如何解决基于对象的土地覆盖分类:将 shapefile 转换为栅格
对于我的硕士论文,我目前正在尝试创建一个基于对象的分类代码。在创建我的分割形状文件并光栅化我的训练数据后,我陷入困境并搜索如何在代码中实现我的 shapefile。我想尝试栅格化 shapefile,但它包含统计信息(17 个属性),因此属性应该以某种方式变成带。以下是我的代码中棘手的部分目前的样子:
# Filename of the raster Tiff that will be created
raster_fn = f'{classif_path}object.tif'
# Filename of input OGR file
train_fn = f'{shapefile_path}SegmentationSTAT_BCK_median.shp'
train_ds = ogr.Open(train_fn)
lyr = train_ds.GetLayer()
# create a new raster layer in memory
driver = gdal.GetDriverByName('MEM')
target_ds = driver.Create('',median_temp_tif.RasterXSize,median_temp_tif.RasterYSize,1,gdal.GDT_UInt16)
target_ds.SetGeoTransform(median_temp_tif.GetGeoTransform())
target_ds.SetProjection(median_temp_tif.GetProjection())
# rasterize the training points
options = ['ATTRIBUTE=A2017_7__m','ATTRIBUTE=A2017_7__1','ATTRIBUTE=A2017_7__2','ATTRIBUTE=A2017_7__s','ATTRIBUTE=A2018_7__m','ATTRIBUTE=A2018_7__1','ATTRIBUTE=A2018_7__2','ATTRIBUTE=A2018_7__s','ATTRIBUTE=A2019_7__m','ATTRIBUTE=A2019_7__1','ATTRIBUTE=A2019_7__2','ATTRIBUTE=A2019_7__s','ATTRIBUTE=A2020_7__m','ATTRIBUTE=A2020_7__1','ATTRIBUTE=A2020_7__2','ATTRIBUTE=A2020_7__s','ATTRIBUTE=CODE']
gdal.RasterizeLayer(target_ds,[17],lyr,options=options)
# retrieve the rasterized data and print basic stats
data = target_ds.GetRasterBand(1).ReadAsArray()
这里是整个分类代码:
in_situ_cal_shp = f'{shapefile_path}{period}_cal.shp'
in_situ_cal_tif = f'{classif_path}{period}_cal.tif'
median_temp_tif = f'{median_path}S1A_IW_SLC__1SDV_A2018_7_DESCENDING_Orb_Thermal_Cal_Sigma_Deb_TC_SRTM1s_Clip_AF_VH_filtered_mean_norm_medianFilter9x9.tif'
polygones_val_shp = f'{shapefile_path}{period}_val.shp'
polygones_val_tif = f'{classif_path}{period}_val.tif'
# Open the calibration shapefile with GeoPandas
in_situ_gdf = gpd.read_file(in_situ_cal_shp)
# Open the raster file you want to use as a template for rasterize
img_src = rasterio.open(median_temp_tif)
img = img_src.read()
meta = img_src.meta.copy()
meta.update(compress='lzw')
meta.update(nodata=0)
# Burn the features into the raster and write it out
dst_src = rasterio.open(in_situ_cal_tif,'w+',**meta)
dst_arr = dst_src.read(1)
# this is where we create a generator of geom,value pairs to use in rasterizing
geom_col = in_situ_gdf.geometry
code_col = in_situ_gdf.CODE
shapes = ((geom,value) for geom,value in zip(geom_col,code_col))
in_situ_cal_arr = features.rasterize(shapes=shapes,fill=0,out=dst_arr,transform=dst_src.transform)
dst_src.write_band(1,in_situ_cal_arr)
# Close rasterio objects
img_src.close()
dst_src.close()
# Filename of the raster Tiff that will be created
raster_fn = f'{classif_path}object.tif'
# Filename of input OGR file
train_fn = f'{shapefile_path}SegmentationSTAT_BCK_median.shp'
train_ds = ogr.Open(train_fn)
lyr = train_ds.GetLayer()
# create a new raster layer in memory
driver = gdal.GetDriverByName('MEM')
target_ds = driver.Create('',options=options)
# retrieve the rasterized data and print basic stats
data = target_ds.GetRasterBand(1).ReadAsArray()
# Create an empty list to append all feature rasters one by one
list_src_arr = []
list_im = target_ds
for im_file in list_im:
src = rasterio.open(im_file,"r")
im = src.read(1)
list_src_arr.append(im)
src.close()
# Merge all the 2D matrices from the list into one 3D matrix
feat_arr = np.dstack(list_src_arr)
print(feat_arr.shape)
print(f'There are {feat_arr.shape[2]} features')
print(f'The features type is : {feat_arr.dtype}')
# Open in-situ used for calibration
src = rasterio.open(in_situ_cal_tif,"r")
cal_arr = src.read(1)
src.close()
