如何将300度等距柱状全景图像转换为立方体面？
问题描述 投票：0回答：1
我想使用 Python 中的 OpenCV 将 300 度等距柱状全景图像转换为立方体面。我找到了 360 度图像的代码。如何修改它以处理 300 度图像？
import cv2
import numpy as np
def equirectangular_to_cube(img, cube_size):
h, w = img.shape[:2]
#
# Create cube map faces
cube_faces = np.zeros((cube_size, cube_size * 6, 3), dtype=np.uint8)
#
# Calculate the size of each cube face
face_size = cube_size
#
# Define the mapping coordinates for 360 degrees
x = np.linspace(-np.pi, np.pi, num=w, dtype=np.float32)
y = np.linspace(np.pi / 2, -np.pi / 2, num=h, dtype=np.float32)
#
# Create grid of coordinates
xx, yy = np.meshgrid(x, y)
#
# Calculate 3D coordinates
z = np.cos(yy) * np.cos(xx)
x = np.cos(yy) * np.sin(xx)
y = np.sin(yy)
#
# Normalize coordinates
norm = np.sqrt(x**2 + y**2 + z**2)
x /= norm
y /= norm
z /= norm
#
# Map coordinates to cube faces
front_mask = (z >= np.abs(x)) & (z >= np.abs(y))
right_mask = (x >= np.abs(y)) & (x >= np.abs(z))
back_mask = (z <= -np.abs(x)) & (z <= -np.abs(y))
left_mask = (x <= -np.abs(y)) & (x <= -np.abs(z))
top_mask = (y >= np.abs(x)) & (y >= np.abs(z))
bottom_mask = (y <= -np.abs(x)) & (y <= -np.abs(z))
#
# Interpolate and assign pixel values to cube faces
for i in range(cube_size):
for j in range(cube_size):
# Front face
u = (0.5 + 0.5 * x[front_mask] / z[front_mask]) * (w - 1)
v = (0.5 + 0.5 * y[front_mask] / z[front_mask]) * (h - 1)
cube_faces[i, j] = cv2.remap(img, u.reshape(-1, 1).astype(np.float32), v.reshape(-1, 1).astype(np.float32), cv2.INTER_LINEAR)
#
# Right face
u = (0.5 + 0.5 * z[right_mask] / x[right_mask]) * (w - 1)
v = (0.5 + 0.5 * y[right_mask] / x[right_mask]) * (h - 1)
cube_faces[i, j + cube_size] = cv2.remap(img, u.reshape(-1, 1).astype(np.float32), v.reshape(-1, 1).astype(np.float32), cv2.INTER_LINEAR)
#
# Back face
u = (0.5 - 0.5 * x[back_mask] / z[back_mask]) * (w - 1)
v = (0.5 + 0.5 * y[back_mask] / z[back_mask]) * (h - 1)
cube_faces[i, j + cube_size*2] = cv2.remap(img, u.reshape(-1, 1).astype(np.float32), v.reshape(-1, 1).astype(np.float32), cv2.INTER_LINEAR)
#
# Left face
u = (0.5 - 0.5 * z[left_mask] / x[left_mask]) * (w - 1)
v = (0.5 + 0.5 * y[left_mask] / x[left_mask]) * (h - 1)
cube_faces[i, j + cube_size*3] = cv2.remap(img, u.reshape(-1, 1).astype(np.float32), v.reshape(-1, 1).astype(np.float32), cv2.INTER_LINEAR)
#
# Top face
u = (0.5 + 0.5 * x[top_mask] / y[top_mask]) * (w - 1)
v = (0.5 - 0.5 * z[top_mask] / y[top_mask]) * (h - 1)
cube_faces[i, j + cube_size*4] = cv2.remap(img, u.reshape(-1, 1).astype(np.float32), v.reshape(-1, 1).astype(np.float32), cv2.INTER_LINEAR)
#
# Bottom face
u = (0.5 + 0.5 * x[bottom_mask] / y[bottom_mask]) * (w - 1)
