getRotationAngle.py

from __future__ import print_function
import cv2
import math
import numpy as np

PI = math.pi
MAX_FEATURES = 500
GOOD_MATCH_PERCENT = 0.15

def alignImages(im1, im2, windowName):
    # Convert images to grayscale
    im1Gray = cv2.cvtColor(im1, cv2.COLOR_BGR2GRAY)
    im2Gray = cv2.cvtColor(im2, cv2.COLOR_BGR2GRAY)

    # Detect ORB features and compute descriptors.
    orb = cv2.ORB_create(MAX_FEATURES)
    keypoints1, descriptors1 = orb.detectAndCompute(im1Gray, None)
    keypoints2, descriptors2 = orb.detectAndCompute(im2Gray, None)

    # Match features.
    matcher = cv2.DescriptorMatcher_create(cv2.DESCRIPTOR_MATCHER_BRUTEFORCE_HAMMING)
    matches = matcher.match(descriptors1, descriptors2, None)

    # Sort matches by score
    matches.sort(key=lambda x: x.distance, reverse=False)

    # Remove not so good matches
    numGoodMatches = int(len(matches) * GOOD_MATCH_PERCENT)
    matches = matches[:numGoodMatches]

    # Draw top matches
    imMatches = cv2.drawMatches(im1, keypoints1, im2, keypoints2, matches, None)
    cv2.imshow(windowName, imMatches)

    # Extract location of good matches
    points1 = np.zeros((len(matches), 2), dtype=np.float32)
    points2 = np.zeros((len(matches), 2), dtype=np.float32)

    for i, match in enumerate(matches):
        points1[i, :] = keypoints1[match.queryIdx].pt
        points2[i, :] = keypoints2[match.trainIdx].pt

    # Find homography
    h, mask = cv2.findHomography(points1, points2, cv2.RANSAC)

    # Use homography
    height, width, channels = im2.shape
    im1Reg = cv2.warpPerspective(im1, h, (width, height))

    return im1Reg, h

def drawInclination(theta):
    canvasWidth = 200
    canvas = np.zeros((canvasWidth, canvasWidth, 3), np.uint8)

    theta = theta * PI / 180;

    cv2.line(canvas, (0, canvasWidth//2), (canvasWidth, canvasWidth//2), (255, 255, 255));
    cv2.line(canvas,
        (canvasWidth//2, canvasWidth//2),
        (canvasWidth//2 + int(canvasWidth*math.cos(theta)), canvasWidth//2 + int(canvasWidth*math.sin(theta))),
        (0, 255, 0), 2);

    cv2.imshow('Inclunacion', canvas);

if __name__ == '__main__':
    # Read reference image
    refFilename = "spaceinvader.jpg"
    imReference = cv2.imread(refFilename, cv2.IMREAD_COLOR)

    cap = cv2.VideoCapture(0)
    while(True):
        try:
            ret, frame = cap.read()
            im = cv2.flip(frame, 1)

            # Registered image will be resotred in imReg.
            # The estimated homography will be stored in H.
            imReg, H = alignImages(im, imReference, "Matches")
            cv2.imshow('Aligned image', imReg)

            a = H[0, 0]
            b = H[0, 1]
            theta = math.atan2(b, a) * (180 / PI)

            drawInclination(theta)

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

    cap.release()
    cv2.destroyAllWindows()

Hello,
How can i check is the homography is good or not by interpreting the matrix homograph ?