Python打开TIF失败多个库

Question

我在打开我拥有的一些 .tif 文件时遇到了一些问题。我尝试过使用pillow、gdal、cv2 和skimage。我更喜欢使用pillow，因为我确实在其他脚本中使用过它。我不能使用rasterio，因为当我设置批处理文件rasterio 时会抛出我尚未解决的gdal._version error。

这个打开图像错误对我来说很奇怪，因为我有另一个使用 gdal 并且打开它没有问题的分割光栅图像的代码（有一个丢失数据的问题，所以我切换到这个）。我读了几篇关于pillow 如何不支持某些数据类型的帖子，但我还没有任何解决方法。我已附加图像的属性，并将继续解决问题。

有什么问题需要我修复吗？同样，我更喜欢使用我发布的第一个代码块（使用枕头）。

枕头

import os
from PIL import Image
from itertools import product

def tile(filename, dir_in, dir_out, d):
    Image.MAX_IMAGE_PIXELS = None
    name, ext = os.path.splitext(filename)
    img = Image.open(os.path.join(dir_in, filename))
    w, h = img.size

    grid = list(product(range(0, h - h % d, d), range(0, w - w % d, d)))
    for i, j in grid:
        box = (j, i, j + d, i + d)
        out = os.path.join(dir_out, f'{name}_{i}_{j}{ext}')
        img.crop(box).save(out)

tile('name.tif',
     r'D:\image',
     r'D:\images_split',
     1000)

Traceback (most recent call last):
  File "C:/Users/delete_NA/split.py", line 22, in <module>
    1000)
  File "C:/Users/delete_NA/split.py", line 9, in tile
    img = Image.open(os.path.join(dir_in, filename))
  File "C:\Users\anaconda3\envs\split\lib\site-packages\PIL\Image.py", line 2959, in open
    "cannot identify image file %r" % (filename if filename else fp)
PIL.UnidentifiedImageError: cannot identify image file 'D:\\image\\image_to_split.tif'

GDAL

import os
import gdal
from itertools import product

def tile(filename, dir_in, dir_out, d):
    Image.MAX_IMAGE_PIXELS = None
    name, ext = os.path.splitext(filename)
    img = gdal.Open(os.path.join(dir_in, filename))
    w, h = img.size

    grid = list(product(range(0, h - h % d, d), range(0, w - w % d, d)))
    for i, j in grid:
        box = (j, i, j + d, i + d)
        out = os.path.join(dir_out, f'{name}_{i}_{j}{ext}')
        img.crop(box).save(out)

tile('name.tif',
     r'D:\image',
     r'D:\images_split',
     1000)

Traceback (most recent call last):
  File "C:/Users/delete_NA/split.py", line 22, in <module>
    1000)
  File "C:/Users/delete_NA/split.py", line 10, in tile
    w, h = img.size
  File "C:\Users\anaconda3\envs\split\lib\site-packages\osgeo\gdal.py", line 2184, in <lambda>
    __getattr__ = lambda self, name: _swig_getattr(self, Dataset, name)
  File "C:\Users\anaconda3\envs\split\lib\site-packages\osgeo\gdal.py", line 80, in _swig_getattr
    raise AttributeError("'%s' object has no attribute '%s'" % (class_type.__name__, name))
AttributeError: 'Dataset' object has no attribute 'size'

使用 gdal 的其他拆分代码 - 这个有效

import os
from osgeo import gdal
# import variables

# Setting the directory
os.chdir(r"D:\ortho")

# Loading in the image
rimg = gdal.Open("image.tif")

# Upper left corner of the minX and maxY
gt = rimg.GetGeoTransform()

xmin = gt[0]
ymax = gt[3]

res = gt[1]
xlen = res * rimg.RasterXSize # units is important UTM or WGS
ylen = res * rimg.RasterYSize

# how many tiles you want to have in each row and column
xdiv = 150
ydiv = 150

# Determining the size of each new image 
xsize = xlen/xdiv
ysize = ylen/ydiv

print(xsize)
print(ysize)

xsteps = [xmin + xsize * i for i in range(xdiv+1)] # plut because we start in the left top corner where X is at its lowest
ysteps = [ymax - ysize * i for i in range(ydiv+1)] # minus because we start in the left top corner where Y is at its highest

for i in range(xdiv):
    for j in range(ydiv):
        xmin = xsteps[i]
        xmax = xsteps[i+1]
        ymax = ysteps[j]
        ymin = ysteps[j+1]

        # Splices the image up into the set divs and saves them.
        gdal.Warp("D:/split_images/item" + str(i)+str(j) + ".tif",rimg,
                  outputBounds = (xmin,ymin,xmax,ymax),dstNodata = -9999)

Tif Properties Images

修改 我运行了另一个图像，它的大小只有一小部分，具有相同的属性。相同的 CRS、单位、数据类型等。我认为这不是尺寸问题，因为我通过了Image.MAX_IMAGE_PIXELS = None。不过需要注意的一点是，每个分割的图像都没有分配 CRS，这确实给我以后带来了问题。

Answer 1

经过一番挖掘，我发现pillow 中的Image.open() 不支持BigTiffs。它也只支持特定的byte sizes。 tifffile 可用于打开 BigTiffs。我最终在我的代码中更改了几件事。首先，使用tifffile 而不是pillow。二、将img.size改为img.shape。第三，tifffile 将图像打开为 numpy 数组，因此请改用clip 方法。该代码确实有效，尽管它没有被剪裁。不过，这回答了我最初的问题。

import os
import tifffile
from itertools import product

def tile(filename, dir_in, dir_out, d):
    name, ext = os.path.splitext(filename)
    img = tifffile.imread(os.path.join(dir_in, filename))
    w = img.shape[0]
    h = img.shape[1]

    grid = list(product(range(0, h - h % d, d), range(0, w - w % d, d)))
    for i, j in grid:
        box = (j, i, j + d, i + d)
        out = os.path.join(dir_out, f'{name}_{i}_{j}{ext}')
        img = img.clip(box)
        img = img.astype('uint8')
        tifffile.imsave(out, img)

tile('name.tif',
     r'D:\image',
     r'D:\images_split',
     1000)