v = (0.5 + 0.5 * z[bottom_mask] / y[bottom_mask]) * (h - 1)
cube_faces[i, j + cube_size*5] = cv2.remap(img, u.reshape(-1, 1).astype(np.float32), v.reshape(-1, 1).astype(np.float32), cv2.INTER_LINEAR)
#
return cube_faces
# Usage example
image_path = 'path/to/300_degree_image.jpg'
cube_size = 512
img = cv2.imread(image_path)
cube_faces = equirectangular_to_cube(img, cube_size)
# Save the cube faces as separate images
front = cube_faces[:, :cube_size]
right = cube_faces[:, cube_size:cube_size*2]
back = cube_faces[:, cube_size*2:cube_size*3]
left = cube_faces[:, cube_size*3:cube_size*4]
top = cube_faces[:, cube_size*4:cube_size*5]
bottom = cube_faces[:, cube_size*5:]
cv2.imwrite("front.jpg", front)
cv2.imwrite("right.jpg", right)
cv2.imwrite("back.jpg", back)
cv2.imwrite("left.jpg", left)
cv2.imwrite("top.jpg", top)
cv2.imwrite("bottom.jpg", bottom)
它使用
np.linspace(-np.pi, np.pi, num=w, dtype=np.float32)图片：
我尝试过的：
# convert using an inverse transformation
def convertBack(imgIn,imgOut):
inSize = imgIn.size
outSize = imgOut.size
inPix = imgIn.load()
outPix = imgOut.load()
#
extendedSize = [0,0]
extendedSize[0] = int(360/300 * inSize[0])
extendedSize[1] = inSize[1]
edge = int(extendedSize[0]/4) # theoretical length of each edge
#
for i in range(outSize[0]):
face = int(i/edge) # 0 - back, 1 - left 2 - front, 3 - right
if face==2:
rng = range(0,edge*3)
else:
rng = range(edge,edge*2)
#
for j in rng:
if j<edge:
face2 = 4 # top
elif j>=2*edge:
face2 = 5 # bottom
else:
face2 = face
#
(x,y,z) = outImgToXYZ(i,j,face2,edge)
theta = atan2(y,x) # range -pi to pi
r = hypot(x,y)
phi = atan2(z,r) # range -pi/2 to pi/2
# source img coords
uf = ( 2.0*edge*(theta + pi)/pi )
vf = ( 2.0*edge * (pi/2 - phi)/pi)
if uf < inSize[0]:
# Use bilinear interpolation between the four surrounding pixels
ui = floor(uf) # coord of pixel to bottom left
vi = floor(vf)
u2 = clip(ui+1, 0, inSize[0]-1) # Clip u2 to stay within the valid range
v2 = clip(vi+1, 0, inSize[1]-1) # Clip v2 to stay within the valid range
mu = uf-ui # fraction of way across pixel
nu = vf-vi
# Pixel values of four corners
A = inPix[ui,vi]
B = inPix[u2,vi]
C = inPix[ui,v2]
D = inPix[u2,v2]
# interpolate
(r,g,b) = (
A[0]*(1-mu)*(1-nu) + B[0]*(mu)*(1-nu) + C[0]*(1-mu)*nu+D[0]*mu*nu,
A[1]*(1-mu)*(1-nu) + B[1]*(mu)*(1-nu) + C[1]*(1-mu)*nu+D[1]*mu*nu,
A[2]*(1-mu)*(1-nu) + B[2]*(mu)*(1-nu) + C[2]*(1-mu)*nu+D[2]*mu*nu )
else:
(r,g,b) = (0,0,0)
#
outPix[i,j] = (int(round(r)),int(round(g)),int(round(b)))
这就是变化：
extendedSize = [0,0]
extendedSize[0] = int(360/300 * inSize[0])
extendedSize[1] = inSize[1]
edge = int(extendedSize[0]/4) # theoretical length of each edge
