DOTA转YOLO

#DOTA_to_YOLO.py:

import data_util as util
import os
import numpy as np
from PIL import Image

from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
Image.MAX_IMAGE_PIXELS = None


## trans dota format to format YOLO(darknet) required
def dota2darknet(imgpath, txtpath, dstpath, extractclassname):
    """
    :param imgpath: the path of images
    :param txtpath: the path of txt in dota format
    :param dstpath: the path of txt in YOLO format
    :param extractclassname: the category you selected
    :return:
    """
    filelist = util.GetFileFromThisRootDir(txtpath)
    for fullname in filelist:
        objects = util.parse_dota_poly(fullname)
        name = os.path.splitext(os.path.basename(fullname))[0]
        img_fullname = os.path.join(imgpath, name + '.png')
        img = Image.open(img_fullname)
        img_w, img_h = img.size
        # print img_w,img_h
        with open(os.path.join(dstpath, name + '.txt'), 'w') as f_out:
            for obj in objects:
                poly = obj['poly']
                bbox = np.array(util.dots4ToRecC(poly, img_w, img_h))
                if (sum(bbox <= 0) + sum(bbox >= 1)) >= 1:
                    continue
                if (obj['name'] in extractclassname):
                    id = extractclassname.index(obj['name'])
                else:
                    continue
                outline = str(id) + ' ' + ' '.join(list(map(str, bbox)))
                f_out.write(outline + '\n')


if __name__ == '__main__':
    dota2darknet('E:\BaiduNetdiskDownload\DOTA1.5\DOTA\\train1.5\images',
                 'E:\BaiduNetdiskDownload\DOTA1.5\DOTA\\train1.5\labels',
                 'E:\BaiduNetdiskDownload\DOTA1.5\DOTA\\train1.5\labels_yolo',
                 util.wordname_18)

    dota2darknet('E:\BaiduNetdiskDownload\DOTA1.5\DOTA\\val1.5\images',
                 'E:\BaiduNetdiskDownload\DOTA1.5\DOTA\\val1.5\labels',
                 'E:\BaiduNetdiskDownload\DOTA1.5\DOTA\\val1.5\labels_yolo',
                 util.wordname_18)

 

data_util.py

import sys
import codecs
import numpy as np
import shapely.geometry as shgeo
import os
import re
import math
"""
    some basic functions which are useful for process DOTA data
"""
#DOTA1.5
wordname_18 = ['small-vehicle', 'large-vehicle', 'plane', 'storage-tank', 'ship',
 'harbor', 'ground-track-field','soccer-ball-field', 'tennis-court',
 'swimming-pool', 'baseball-diamond', 'roundabout', 'basketball-court',
'bridge', 'helicopter','container crane']


def custombasename(fullname):
    return os.path.basename(os.path.splitext(fullname)[0])

def GetFileFromThisRootDir(dir,ext = None):
  allfiles = []
  needExtFilter = (ext != None)
  for root,dirs,files in os.walk(dir):
    for filespath in files:
      filepath = os.path.join(root, filespath)
      extension = os.path.splitext(filepath)[1][1:]
      if needExtFilter and extension in ext:
        allfiles.append(filepath)
      elif not needExtFilter:
        allfiles.append(filepath)
  return allfiles

def TuplePoly2Poly(poly):
    outpoly = [poly[0][0], poly[0][1],
                       poly[1][0], poly[1][1],
                       poly[2][0], poly[2][1],
                       poly[3][0], poly[3][1]
                       ]
    return outpoly

def parse_dota_poly(filename):
    """
        parse the dota ground truth in the format:
        [(x1, y1), (x2, y2), (x3, y3), (x4, y4)]
    """
    objects = []
    #print('filename:', filename)
    f = []
    if (sys.version_info >= (3, 5)):
        fd = open(filename, 'r')
        f = fd
    elif (sys.version_info >= 2.7):
        fd = codecs.open(filename, 'r')
        f = fd
    # count = 0
    while True:
        line = f.readline()
        # count = count + 1
        # if count < 2:
        #     continue
        if line:
            splitlines = line.strip().split(' ')
            object_struct = {}
            ### clear the wrong name after check all the data
            #if (len(splitlines) >= 9) and (splitlines[8] in classname):
            if (len(splitlines) < 9):
                continue
            if (len(splitlines) >= 9):
                    object_struct['name'] = splitlines[8]
            if (len(splitlines) == 9):
                object_struct['difficult'] = '0'
            elif (len(splitlines) >= 10):
                # if splitlines[9] == '1':
                # if (splitlines[9] == 'tr'):
                #     object_struct['difficult'] = '1'
                # else:
                object_struct['difficult'] = splitlines[9]
                # else:
                #     object_struct['difficult'] = 0
            object_struct['poly'] = [(float(splitlines[0]), float(splitlines[1])),
                                     (float(splitlines[2]), float(splitlines[3])),
                                     (float(splitlines[4]), float(splitlines[5])),
                                     (float(splitlines[6]), float(splitlines[7]))
                                     ]
            gtpoly = shgeo.Polygon(object_struct['poly'])
            object_struct['area'] = gtpoly.area
            # poly = list(map(lambda x:np.array(x), object_struct['poly']))
            # object_struct['long-axis'] = max(distance(poly[0], poly[1]), distance(poly[1], poly[2]))
            # object_struct['short-axis'] = min(distance(poly[0], poly[1]), distance(poly[1], poly[2]))
            # if (object_struct['long-axis'] < 15):
            #     object_struct['difficult'] = '1'
            #     global small_count
            #     small_count = small_count + 1
            objects.append(object_struct)
        else:
            break
    return objects

