microproduct/tool/algorithm/polsarpro/bin2tif.py

import os
import glob
import numpy as np
import struct
from PIL import Image
from tool.algorithm.ml.machineLearning import MachineLeaning as ml


def read_bin_to_img(bin_path):
    """
    读取bin格式二进制数据，输出为矩阵
    :param bin_path : bin文件的路径，包含.bin,.config
    :return : 矩阵信息
    """
    (bin_dir, bin_name) = os.path.split(bin_path)
    config_path = os.path.join(bin_dir, 'config.txt')
    config = open(config_path, 'r').read().split('\n', -1)
    rows = int(config[1])
    cols = int(config[4])

    bin_file = open(bin_path, 'rb')  # 打开二进制文件
    size = os.path.getsize(bin_path)  # 获得文件大小
    if size < rows * cols * 4:
        raise Exception(
            'bin size less than rows*cols*4! size:',
            size,
            'byte, rows:',
            rows,
            'cols:',
            cols)

    img = np.zeros([rows, cols], dtype=np.float32)
    for row in range(rows):
        data = bin_file.read(4 * cols)  # 每次读取一行的二进制数据
        row_data = struct.unpack('f' * cols, data)  # 转为一行float数据
        img[row, :] = row_data
    bin_file.close()
    return img

def write_bin_to_tif(out_tif_dir, bin_dir):
    """
    读取H-A-Alpha分解二进制数据，输出为矩阵格式的字典
    :param out_tif_dir : tif的输出路径
    :param bin_dir : 二进制数据的目录,包含.bin,.config
    :return out_tif_path: 生成tif的路径字典
    """
    bin_paths = list(glob.glob(os.path.join(bin_dir, '*.bin')))
    out_tif_path = {}
    for in_path in bin_paths:
        name = os.path.split(in_path)[1].split('.')[0]
        out_path = os.path.join(out_tif_dir, name + '.tif')
        out_tif_path.update({name: out_path})
        if os.path.exists(os.path.split(out_path)[0]) is False:
            os.makedirs(os.path.split(out_path)[0])
        img_array = read_bin_to_img(in_path)
        img_array[np.isnan(img_array)] = 0  # 异常值填充为0
        img_array = ml.standardization(img_array)  # 数据标准化到[0,1]
        out_image = Image.fromarray(img_array)
        out_image.save(out_path)
    return out_tif_path

def write_bin_to_tif_soil(out_tif_dir, bin_dir):
    """
    读取H-A-Alpha分解二进制数据，输出为矩阵格式的字典
    :param out_tif_dir : tif的输出路径
    :param bin_dir : 二进制数据的目录,包含.bin,.config
    :return out_tif_path: 生成tif的路径字典
    """
    bin_paths = list(glob.glob(os.path.join(bin_dir, '*.bin')))
    out_tif_path = {}
    for in_path in bin_paths:
        name = os.path.split(in_path)[1].split('.')[0]
        out_path = os.path.join(out_tif_dir, name + '.tif')
        out_tif_path.update({name: out_path})
        if os.path.exists(os.path.split(out_path)[0]) is False:
            os.makedirs(os.path.split(out_path)[0])
        img_array = read_bin_to_img(in_path)
        img_array[np.isnan(img_array)] = 0  # 异常值填充为0
        # img_array = ml.standardization(img_array)  # 数据标准化到[0,1]
        out_image = Image.fromarray(img_array)
        out_image.save(out_path)
    return out_tif_path

if __name__ == '__main__':
    bin_dir = r'F:\TempData\oh2004'
    out_tif_dir = r'F:\TempData\oh2004tif'
    write_bin_to_tif_soil(out_tif_dir, bin_dir)