更新：
我已经部分工作了。任何反馈都会非常有帮助。
我在下面添加了更新的代码
# convert using an inverse transformation
def convertBack(imgIn,imgOut):
inSize = imgIn.size
outSize = imgOut.size
inPix = imgIn.load()
outPix = imgOut.load()
extendedSize = imgIn.size
extendedSize = (int(360/300 * inSize[0]), inSize[1])
edge = extendedSize[0]/4 # theoretical length of edge
# edge = inSize[0]/4 # the length of each edge in pixels
for i in range(outSize[0]):
# print(i)
face = int(i/edge) # 0 - back, 1 - left 2 - front, 3 - right
if face==2:
rng = range(0, int(edge*3))
else:
rng = range(int(edge), int(edge*2))
#
for j in rng:
if j<edge:
face2 = 4 # top
elif j>=2*edge:
face2 = 5 # bottom
else:
face2 = face
#
(x,y,z) = outImgToXYZ(i,j,face2,edge)
theta = atan2(y,x) # range -pi to pi
r = hypot(x,y)
phi = atan2(z,r) # range -pi/2 to pi/2
# source img coords
uf = ( 2.0*edge*(theta + pi)/pi )
vf = ( 2.0*edge * (pi/2 - phi)/pi)
#
if uf < inSize[0] :
# Use bilinear interpolation between the four surrounding pixels
ui = floor(uf) # coord of pixel to bottom left
vi = floor(vf)
u2 = ui+1 # coords of pixel to top right
v2 = vi+1
mu = uf-ui # fraction of way across pixel
nu = vf-vi
#
# Clip coordinates to stay within the valid range
ui = max(0, min(ui, extendedSize[0]-1))
u2 = max(0, min(u2, extendedSize[0]-1))
vi = max(0, min(vi, extendedSize[1]-1))
v2 = max(0, min(v2, extendedSize[1]-1))
# #
# # Pixel values of four corners
A = inPix[ui % inSize[0],clip(vi,0,inSize[1]-1)]
B = inPix[u2 % inSize[0],clip(vi,0,inSize[1]-1)]
C = inPix[ui % inSize[0],clip(v2,0,inSize[1]-1)]
D = inPix[u2 % inSize[0],clip(v2,0,inSize[1]-1)]
# interpolate
(r,g,b) = (
A[0]*(1-mu)*(1-nu) + B[0]*(mu)*(1-nu) + C[0]*(1-mu)*nu+D[0]*mu*nu,
A[1]*(1-mu)*(1-nu) + B[1]*(mu)*(1-nu) + C[1]*(1-mu)*nu+D[1]*mu*nu,
A[2]*(1-mu)*(1-nu) + B[2]*(mu)*(1-nu) + C[2]*(1-mu)*nu+D[2]*mu*nu )
#
# (r,g,b) = (0,0,0)
else:
(r,g,b) = (0,0,0)
#
# Clip the coordinates to stay within the output image dimensions
i_clipped = max(0, min(i, outSize[0]-1))
j_clipped = max(0, min(j, outSize[1]-1))
outPix[i_clipped,j_clipped] = (int(round(r)),int(round(g)),int(round(b)))
1个回答
0
投票
投票
我认为问题来自于 edge 变量。它应该根据 outSize 而不是 inSize 计算。我会用
edge = outSize[0]/4 # theoretical length of edge
一旦解决了这个问题，几行后出现的源坐标uf和vf就不能再依赖于edge变量，必须更改为：
# source img coords
uf = extendedSize[0] * (theta + pi) / (2 * pi)
vf = extendedSize[1] * (pi / 2 - phi) / pi
所以完整的代码就变成了
# convert using an inverse transformation
def convertBack(imgIn,imgOut):
inSize = imgIn.size
outSize = imgOut.size
inPix = imgIn.load()
outPix = imgOut.load()
extendedSize = imgIn.size
extendedSize = (int(360/300 * inSize[0]), inSize[1])
