图像转换的单应性不起作用
Homography for image tranformation doesn't work right
我正在尝试进行多尺度模板匹配来检测模板，然后使用 alpha 混合将 png 粘贴到检测到的区域] 和 使用单应性变换图像 。我在实时网络摄像头捕获中执行此操作，但在使用单应性后我没有得到预期的结果。我将按照我的描述逐部分提及我的代码。
1) 多尺度模板匹配
import cv2 as cv2
import numpy as np
import imutils
def main():
template1 = cv2.imread("C:\Users\Manthika\Desktop\opencvtest\templates\template1.jpg")
template2 = cv2.imread("C:\Users\Manthika\Desktop\opencvtest\templates\temp.jpg")
templates = [template1, template2]
for i in range(len(templates)):
templates[i] = cv2.cvtColor(templates[i], cv2.COLOR_BGR2GRAY)
templates[i] = cv2.Canny(templates[i], 50, 140)
templates[i] = cv2.GaussianBlur(templates[i],(5,5),0)
templates[i] = imutils.resize(templates[i], width=50)
(tH, tW) = templates[0].shape[:2]
# print(tH)
# print(tW)
# cv2.imshow("Template", template)
cap = cv2.VideoCapture(0)
if cap.isOpened():
ret, frame = cap.read()
else:
ret = False
# loop over the frames to find the template
while ret:
# load the image, convert it to grayscale, and initialize the
# bookkeeping variable to keep track of the matched region
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
found = None
# loop over the scales of the image
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
# resize the image according to the scale, and keep track
# of the ratio of the resizing
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
# if the resized image is smaller than the template, then break
# from the loop
if resized.shape[0] < tH or resized.shape[1] < tW:
print("frame is smaller than the template")
break
# detect edges in the resized, grayscale image and apply template
# matching to find the template in the image
edged = cv2.Canny(resized, 50, 160)
blurred = cv2.GaussianBlur(edged,(5,5),0)
curr_max = 0
index = 0
result = None
# find the best match
for i in range(len(templates)):
# perform matchtemplate
res = cv2.matchTemplate(blurred, templates[i], cv2.TM_CCOEFF)
# get the highest correlation value of the result
maxVal = res.max()
# if the correlation is highest thus far, store the value and index of template
if maxVal > curr_max:
curr_max = maxVal
index = i
result = res
print(index)
# result = cv2.matchTemplate(edged, templates[index], cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
# if we have found a new maximum correlation value, then update
# the bookkeeping variable
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
# unpack the bookkeeping variable and compute the (x, y) coordinates
# of the bounding box based on the resized ratio
# print(found)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
这工作正常，正如我所料，而且没有错误。我可以获得 (startX, startY) 和 (endX, endY) 值以在检测到的区域周围绘制边界框。
2) 使用 alpha 混合将 png 粘贴到检测到的区域
cropped = frame[startY:endY, startX:endX]
cv2.imshow("cropped", cropped)
# Read the foreground image with alpha channel
foreGroundImage = cv2.imread("C:\Users\Manthika\Desktop\opencvtest\tattoo2.png", -1)
# Read background image
background = cropped
dim = (background.shape[1], background.shape[0])
foreGroundImage = cv2.resize(foreGroundImage, dim)
# Split png foreground image
b, g, r, a = cv2.split(foreGroundImage)
# Save the foregroung RGB content into a single object
foreground = cv2.merge((b, g, r))
# Save the alpha information into a single Mat
alpha = cv2.merge((a, a, a))
# background = cv2.resize(background, dim, interpolation = cv2.INTER_AREA)
# Convert uint8 to float
foreground = foreground.astype(float)
background = background.astype(float)
alpha = alpha.astype(float) / 255
# Perform alpha blending
foreground = cv2.multiply(alpha, foreground)
beta = 1.0 - alpha
background = cv2.multiply(beta, background)
outImage = cv2.add(foreground, background)
outImage = outImage/255
cv2.imshow("outImage", outImage)
print(outImage.shape)
在这里，我裁剪了检测到的框架部分并在其上粘贴了 png。 outImage 是该过程的输出。我也如我所料得到它。
3) 使用单应性变换图像
# Read source image.
im_src = outImage.copy()
size = im_src.shape
# Create a vector of source points.
pts_src = np.array(
[
[0, 0],
[size[1] - 1, 0],
[size[1] - 1, size[0] - 1],
[0, size[0] - 1]
], dtype=float
)
# Read destination image
im_dst = frame.copy()
cv2.imshow("im_dst", im_dst)
# Create a vector of destination points.
pts_dst = np.array(
[
[startX, startY],
[endX, startY],
[endX, endY],
[startX, endY]
]
)
# Calculate Homography between source and destination points
h, status = cv2.findHomography(pts_src, pts_dst)
# Warp source image
im_temp = cv2.warpPerspective(im_src, h, (im_dst.shape[1], im_dst.shape[0]))
# Black out polygonal area in destination image.
cv2.fillConvexPoly(im_dst, pts_dst.astype(int), 0, 16)