# Find how many non-zero entries we have -- i.e. how many training data samples?
n_samples = (cal_arr > 0).sum()
print(f'We have {n_samples} samples\n')
# What are our classification labels?
labels = np.unique(cal_arr[cal_arr > 0])
print(f'The training data include {labels.size} classes: {labels} \n')
# We will need a "X" matrix containing our features,and a "y" array containing our labels
# These will have n_samples rows
# In other languages we would need to allocate these and them loop to fill them,but NumPy can be faster
X = feat_arr[cal_arr > 0,:]
y = in_situ_cal_arr[cal_arr > 0]
X = np.nan_to_num(X,nan=-10)
print(f'Our X matrix is sized: {X.shape}')
print(f'Our y array is sized: {y.shape}')
start_training = time.time()
# Initialize our model with 500 trees
rf = RandomForestClassifier(n_estimators=500,oob_score=True)
# Fit our model to training data
rf = rf.fit(X,y)
end_training = time.time()
# Get time elapsed during the Random Forest training
hours,rem = divmod(end_training-start_training,3600)
minutes,seconds = divmod(rem,60)
print("Random Forest training : {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
print(f'Our OOB prediction of accuracy is: {round(rf.oob_score_ * 100,2)}%')
bands = range(1,X.shape[1]+1)
for b,imp in zip(bands,rf.feature_importances_):
print(f'Band {b} importance: {round(imp,4)}')
# Setup a dataframe
df = pd.DataFrame()
df['truth'] = y
df['predict'] = rf.predict(X)
# Cross-tabulate predictions
cross_tab = pd.crosstab(df['truth'],df['predict'],margins=True)
display(cross_tab)
# Take our full image and reshape into long 2d array (nrow * ncol,nband) for classification
img = feat_arr
img = np.nan_to_num(img,nan=-10)
new_shape = (img.shape[0] * img.shape[1],img.shape[2])
img_as_array = img[:,:,:].reshape(new_shape)
print(f'Reshaped from {img.shape} to {img_as_array.shape}')
start_classification = time.time()
# Now predict for each pixel
class_prediction = rf.predict(img_as_array)
# Reshape our classification map
class_prediction = class_prediction.reshape(img[:,0].shape)
end_classification = time.time()
hours,rem = divmod(end_classification-start_classification,seconds))
classif_tif = f'{classif_path}Classif_{period}.tif'
print(class_prediction.shape)
img_src = rasterio.open(median_temp_tif)
img = img_src.read()
meta = img_src.meta.copy()
meta.update(compress='lzw')
print(meta)
dst = rasterio.open(classif_tif,'w',**meta)
dst.write(class_prediction,1)
dst.close()
# Open the shapefile with GeoPandas
polygones_gdf = gpd.read_file(polygones_val_shp)
# Open the raster file you want to use as a template for rasterize
img_src = rasterio.open(median_temp_tif)
img = img_src.read()
meta = img_src.meta.copy()
meta.update(compress='lzw')
meta.update(nodata=0)
# Burn the features into the raster and write it out
dst_src = rasterio.open(polygones_val_tif,value pairs to use in rasterizing
geom_col = polygones_gdf.geometry
code_col = polygones_gdf.CODE
shapes = ((geom,code_col))
polygones_val_arr = features.rasterize(shapes=shapes,polygones_val_arr)
# Close rasterio objects
img_src.close()
dst_src.close()
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。