File size: 5,718 Bytes
928c066 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 |
import argparse
import numpy as np
import cv2
import axengine as axe
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser()
parser.add_argument("--model", type=str, required=True, help="Path to the axmodel")
parser.add_argument("--img1", type=str, required=True, help="Path to the first image")
parser.add_argument("--img2", type=str, required=True, help="Path to the second image")
parser.add_argument("--output", type=str, default="matches.jpg", help="The output image directory")
parser.add_argument("--threshold", type=float, default=0.005, help="The keypoint threshold")
parser.add_argument("--max_points", type=int, default=100, help="The max num for keypoints")
return parser.parse_args()
def preprocess_image(path: str, h: int, w: int):
img = cv2.imread(path)
raw_h, raw_w = img.shape[:2]
if (raw_h, raw_w) != (h, w):
img = cv2.resize(img, (w, h))
scale_h = raw_h / h
scale_w = raw_w / w
else:
scale_h = 1.0
scale_w = 1.0
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_tensor = img_gray.astype(np.float32) / 255.0
img_tensor = img_tensor[None, None, :, :] # -> (1, 1, H, W)
return img_tensor, img, (scale_h, scale_w)
def get_keypoints(score_map, threshold):
row, col = np.where(score_map > threshold) # y, x
if len(row) == 0:
return np.zeros((0, 2), dtype=np.float32), np.zeros((0,), dtype=np.float32)
scores = score_map[row, col]
keypoints = np.stack([col, row], axis=1).astype(np.float32)
return keypoints, scores
def get_descriptors(kp, desc_map):
if len(kp) == 0:
return np.zeros((0, 256), dtype=np.float32)
c, h, w = desc_map.shape
x = kp[:, 0] / 8.0
y = kp[:, 1] / 8.0
x0 = np.floor(x).astype(np.int32)
x1 = x0 + 1
y0 = np.floor(y).astype(np.int32)
y1 = y0 + 1
x0 = np.clip(x0, 0, w - 1)
x1 = np.clip(x1, 0, w - 1)
y0 = np.clip(y0, 0, h - 1)
y1 = np.clip(y1, 0, h - 1)
wa = (x1 - x) * (y1 - y)
wb = (x1 - x) * (y - y0)
wc = (x - x0) * (y1 - y)
wd = (x - x0) * (y - y0)
wa = wa[None, :]
wb = wb[None, :]
wc = wc[None, :]
wd = wd[None, :]
Q_tl = desc_map[:, y0, x0]
Q_bl = desc_map[:, y1, x0]
Q_tr = desc_map[:, y0, x1]
Q_br = desc_map[:, y1, x1]
sampled = (Q_tl * wa + Q_bl * wb + Q_tr * wc + Q_br * wd)
descriptors = sampled.T
norm = np.linalg.norm(descriptors, axis=1, keepdims=True)
descriptors = descriptors / (norm + 1e-6)
return descriptors.astype(np.float32)
def infer(model: str, img1_path: str, img2_path: str, output: str, threshold: float, max_points: int):
session = axe.InferenceSession(model)
# superpoint only have one input
input_name = session.get_inputs()[0].name # get model input node name
input_shape = session.get_inputs()[0].shape # get model input shape (1, 1, H, W)
target_h, target_w = input_shape[2], input_shape[3]
print(f"Inference resolution: {target_w}x{target_h}")
# preprocess images
input_tensor1, img1, scale1 = preprocess_image(img1_path, target_h, target_w)
input_tensor2, img2, scale2 = preprocess_image(img2_path, target_h, target_w)
res1 = session.run(None, {input_name: input_tensor1})
res2 = session.run(None, {input_name: input_tensor2})
# [1,480,640], [1,256,60,80]
score_map1, desc1_map = res1[0], res1[1]
score_map2, desc2_map = res2[0], res2[1]
keypoints1, scores1 = get_keypoints(score_map1[0], threshold)
keypoints2, scores2 = get_keypoints(score_map2[0], threshold)
print(f"Found {len(keypoints1)} keypoints in image 1")
print(f"Found {len(keypoints2)} keypoints in image 2")
if len(keypoints1) > max_points:
idx = np.argsort(scores1)[::-1][:max_points]
keypoints1 = keypoints1[idx]
scores1 = scores1[idx]
if len(keypoints2) > max_points:
idx = np.argsort(scores2)[::-1][:max_points]
keypoints2 = keypoints2[idx]
scores2 = scores2[idx]
desc1 = get_descriptors(keypoints1, desc1_map[0])
desc2 = get_descriptors(keypoints2, desc2_map[0])
bf = cv2.BFMatcher(cv2.NORM_L2, crossCheck=True)
matches = bf.match(desc1, desc2)
matches = sorted(matches, key=lambda x: x.distance)
points1 = [cv2.KeyPoint(x, y, 1) for x, y in keypoints1]
points2 = [cv2.KeyPoint(x, y, 1) for x, y in keypoints2]
match_img = cv2.drawMatches(
img1, points1,
img2, points2,
matches, None,
flags=cv2.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS,
matchColor=(0, 255, 0)
)
# if len(matches) > 4:
# pts1 = np.float32([keypoints1[m.queryIdx] for m in matches]).reshape(-1, 1, 2)
# pts2 = np.float32([keypoints2[m.trainIdx] for m in matches]).reshape(-1, 1, 2)
# H, mask = cv2.findHomography(pts1, pts2, cv2.RANSAC, 3.0)
# if mask is not None:
# matches_mask = mask.ravel().tolist()
# inlier_matches = [m for i, m in enumerate(matches) if matches_mask[i]]
# print(f"Inliers: {len(inlier_matches)} / {len(matches)}")
# inlier_img = cv2.drawMatches(
# img1, points1,
# img2, points2,
# inlier_matches, None,
# flags=cv2.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS,
# matchColor=(0, 255, 0)
# )
# cv2.imwrite("inliers_" + output, inlier_img)
cv2.imwrite(output, match_img)
print(f"Result saved to {output}")
def main():
args = parse_args()
infer(args.model, args.img1, args.img2, args.output, args.threshold, args.max_points)
if __name__ == '__main__':
main() |