python - OpenCV 特征匹配图像中的多个相似对象

Question

我目前有一个项目，我需要在其中使用 OpenCV 和 Python 找到照片中列出的带圆圈的 X。我尝试过使用模板匹配和特征匹配，但是我只能得到我从照片中裁剪出来的一个 X 用作查询图像。查询照片与其他 X 不完全相同，但非常相似，所以我很困惑为什么特征匹配无法检测到其他照片。这段代码是从另一个教程中提取的，但我似乎无法完成这项工作。请帮忙!

当前代码:

    import cv2
from matplotlib import pyplot as plt

MIN_MATCH_COUNT = 3

img1 = cv2.imread('template.jpg', 0)  # queryImage
img2 = cv2.imread('originalPic.jpg', 0) # trainImage

orb = cv2.ORB_create(10000, 1.2, nlevels=8, edgeThreshold = 5)

# find the keypoints and descriptors with ORB
kp1, des1 = orb.detectAndCompute(img1, None)
kp2, des2 = orb.detectAndCompute(img2, None)

import numpy as np
from sklearn.cluster import MeanShift, estimate_bandwidth

x = np.array([kp2[0].pt])

for i in range(len(kp2)):
    x = np.append(x, [kp2[i].pt], axis=0)

x = x[1:len(x)]

bandwidth = estimate_bandwidth(x, quantile=0.1, n_samples=500)

ms = MeanShift(bandwidth=bandwidth, bin_seeding=True, cluster_all=True)
ms.fit(x)
labels = ms.labels_
cluster_centers = ms.cluster_centers_

labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
print("number of estimated clusters : %d" % n_clusters_)

s = [None] * n_clusters_
for i in range(n_clusters_):
    l = ms.labels_
    d, = np.where(l == i)
    print(d.__len__())
    s[i] = list(kp2[xx] for xx in d)

des2_ = des2

for i in range(n_clusters_):

    kp2 = s[i]
    l = ms.labels_
    d, = np.where(l == i)
    des2 = des2_[d, ]

    FLANN_INDEX_KDTREE = 0
    index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)
    search_params = dict(checks = 50)

    flann = cv2.FlannBasedMatcher(index_params, search_params)

    des1 = np.float32(des1)
    des2 = np.float32(des2)

    matches = flann.knnMatch(des1, des2, 2)

    # store all the good matches as per Lowe's ratio test.
    good = []
    for m,n in matches:
        if m.distance < 0.7*n.distance:
            good.append(m)

    if len(good)>3:
        src_pts = np.float32([ kp1[m.queryIdx].pt for m in good ]).reshape(-1,1,2)
        dst_pts = np.float32([ kp2[m.trainIdx].pt for m in good ]).reshape(-1,1,2)

        M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 2)

        if M is None:
            print ("No Homography")
        else:
            matchesMask = mask.ravel().tolist()

            h,w = img1.shape
            pts = np.float32([ [0,0],[0,h-1],[w-1,h-1],[w-1,0] ]).reshape(-1,1,2)
            dst = cv2.perspectiveTransform(pts,M)

            img2 = cv2.polylines(img2,[np.int32(dst)],True,255,3, cv2.LINE_AA)

            draw_params = dict(matchColor=(0, 255, 0),  # draw matches in green color
                               singlePointColor=None,
                               matchesMask=matchesMask,  # draw only inliers
                               flags=2)

            img3 = cv2.drawMatches(img1, kp1, img2, kp2, good, None, **draw_params)

            plt.imshow(img3, 'gray'), plt.show()

    else:
        print ("Not enough matches are found - %d/%d" % (len(good),MIN_MATCH_COUNT))
        matchesMask = None

Query Object | Image To Search Through

Answer 1

这是一种更简单的方法，只使用 openCV 和 numpy。由于查询图像的大小远小于训练图像的大小，我首先将训练图像缩小了 0.33 倍以适合我的屏幕，然后创建了一个函数来遍历各种大小的查询图像，因为为此方法你也必须匹配尺寸。

当然，您可以调整变量 fx 和 fy、mult 和阈值以查看您可以获得多少 X。我的最高数字是 3，来自粗略的迭代，但下面的这个设置达到了 2:

import cv2
import numpy as np

originalPicRead = cv2.imread('originalPic.jpg')
img_bgr = cv2.resize(originalPicRead, (0,0), fx=0.33, fy=0.33)
img_gray = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY)

templateR = cv2.imread('template.jpg',0)

w,h = templateR.shape[::-1]

for magn in range(1,11):
    mult = magn*0.35
    w,h = int(mult*w),int(mult*h)
    template = cv2.resize(templateR, (0,0), fx=mult, fy = mult)

    res = cv2.matchTemplate(img_gray, template, cv2.TM_CCOEFF_NORMED)
    threshold = 0.35
    loc = np.where(res >= threshold)

    for pt in zip(*loc[::-1]):
        cv2.rectangle(img_bgr, pt, (pt[0]+w, pt[1]+h), (0,255,255), 2)

cv2.imshow('Detected', img_bgr)
cv2.waitKey(0)
cv2.destroyAllWindows()