Harris算法特征点检测和匹配python代码
时间: 2024-01-17 17:03:51 浏览: 45
以下是使用Python实现Harris角点检测和特征匹配的示例代码:
Harris角点检测:
```python
import cv2
import numpy as np
# 读入图片
img = cv2.imread('test.jpg')
# 转换为灰度图
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 计算Harris角点
dst = cv2.cornerHarris(gray, 2, 3, 0.04)
# 归一化处理
dst_norm = np.empty(dst.shape, dtype=np.float32)
cv2.normalize(dst, dst_norm, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX)
# 阈值处理
threshold = 150
corners = np.argwhere(dst_norm > threshold)
for pt in corners:
cv2.circle(img, tuple(pt[::-1]), 3, (0, 255, 0), 2)
# 显示图片
cv2.imshow('Harris corners', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
```
特征匹配:
```python
import cv2
import numpy as np
# 读入图片
img1 = cv2.imread('img1.jpg')
img2 = cv2.imread('img2.jpg')
# 转换为灰度图
gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
gray2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
# 计算特征点和特征描述符
sift = cv2.xfeatures2d.SIFT_create()
kp1, des1 = sift.detectAndCompute(gray1, None)
kp2, des2 = sift.detectAndCompute(gray2, None)
# 匹配特征点
bf = cv2.BFMatcher(cv2.NORM_L2, crossCheck=True)
matches = bf.match(des1, des2)
# 绘制匹配结果
match_img = cv2.drawMatches(img1, kp1, img2, kp2, matches[:50], None, flags=2)
# 显示图片
cv2.imshow('SIFT matches', match_img)
cv2.waitKey(0)
cv2.destroyAllWindows()
```
注意:上述代码仅是示例代码,实际使用中需要根据具体情况进行调整和优化。