# Add warped source image to destination image.
im_dst = im_dst + im_temp
cv2.imshow("Final", im_dst)
cv2.imshow("frame2222", frame)
if cv2.waitKey(1) == 27:
break
cv2.destroyAllWindows()
cap.release()
if __name__ == "__main__":
main()
在这里我想要将 alpha 混合 outImage 粘贴到框架的给定点上。当我从 im_src = cv2.imread("someimage.png") 和 运行 替换 im_src = outImage.copy() 时它工作正常。 我可以读取图像并将其粘贴到相框上，但我无法使用 outImage 并执行相同的操作。如果您能帮我解决这个问题，那就太好了。如果您需要我使用的图像或输出，请告诉我。
编辑：
输出 im_src = cv2.imread("someimage.png")
someimage.png 显示在模板上
输出 im_src = outImage.copy()
框架的其他部分是白色
问题
在糟糕的情况下，即 im_src = outImage.copy() 你有 dtype= float64 如果你看一下这一行：
outImage = outImage/255
然后您会注意到您的值从 0 到 1。那么你有：
im_dst = frame.copy()
和
im_temp = cv2.warpPerspective(im_src, h, (im_dst.shape[1], im_dst.shape[0]))
...
im_dst = im_dst + im_temp
这意味着 im_dst 的类型为 CV_8UC3（或在 numpy 中为 numpy.uint8），因为它是从相机帧复制的。此值介于 0-255 之间。然后你添加两个具有不同类型和不同值范围的图像，最后给出一个 float 类型的图像，但是背景的值是从 0-255，在 imshow 中显示为白色，如果是 value > = 1 用于浮动类型图像。
好的情况下，类型相同，就不会出现这个问题
解决方案：
一是做：
im_src = np.uint8(outImage.copy() * 255)
但如果您不需要将 outImage 用作其他内容的浮动，只需替换：
outImage = cv2.add(foreground, background)
outImage = outImage/255
用于：
outImage = cv2.add(foreground, background, dtype=np.uint8)
建议：
我发现有几件事可以更快地完成（更少的操作），这只是我建议您做的一些更改：
1) 这个：
# Split png foreground image
b, g, r, a = cv2.split(foreGroundImage)
# Save the foregroung RGB content into a single object
foreground = cv2.merge((b, g, r))
等同于：
# Split png foreground image
a = foreGroundImage[:,:,3]
# Save the foregroung RGB content into a single object
foreground = foreGroundImage[:,:,0:3]
2) 最后一部分完全可以通过调整大小和复制来完成。除非您打算对图像进行旋转或其他操作，否则单应性就太过分了。
类似于：
im_dst[startY:endY, startX,endX] = cv2.resize(im_src, (endX-startX, endY-startY))
我正在尝试进行多尺度模板匹配来检测模板，然后使用 alpha 混合将 png 粘贴到检测到的区域] 和 使用单应性变换图像 。我在实时网络摄像头捕获中执行此操作，但在使用单应性后我没有得到预期的结果。我将按照我的描述逐部分提及我的代码。
1) 多尺度模板匹配
import cv2 as cv2
import numpy as np
import imutils
def main():
template1 = cv2.imread("C:\Users\Manthika\Desktop\opencvtest\templates\template1.jpg")
template2 = cv2.imread("C:\Users\Manthika\Desktop\opencvtest\templates\temp.jpg")
templates = [template1, template2]
for i in range(len(templates)):
templates[i] = cv2.cvtColor(templates[i], cv2.COLOR_BGR2GRAY)
templates[i] = cv2.Canny(templates[i], 50, 140)
templates[i] = cv2.GaussianBlur(templates[i],(5,5),0)
templates[i] = imutils.resize(templates[i], width=50)
(tH, tW) = templates[0].shape[:2]
# print(tH)
# print(tW)
# cv2.imshow("Template", template)
cap = cv2.VideoCapture(0)
if cap.isOpened():
ret, frame = cap.read()
else:
ret = False
# loop over the frames to find the template
while ret:
# load the image, convert it to grayscale, and initialize the
# bookkeeping variable to keep track of the matched region
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
found = None
# loop over the scales of the image
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
# resize the image according to the scale, and keep track
# of the ratio of the resizing
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
# if the resized image is smaller than the template, then break
# from the loop
if resized.shape[0] < tH or resized.shape[1] < tW:
print("frame is smaller than the template")
break
# detect edges in the resized, grayscale image and apply template
# matching to find the template in the image
edged = cv2.Canny(resized, 50, 160)
blurred = cv2.GaussianBlur(edged,(5,5),0)
curr_max = 0
index = 0
result = None
# find the best match
for i in range(len(templates)):
# perform matchtemplate
res = cv2.matchTemplate(blurred, templates[i], cv2.TM_CCOEFF)
# get the highest correlation value of the result
maxVal = res.max()
# if the correlation is highest thus far, store the value and index of template
if maxVal > curr_max:
curr_max = maxVal
index = i
result = res
print(index)
# result = cv2.matchTemplate(edged, templates[index], cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
# if we have found a new maximum correlation value, then update
# the bookkeeping variable
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