def dots4ToRecC(poly, img_w, img_h):
    xmin, ymin, xmax, ymax = dots4ToRec4(poly)
    x = (xmin + xmax)/2
    y = (ymin + ymax)/2
    w = xmax - xmin
    h = ymax - ymin
    return x/img_w, y/img_h, w/img_w, h/img_h

def parse_dota_poly2(filename):
    """
        parse the dota ground truth in the format:
        [x1, y1, x2, y2, x3, y3, x4, y4]
    """
    objects = parse_dota_poly(filename)
    for obj in objects:
        obj['poly'] = TuplePoly2Poly(obj['poly'])
        obj['poly'] = list(map(int, obj['poly']))
    return objects

def parse_dota_rec(filename):
    """
        parse the dota ground truth in the bounding box format:
        "xmin, ymin, xmax, ymax"
    """
    objects = parse_dota_poly(filename)
    for obj in objects:
        poly = obj['poly']
        bbox = dots4ToRec4(poly)
        obj['bndbox'] = bbox
    return objects
## bounding box transfer for varies format

def dots4ToRec4(poly):
    xmin, xmax, ymin, ymax = min(poly[0][0], min(poly[1][0], min(poly[2][0], poly[3][0]))), \
                            max(poly[0][0], max(poly[1][0], max(poly[2][0], poly[3][0]))), \
                             min(poly[0][1], min(poly[1][1], min(poly[2][1], poly[3][1]))), \
                             max(poly[0][1], max(poly[1][1], max(poly[2][1], poly[3][1])))
    return xmin, ymin, xmax, ymax
def dots4ToRec8(poly):
    xmin, ymin, xmax, ymax = dots4ToRec4(poly)
    return xmin, ymin, xmax, ymin, xmax, ymax, xmin, ymax
    #return dots2ToRec8(dots4ToRec4(poly))
def dots2ToRec8(rec):
    xmin, ymin, xmax, ymax = rec[0], rec[1], rec[2], rec[3]
    return xmin, ymin, xmax, ymin, xmax, ymax, xmin, ymax

def groundtruth2Task1(srcpath, dstpath):
    filelist = GetFileFromThisRootDir(srcpath)
    # names = [custombasename(x.strip())for x in filelist]
    filedict = {}
    for cls in wordname_15:
        fd = open(os.path.join(dstpath, 'Task1_') + cls + r'.txt', 'w')
        filedict[cls] = fd
    for filepath in filelist:
        objects = parse_dota_poly2(filepath)

        subname = custombasename(filepath)
        pattern2 = re.compile(r'__([\d+\.]+)__\d+___')
        rate = re.findall(pattern2, subname)[0]

        for obj in objects:
            category = obj['name']
            difficult = obj['difficult']
            poly = obj['poly']
            if difficult == '2':
                continue
            if rate == '0.5':
                outline = custombasename(filepath) + ' ' + '1' + ' ' + ' '.join(map(str, poly))
            elif rate == '1':
                outline = custombasename(filepath) + ' ' + '0.8' + ' ' + ' '.join(map(str, poly))
            elif rate == '2':
                outline = custombasename(filepath) + ' ' + '0.6' + ' ' + ' '.join(map(str, poly))

            filedict[category].write(outline + '\n')

def Task2groundtruth_poly(srcpath, dstpath):
    thresh = 0.1
    filedict = {}
    Tasklist = GetFileFromThisRootDir(srcpath, '.txt')

    for Taskfile in Tasklist:
        idname = custombasename(Taskfile).split('_')[-1]
        # idname = datamap_inverse[idname]
        f = open(Taskfile, 'r')
        lines = f.readlines()
        for line in lines:
            if len(line) == 0:
                continue
            # print('line:', line)
            splitline = line.strip().split(' ')
            filename = splitline[0]
            confidence = splitline[1]
            bbox = splitline[2:]
            if float(confidence) > thresh:
                if filename not in filedict:
                    # filedict[filename] = codecs.open(os.path.join(dstpath, filename + '.txt'), 'w', 'utf_16')
                    filedict[filename] = codecs.open(os.path.join(dstpath, filename + '.txt'), 'w')
                # poly = util.dots2ToRec8(bbox)
                poly = bbox
                #               filedict[filename].write(' '.join(poly) + ' ' + idname + '_' + str(round(float(confidence), 2)) + '\n')
            # print('idname:', idname)

            # filedict[filename].write(' '.join(poly) + ' ' + idname + '_' + str(round(float(confidence), 2)) + '\n')

            filedict[filename].write(' '.join(poly) + ' ' + idname + '\n')


def polygonToRotRectangle(bbox):
    """
    :param bbox: The polygon stored in format [x1, y1, x2, y2, x3, y3, x4, y4]
    :return: Rotated Rectangle in format [cx, cy, w, h, theta]
    """
    bbox = np.array(bbox,dtype=np.float32)
    bbox = np.reshape(bbox,newshape=(2,4),order='F')
    angle = math.atan2(-(bbox[0,1]-bbox[0,0]),bbox[1,1]-bbox[1,0])

    center = [[0],[0]]

    for i in range(4):
        center[0] += bbox[0,i]
        center[1] += bbox[1,i]

    center = np.array(center,dtype=np.float32)/4.0

    R = np.array([[math.cos(angle), -math.sin(angle)], [math.sin(angle), math.cos(angle)]], dtype=np.float32)

    normalized = np.matmul(R.transpose(),bbox-center)

    xmin = np.min(normalized[0,:])
    xmax = np.max(normalized[0,:])
    ymin = np.min(normalized[1,:])
    ymax = np.max(normalized[1,:])

    w = xmax - xmin + 1
    h = ymax - ymin + 1

    return [float(center[0]),float(center[1]),w,h,angle]