edge = outSize[0]/4 # theoretical length of edge
# edge = inSize[0]/4 # the length of each edge in pixels
for i in range(outSize[0]):
# print(i)
face = int(i/edge) # 0 - back, 1 - left 2 - front, 3 - right
if face==2:
rng = range(0, int(edge*3))
else:
rng = range(int(edge), int(edge*2))
#
for j in rng:
if j<edge:
face2 = 4 # top
elif j>=2*edge:
face2 = 5 # bottom
else:
face2 = face
#
(x,y,z) = outImgToXYZ(i,j,face2,edge)
theta = atan2(y,x) # range -pi to pi
r = hypot(x,y)
phi = atan2(z,r) # range -pi/2 to pi/2
# source img coords
uf = extendedSize[0] * (theta + pi) / (2 * pi)
vf = extendedSize[1] * (pi / 2 - phi) / pi
#
if uf < inSize[0] :
# Use bilinear interpolation between the four surrounding pixels
ui = floor(uf) # coord of pixel to bottom left
vi = floor(vf)
u2 = ui+1 # coords of pixel to top right
v2 = vi+1
mu = uf-ui # fraction of way across pixel
nu = vf-vi
#
# Clip coordinates to stay within the valid range
ui = max(0, min(ui, extendedSize[0]-1))
u2 = max(0, min(u2, extendedSize[0]-1))
vi = max(0, min(vi, extendedSize[1]-1))
v2 = max(0, min(v2, extendedSize[1]-1))
# #
# # Pixel values of four corners
A = inPix[ui % inSize[0],clip(vi,0,inSize[1]-1)]
B = inPix[u2 % inSize[0],clip(vi,0,inSize[1]-1)]
C = inPix[ui % inSize[0],clip(v2,0,inSize[1]-1)]
D = inPix[u2 % inSize[0],clip(v2,0,inSize[1]-1)]
# interpolate
(r,g,b) = (
A[0]*(1-mu)*(1-nu) + B[0]*(mu)*(1-nu) + C[0]*(1-mu)*nu+D[0]*mu*nu,
A[1]*(1-mu)*(1-nu) + B[1]*(mu)*(1-nu) + C[1]*(1-mu)*nu+D[1]*mu*nu,
A[2]*(1-mu)*(1-nu) + B[2]*(mu)*(1-nu) + C[2]*(1-mu)*nu+D[2]*mu*nu )
#
# (r,g,b) = (0,0,0)
else:
(r,g,b) = (0,0,0)
#
# Clip the coordinates to stay within the output image dimensions
i_clipped = max(0, min(i, outSize[0]-1))
j_clipped = max(0, min(j, outSize[1]-1))
outPix[i_clipped,j_clipped] = (int(round(r)),int(round(g)),int(round(b)))
最新问题
- 图像在不应该被压缩的时候被压缩了
- Apple M2，~/.gitconfig 文件在运行源 ~/.gitconfig 时失败
- 为什么在JSP中点击提交按钮没有任何反应？
- 具有固定纵横比的 Matplotlib 颜色条
- kotlin，如何从函数返回类类型
- Visual Studio 代码“窗口意外终止（原因：‘崩溃’，代码：‘-2147483645’）”
- 如何在 python 3.7 和 Windows 10 上使用 matplotlib 绘制 .kml 文件中的数据？
- 如何用单个元素构成数组类型的限定表达式？
- 如果数据存在于另一个表中，则使用 Y 或 N 更新列
- 在 Spring 中处理 @GetMapping("") 的可选参数未通过 RestAssured 测试
- AWS CodePipeline 在部署前不提取工件
- apex 未安装
- 如何查看通过云功能发送的 Firebase Cloud Messaging 通知？
- 在 Spring 中处理 @GetMapping("") 的可选参数
- 我可以在导航到新页面并等待该页面完成加载后运行函数吗？
- 使列宽占据wxPython ListCtrl中的可用空间
- Terraform“azurerm_app_service_certificate”失败，退出代码“59716”
- Chrome 更新后不再可以通过 WebRTC 禁用私有 IP 匿名化？
- 在 Kotlin 中使用 Google 的生成式 AI 生成图像
- 如何使用 Android Kotlin 获取 Twitch 频道的实时状态？ [已关闭]
© www.soinside.com 2019 - 2024. All rights reserved.