How can I avoid parts of images from getting cut, when performing perspective warping?

user_14183292 0
Viewed 1493

I am trying to turn the perspective of an image so that I get a result that gives the front view perspective. I am using cv2.WarpPerspective function. However, on performing warp, some parts of the image are getting cut off. How can I avoid this? An option I thought is to find the transformation matrix for a specific part of the image and then apply that matrix to the whole image. However, that method is not yielding desirable results.

The code I am using is :

    import numpy as np
    import cv2
    from google.colab.patches import cv2_imshow
    img = cv2.imread("drive/My Drive/Images_for_Adarsh/DSC_0690.JPG")

    height,width = 1000,1500
    img = cv2.resize(img,(width,height))

    pts1 = np.float32([[ 250, 0],[1220, 300],[1300, 770],[ 250, 860]])
    pts2 = np.float32([[0,0],[width,0],[width,height],[0,height]])
    matrix = cv2.getPerspectiveTransform(pts1,pts2)


    print(matrix.shape)
    print(matrix)
    imgOutput = cv2.warpPerspective(img,matrix,(width,height))
    cv2_imshow(imgOutput)
    cv2.imwrite("drive/My Drive/PerspectiveWarp-Results1/0690_coarse/0690([[ 250, 0],[1220, 300],[1300, 770],[ 250, 860]]).JPG",imgOutput)

The input image: The input image:

The warped image: The warped image:

perspectivecamera opencv image-processing python
1 Answers

Here is one simple way to warp the image in Python/OpenCV and add extra space that will contain more of the input, but have areas outside the input as transparent.

Input:

enter image description here

import numpy as np
import cv2

# read input
img = cv2.imread("building.jpg")

# resize
height,width = 1000,1500
img = cv2.resize(img, (width,height))

# specify conjugate coordinates and shift output on left and top by 500
pts1 = np.float32([[ 250, 0],[1220, 300],[1300, 770],[ 250, 860]])
pts2 = np.float32([[+500,+500],[width+500,+500],[width+500,height+500],[+500,height+500]])

# compute perspective matrix
matrix = cv2.getPerspectiveTransform(pts1,pts2)

print(matrix.shape)
print(matrix)

# convert image to BGRA with opaque alpha
img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)

# do perspective transformation setting area outside input to transparent
# extend output size so extended by 500 all around
imgOutput = cv2.warpPerspective(img, matrix, (width+1000,height+1000), cv2.INTER_LINEAR, borderMode=cv2.BORDER_CONSTANT, borderValue=(0,0,0,0))

# resize output, since it is too large to post
imgOutput = cv2.resize(imgOutput, (width,height))
    
# save the warped output
cv2.imwrite("building_warped.png", imgOutput)

# show the result
cv2.imshow("result", imgOutput)
cv2.waitKey(0)
cv2.destroyAllWindows()

enter image description here

Note: it should be possible to use the matrix to project the input corners to the output domain and compute the required output size to hold all of the warped input.

user_73557410
Related