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


MIN_MATCH_COUNT = 10

img1 = cv2.imread('testb.jpg',0)          # queryImage
 # trainImage
url='http://100.79.196.20:8080/shot.jpg'

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

# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1,None)
while(True):
	 # Use urllib to get the image from the IP camera
        imgResp = urllib.urlopen(url)
    
    # Numpy to convert into a array
        imgNp = np.array(bytearray(imgResp.read()),dtype=np.uint8)
    
    # Finally decode the array to OpenCV usable format ;) 
        frame = cv2.imdecode(imgNp,-1) 
	gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
	kp2, des2 = sift.detectAndCompute(gray,None)
	#plt.imshow(des1, 'gray'),plt.show()

	#print des1.shape
	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)

	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)
	    check = np.array(cv2.perspectiveTransform(pts,M))
	    #print check
	    x = .25*(check.item((0,0,0))+check.item((1,0,0))+check.item((2,0,0))+check.item((3,0,0)))
	    y =.25*(check.item((0,0,1))+check.item((1,0,1))+check.item((2,0,1))+check.item((3,0,1)))
	    center = np.array([x,y])
	    print  center

   
	    frame = cv2.polylines(frame,[np.int32(dst)],True,255,3, cv2.LINE_AA)
	
	else:
	    print "Not enough matches are found - %d/%d" % (len(good),MIN_MATCH_COUNT)
	    matchesMask = None
	draw_params = dict(matchColor = (0,255,0), # draw matches in green co     singlePointColor = None,
                   	matchesMask = matchesMask, # draw only inliers
                   	flags = 2)

	img3 = cv2.drawMatches(img1,kp1,frame,kp2,good,None,**draw_params)
	cv2.imshow('frame',img3)

        if cv2.waitKey(1) & 0xFF == ord('q'):
        	break

# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()