image warping using OpenCV displaying white screen

Question

I'm trying to write a python script which will accept an image from the user and accept 6 points which are obtained by the user clicking on the image which gets the coordinates of the clicks. The first 4 coordinates are used to warp the image to make those points the corners. However all im getting is a white screen as an output.

transform.py

# import the necessary packages https://www.pyimagesearchcv2.waitKey(0).com/2014/08/25/4-point-opencv-getperspective-transform-example/
import numpy as np
import cv2

def order_points(pts):
    # initialzie a list of coordinates that will be ordered
    # such that the first entry in the list is the top-left,
    # the second entry is the top-right, the third is the
    # bottom-right, and the fourth is the bottom-left
    rect = np.zeros((4, 2), dtype = "float32")

    # the top-left point will have the smallest sum, whereas
    # the bottom-right point will have the largest sum
    s = pts.sum(axis = 1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]

    # now, compute the difference between the points, the
    # top-right point will have the smallest difference,r
    # whereas the bottom-left will have the largest difference
    diff = np.diff(pts, axis = 1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]

    # return the ordered coordinates
    return rect

def four_point_transform(image, pts):
    # obtain a consistent order of the points and unpack them
    # individually
    rect = order_points(pts)
    (tl, tr, br, bl) = rect
    for i in rect: print (i)

    # compute the width of the new image, which will be the
    # maximum distance between bottom-right and bottom-left
    # x-coordiates or the top-right and top-left x-coordinates
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    # compute the height of the new image, which will be the
    # maximum distance between the top-right and bottom-right
    # y-coordinates or the top-left and bottom-left y-coordinates
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    # now that we have the dimensions of the new image, construct
    # the set of destination points to obtain a "birds eye view",
    # (i.e. top-down view) of the image, again specifying points
    # in the top-left, top-right, bottom-right, and bottom-left
    # order
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype = "float32")

    # compute the perspective transform matrix and then apply it
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # return the warped image
    return warped

transform_example.py

# import the necessary packages
from transform import four_point_transform
import numpy as np
import argparse
import cv2

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", help = "path to the image file")
args = vars(ap.parse_args())

# load the image
image = cv2.imread(args["image"])

mouse_pts = []

def get_mouse_points(event, x, y, flags, param):
    # Used to mark 4 points on the frame zero of the video that will be warped
    # Used to mark 2 points on the frame zero of the video that are 6 feet away
    global mouseX, mouseY, mouse_pts
    if event == cv2.EVENT_LBUTTONDOWN:
        mouseX, mouseY = x, y
        cv2.circle(image, (x, y), 10, (0, 255, 255), 10)
        if "mouse_pts" not in globals():
            mouse_pts = []
        mouse_pts.append((x, y))
        print("Point detected")
        print(mouse_pts)

cv2.namedWindow("persp")
cv2.setMouseCallback("persp", get_mouse_points)
cv2.imshow("persp", image)

while(True):   
    cv2.waitKey(1)
    if len(mouse_pts) == 7:
        cv2.destroyWindow("persp")
        break

four_pts = np.array(mouse_pts[0:4], dtype="float32")

# apply the four point tranform to obtain a "birds eye view" of
# the image
warped = four_point_transform(image, four_pts)

# show warped images
cv2.imshow("persp", warped)
cv2.waitKey(0)

original image:

the points selected are on the fence on either side of the road. what i want is a kinda birds eye view of the bridge.

output image:

Thanks for the help!

Answer 1

Have a look at my answer on a similar question.

The order_points function was later fixed by Adrian in a separate article.

The working code:

import numpy
import cv2
import numpy as np
from scipy.spatial import distance as dist

def on_click(event, x, y, flags, param):
    global a_, b_, c_, d_, to_set
    if event == cv2.EVENT_LBUTTONDOWN:
        print("click")
        if to_set == 0:
            to_set = 1
            a_ = [x, y]
        elif to_set == 1:
            to_set = 2
            b_ = [x, y]
        elif to_set == 2:
            to_set = 3
            c_ = [x, y]
        elif to_set == 3:
            to_set = 0
            d_ = [x, y]



def order_points(pts):
    # sort the points based on their x-coordinates
    xSorted = pts[np.argsort(pts[:, 0]), :]
    # grab the left-most and right-most points from the sorted
    # x-roodinate points
    leftMost = xSorted[:2, :]
    rightMost = xSorted[2:, :]
    # now, sort the left-most coordinates according to their
    # y-coordinates so we can grab the top-left and bottom-left
    # points, respectively
    leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
    (tl, bl) = leftMost
    # now that we have the top-left coordinate, use it as an
    # anchor to calculate the Euclidean distance between the
    # top-left and right-most points; by the Pythagorean
    # theorem, the point with the largest distance will be
    # our bottom-right point
    D = dist.cdist(tl[np.newaxis], rightMost, "euclidean")[0]
    (br, tr) = rightMost[np.argsort(D)[::-1], :]
    # return the coordinates in top-left, top-right,
    # bottom-right, and bottom-left order
    return np.array([tl, tr, br, bl], dtype="float32")


def four_point_transform(image, pts):
    # obtain a consistent order of the points and unpack them
    # individually
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    # compute the width of the new image, which will be the
    # maximum distance between bottom-right and bottom-left
    # x-coordiates or the top-right and top-left x-coordinates
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    # compute the height of the new image, which will be the
    # maximum distance between the top-right and bottom-right
    # y-coordinates or the top-left and bottom-left y-coordinates
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    # now that we have the dimensions of the new image, construct
    # the set of destination points to obtain a "birds eye view",
    # (i.e. top-down view) of the image, again specifying points
    # in the top-left, top-right, bottom-right, and bottom-left
    # order
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    # compute the perspective transform matrix and then apply it
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # return the warped image
    return warped


# load the image
image = cv2.imread('test2.jpg')

mouse_pts = []

def get_mouse_points(event, x, y, flags, param):
    # Used to mark 4 points on the frame zero of the video that will be warped
    # Used to mark 2 points on the frame zero of the video that are 6 feet away
    global mouseX, mouseY, mouse_pts
    if event == cv2.EVENT_LBUTTONDOWN:
        mouseX, mouseY = x, y
        cv2.circle(image, (x, y), 10, (0, 255, 255), 10)
        if "mouse_pts" not in globals():
            mouse_pts = []
        mouse_pts.append((x, y))
        print("Point detected")
        print(mouse_pts)

cv2.namedWindow("persp")
cv2.setMouseCallback("persp", get_mouse_points)
cv2.imshow("persp", image)

while(True):   
    cv2.waitKey(1)
    if len(mouse_pts) == 7:
        cv2.destroyWindow("persp")
        break

four_pts = np.array(mouse_pts[0:4], dtype="float32")

# apply the four point tranform to obtain a "birds eye view" of
# the image
warped = four_point_transform(image, four_pts)

# show warped images
cv2.imshow("persp", warped)
cv2.waitKey(0)