SIFT 匹配计算机视觉

Question

我需要确定超市中酸奶的位置。源照片看起来像

带模板：

我使用SIFT提取模板的关键点：

img1 = cv.imread('train.jpg')
sift = cv.SIFT_create()# queryImage
kp1, des1 = sift.detectAndCompute(img1, None)
path = glob.glob("template.jpg")
cv_img = []
l=0

for img in path:
    img2 = cv.imread(img) # trainImage
    # Initiate SIFT detector

    # find the keypoints and descriptors with SIFT

    kp2, des2 = sift.detectAndCompute(img2,None)
    # FLANN parameters
    FLANN_INDEX_KDTREE = 1
    index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)
    search_params = dict(checks=50)   # or pass empty dictionary
    flann = cv.FlannBasedMatcher(index_params,search_params)
    matches = flann.knnMatch(des1,des2,k=2)
    # Need to draw only good matches, so create a mask

    # ratio test as per Lowe's paper

    if (l < len(matches)):
        l = len(matches)
        image = img2
        match = matches

        
        
    h_query, w_query, _= img2.shape

    matchesMask = [[0,0] for i in range(len(match))]
    good_matches = []
    good_matches_indices = {}
    for i,(m,n) in enumerate(match):
        if m.distance < 0.7*n.distance:
            matchesMask[i]=[1,0]
            good_matches.append(m)
            good_matches_indices[len(good_matches) - 1] = i

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

    model, inliers = initialize_ransac(src_pts, dst_pts)
    
    n_inliers = np.sum(inliers)
    matched_indices = [good_matches_indices[idx] for idx in inliers.nonzero()[0]]
    
    print(len(matched_indices))
    model, inliers = ransac(
        (src_pts, dst_pts),
        AffineTransform, min_samples=4,
        residual_threshold=4, max_trials=20000
    )

    n_inliers = np.sum(inliers)
    print(n_inliers)
    matched_indices = [good_matches_indices[idx] for idx in inliers.nonzero()[0]]
    print(matched_indices)
    

    q_coordinates = np.array([(0, 0), (h_query, w_query)])
    coords = model.inverse(q_coordinates)
    print(coords)
    
    h_query, w_query,_ = img2.shape
    q_coordinates = np.array([(0, 0), (h_query, w_query)])
    coords = model.inverse(q_coordinates)
    print(coords)
#     bboxes_list.append((i, coords))
                

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

    draw_params = dict(matchColor = (0,255,0),
                        singlePointColor = (255,0,0),
                        matchesMask = matchesMask,
                        flags = cv.DrawMatchesFlags_DEFAULT)

    img3 = cv.drawMatchesKnn(img1,kp1,image,kp2,match,None,**draw_params)

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

SIFT 的结果是这样的

问题是对点进行分类以获得代表每种酸奶的矩形的最佳方法是什么？我尝试了RANSAC，但这种方法在这种情况下不起作用。

Answer 1

首先，您可以使用this 之类的网络检测货架上的任何商品，它已在此确切上下文中进行了预训练并且运行良好。您还应该在将图像输入网络之前对其进行校正。您将获得每个产品的边界框（可能是一些误报/误报，但这是另一个问题）。然后，您可以使用 SIFT 将每个框与模板匹配并计算分数（取决于您定义哪个分数有效），但如果您的数据集一致，我建议使用其他方法，例如连体网络。