, homographies): if len(images) - 1 != len(homographies): raise ValueError("The number of homography matrices must be one less than the number of images.") # Warp all images except the first one using their corresponding homography matrices warped_images = [images[0]] + [warp_perspective(img, H, True) for img, H in zip(images[1:], homographies)] # Compute the size of the merged image min_x, min_y, max_x, max_y = 0, 0, 0, 0 for img in warped_images: h, w = img.shape[:2] corners = np.array([[0, 0, 1], [h, 0, 1], [0, w, 1], [h, w, 1]]) min_x = min(min_x, corners[:, 1].min()) min_y = min(min_y, corners[:, 0].min()) max_x = max(max_x, corners[:, 1].max()) max_y = max(max_y, corners[:, 0].max()) print(corners, min_x, min_y, max_x, max_y) merged_height = int(np.ceil(max_y - min_y)) merged_width = int(np.ceil(max_x - min_x)) # Initialize the merged image with zeros merged_image = np.zeros((merged_height, merged_width, 3), dtype=np.uint8) print(merged_image.shape) # Merge the warped images by overlaying them on the merged image for img in warped_images: mask = np.all(img == 0, axis=-1) y_offset, x_offset = max(0, -min_y), max(0, -min_x) merged_image_slice = merged_image[y_offset:y_offset + img.shape[0], x_offset:x_offset + img.shape[1]] merged_image_slice[~mask] = img[~mask] print(merged_image.shape) return merged_image"