# unpack the bookkeeping variable and compute the (x, y) coordinates
# of the bounding box based on the resized ratio
# print(found)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
这工作正常，正如我所料，而且没有错误。我可以获得 (startX, startY) 和 (endX, endY) 值以在检测到的区域周围绘制边界框。
2) 使用 alpha 混合将 png 粘贴到检测到的区域
cropped = frame[startY:endY, startX:endX]
cv2.imshow("cropped", cropped)
# Read the foreground image with alpha channel
foreGroundImage = cv2.imread("C:\Users\Manthika\Desktop\opencvtest\tattoo2.png", -1)
# Read background image
background = cropped
dim = (background.shape[1], background.shape[0])
foreGroundImage = cv2.resize(foreGroundImage, dim)
# Split png foreground image
b, g, r, a = cv2.split(foreGroundImage)
# Save the foregroung RGB content into a single object
foreground = cv2.merge((b, g, r))
# Save the alpha information into a single Mat
alpha = cv2.merge((a, a, a))
# background = cv2.resize(background, dim, interpolation = cv2.INTER_AREA)
# Convert uint8 to float
foreground = foreground.astype(float)
background = background.astype(float)
alpha = alpha.astype(float) / 255
# Perform alpha blending
foreground = cv2.multiply(alpha, foreground)
beta = 1.0 - alpha
background = cv2.multiply(beta, background)
outImage = cv2.add(foreground, background)
outImage = outImage/255
cv2.imshow("outImage", outImage)
print(outImage.shape)
在这里，我裁剪了检测到的框架部分并在其上粘贴了 png。 outImage 是该过程的输出。我也如我所料得到它。
3) 使用单应性变换图像
# Read source image.
im_src = outImage.copy()
size = im_src.shape
# Create a vector of source points.
pts_src = np.array(
[
[0, 0],
[size[1] - 1, 0],
[size[1] - 1, size[0] - 1],
[0, size[0] - 1]
], dtype=float
)
# Read destination image
im_dst = frame.copy()
cv2.imshow("im_dst", im_dst)
# Create a vector of destination points.
pts_dst = np.array(
[
[startX, startY],
[endX, startY],
[endX, endY],
[startX, endY]
]
)
# Calculate Homography between source and destination points
h, status = cv2.findHomography(pts_src, pts_dst)
# Warp source image
im_temp = cv2.warpPerspective(im_src, h, (im_dst.shape[1], im_dst.shape[0]))
# Black out polygonal area in destination image.
cv2.fillConvexPoly(im_dst, pts_dst.astype(int), 0, 16)
# Add warped source image to destination image.
im_dst = im_dst + im_temp
cv2.imshow("Final", im_dst)
cv2.imshow("frame2222", frame)
if cv2.waitKey(1) == 27:
break
cv2.destroyAllWindows()
cap.release()
if __name__ == "__main__":
main()
在这里我想要将 alpha 混合 outImage 粘贴到框架的给定点上。当我从 im_src = cv2.imread("someimage.png") 和 运行 替换 im_src = outImage.copy() 时它工作正常。 我可以读取图像并将其粘贴到相框上，但我无法使用 outImage 并执行相同的操作。如果您能帮我解决这个问题，那就太好了。如果您需要我使用的图像或输出，请告诉我。
编辑：
输出 im_src = cv2.imread("someimage.png")
someimage.png 显示在模板上
输出 im_src = outImage.copy()
框架的其他部分是白色
问题
在糟糕的情况下，即 im_src = outImage.copy() 你有 dtype= float64 如果你看一下这一行：
outImage = outImage/255
然后您会注意到您的值从 0 到 1。那么你有：
im_dst = frame.copy()
和
im_temp = cv2.warpPerspective(im_src, h, (im_dst.shape[1], im_dst.shape[0]))
...
im_dst = im_dst + im_temp
这意味着 im_dst 的类型为 CV_8UC3（或在 numpy 中为 numpy.uint8），因为它是从相机帧复制的。此值介于 0-255 之间。然后你添加两个具有不同类型和不同值范围的图像，最后给出一个 float 类型的图像，但是背景的值是从 0-255，在 imshow 中显示为白色，如果是 value > = 1 用于浮动类型图像。
好的情况下，类型相同，就不会出现这个问题
解决方案：
一是做：
im_src = np.uint8(outImage.copy() * 255)
但如果您不需要将 outImage 用作其他内容的浮动，只需替换：
outImage = cv2.add(foreground, background)
outImage = outImage/255
用于：
outImage = cv2.add(foreground, background, dtype=np.uint8)
建议：
我发现有几件事可以更快地完成（更少的操作），这只是我建议您做的一些更改：
1) 这个：
# Split png foreground image
b, g, r, a = cv2.split(foreGroundImage)
# Save the foregroung RGB content into a single object
foreground = cv2.merge((b, g, r))
等同于：
# Split png foreground image
a = foreGroundImage[:,:,3]
# Save the foregroung RGB content into a single object
foreground = foreGroundImage[:,:,0:3]
2) 最后一部分完全可以通过调整大小和复制来完成。除非您打算对图像进行旋转或其他操作，否则单应性就太过分了。
类似于：
im_dst[startY:endY, startX,endX] = cv2.resize(im_src, (endX-startX, endY-startY))