CODEWITHSUNDEEP
python-3.xopencvsiftkeypoint
Reward
Reward

Reputation: 97

Python : Feature Matching + Homography to find Multiple Objects

I'm trying to use opencv via python to find multiple objects in a train image and match it with the key points detected from query image.For my case, i'm trying to detect the tennis courts in the image provided below. I I looked at the online tutorials,and only figured that it can only detect 1 object. I thought of inserting a loop in for it to find multiple objects but i failed to do so. Any idea on how to do it ? *I Used SIFT as ORB does not work that well for my case

Here's the code and a sample set of images.

import numpy as np
import cv2
from matplotlib import pyplot as plt

MIN_MATCH_COUNT = 10
img1 = cv2.imread('Image 11.jpg',0)          # queryImage
img2 = cv2.imread('Image 5.jpg',0) # trainImage

# Initiate SIFT detector
sift = cv2.xfeatures2d.SIFT_create()

# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1,None)
kp2, des2 = sift.detectAndCompute(img2,None)
FLANN_INDEX_KDTREE = 1
index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)
search_params = dict(checks = 50)
flann = cv2.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1,des2,k=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)>MIN_MATCH_COUNT:
    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,5.0)
    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)
else:
    print( "Not enough matches are found - {}/{}".format(len(good), MIN_MATCH_COUNT) )
    matchesMask = None
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()

Train Image

Query Image

Thanks in advance!

Upvotes: 7

Views: 3076

Answers (1)

Francis Cote
Francis Cote

Reputation: 11

If you have the same image multiple times you will have some problems finding the homography. Even with a loop, Your Keypoints descriptions might be mix around the different identical image. You could do a pretreatment and regroup the keypoint to do multiple matching but it might be complex for different image with different size I would suggest using template matching, but the difficulty is the scale and rotation invariance. You could read this article for some help https://www.pyimagesearch.com/2015/01/26/multi-scale-template-matching-using-python-opencv/

Hope it help !

Upvotes: 1

Related Questions