无人机图像语义分割数据集（aeroscapes数据集）使用方法

数据集介绍

aeroscapes数据集下载链接
AeroScapes 航空语义分割基准包括使用商用无人机在 5 到 50 米的高度范围内捕获的图像。该数据集提供 3269 张 720p 图像和 11 个类别的真实掩码。

获取Class类别及其RGB值

由于本数据集未提供类别ID对应的RGB值，可以通过以下代码获取：

from PIL import Imageimport osbase_dir = "Visualizations/"base_seg_dir = "SegmentationClass/"files = os.listdir(base_dir)list1 = []for file in files:    img_dir = base_dir + file    segimg_dir = base_seg_dir + file    im = Image.open(img_dir)    segimg = Image.open(segimg_dir)    pix = im.load()    pix_seg = segimg.load()     width = im.size[0]    height = im.size[1]    for x in range(width): for y in range(height):     r, g, b = pix[x, y]     c = pix_seg[x,y]     if [c,r,g,b] not in list1:  list1.append([c,r,g,b])  print(list1)print(list1)

结果如下：

Person [192,128,128]--------------1Bike [0,128,0]----------------------2Car [128,128,128]----------------- 3Drone [128,0,0]--------------------4Boat [0,0,128]--------------------- 5Animal [192,0,128]---------------- 6Obstacle [192,0,0]------------------7Construction [192,128,0]-----------8Vegetation [0,64,0]-----------------9Road [128,128,0]-------------------10Sky [0,128,128]---------------------11

数据加载dataloder写法（基于pytorch）

由于该数据集提供了掩码图，因此不需要进行掩码图转换。下载完成后，文件结构如下：

• ImageSets文件夹：存放了两个txt文件，划分了训练集和验证集。
• JPEGImages文件夹：存放了RGB图像。
• SegmentationClass：存放了标签的掩模图。
• Visualizations：存放了标签图像。
  为了使用此数据集，需要根据划分好的txt文件读取图像，然后采用Pytorch的Dataloader模块进行加载。具体代码：

'''dataset.py'''import torchimport torch.utils.dataimport numpy as npimport cv2import os# txt_file = open("ImageSets/trn.txt")# train_filenames = txt_file.readlines()# for train_filename in train_filenames:#     print(train_filename)class DatasetTrain(torch.utils.data.Dataset):    def __init__(self, base_dir):  self.base_dir = base_dir self.img_dir = base_dir + "JPEGImages/" self.label_dir = base_dir + "SegmentationClass/" self.new_img_h = 512 self.new_img_w = 1024 self.examples = [] txt_path = self.base_dir + "ImageSets/trn.txt" txt_file = open(txt_path) train_filenames = txt_file.readlines() train_img_dir_path = self.img_dir label_img__dir_path = self.label_dir for train_filename in train_filenames:     train_filename=train_filename.strip('\n')     img_path = train_img_dir_path + train_filename + '.jpg'     label_img_path = label_img__dir_path + train_filename + '.png'     example = {}     example["img_path"] = img_path     example["label_img_path"] = label_img_path     self.examples.append(example) self.num_examples = len(self.examples)    def __getitem__(self, index): example = self.examples[index] img_path = example["img_path"] print(img_path) img = cv2.imread(img_path, -1)  img = cv2.resize(img, (self.new_img_w, self.new_img_h),    interpolation=cv2.INTER_NEAREST)  label_img_path = example["label_img_path"] print(label_img_path) label_img = cv2.imread(label_img_path, cv2.IMREAD_GRAYSCALE)  label_img = cv2.resize(label_img, (self.new_img_w, self.new_img_h),   interpolation=cv2.INTER_NEAREST)  # normalize the img (with the mean and std for the pretrained ResNet): img = img/255.0 img = img - np.array([0.485, 0.456, 0.406]) img = img/np.array([0.229, 0.224, 0.225])  img = np.transpose(img, (2, 0, 1))  img = img.astype(np.float32) # convert numpy -> torch: img = torch.from_numpy(img)  label_img = torch.from_numpy(label_img)  return (img, label_img)    def __len__(self): return self.num_examplesclass DatasetVal(torch.utils.data.Dataset):    def __init__(self, base_dir):  self.base_dir = base_dir self.img_dir = base_dir + "JPEGImages/" self.label_dir = base_dir + "SegmentationClass/" self.new_img_h = 512 self.new_img_w = 1024 self.examples = [] txt_path = self.base_dir + "ImageSets/val.txt" txt_file = open(txt_path) valid_filenames = txt_file.readlines() train_img_dir_path = self.img_dir label_img__dir_path = self.label_dir for valid_filename in valid_filenames:     valid_filename=valid_filename.strip('\n')     img_path = train_img_dir_path + valid_filename + '.jpg'     label_img_path = label_img__dir_path + valid_filename + '.png'     example = {}     example["img_path"] = img_path     example["label_img_path"] = label_img_path     self.examples.append(example) self.num_examples = len(self.examples)    def __getitem__(self, index): example = self.examples[index] img_path = example["img_path"] print(img_path) img = cv2.imread(img_path, -1)  img = cv2.resize(img, (self.new_img_w, self.new_img_h),    interpolation=cv2.INTER_NEAREST)  label_img_path = example["label_img_path"] print(label_img_path) label_img = cv2.imread(label_img_path, cv2.IMREAD_GRAYSCALE)  label_img = cv2.resize(label_img, (self.new_img_w, self.new_img_h),   interpolation=cv2.INTER_NEAREST)  # normalize the img (with the mean and std for the pretrained ResNet): img = img/255.0 img = img - np.array([0.485, 0.456, 0.406]) img = img/np.array([0.229, 0.224, 0.225])  img = np.transpose(img, (2, 0, 1))  img = img.astype(np.float32) # convert numpy -> torch: img = torch.from_numpy(img)  label_img = torch.from_numpy(label_img)  return (img, label_img)    def __len__(self): return self.num_examples'''以下代码为测试功能，正式使用时需要注释掉'''if __name__ == "__main__":    base_dir = "aeroscapes/"    train_dataset = DatasetTrain(base_dir = base_dir)    train_loader = torch.utils.data.DataLoader(dataset=train_dataset,  batch_size=3, shuffle=True,  num_workers=1,drop_last=True)    val_dataset = DatasetVal(base_dir = base_dir)    val_loader = torch.utils.data.DataLoader(dataset=val_dataset,  batch_size=3, shuffle=True,  num_workers=1,drop_last=True)    from torch.autograd import Variable    for step, (imgs, label_imgs) in enumerate(train_loader): imgs = Variable(imgs).cuda() # (shape: (batch_size, 3, img_h, img_w)) print(imgs.shape) label_imgs = Variable(label_imgs.type(torch.LongTensor)).cuda() # (shape: (batch_size, img_h, img_w)) print(label_imgs.shape)    for step, (imgs, label_imgs) in enumerate(val_loader): imgs = Variable(imgs).cuda() # (shape: (batch_size, 3, img_h, img_w)) print(imgs.shape) label_imgs = Variable(label_imgs.type(torch.LongTensor)).cuda() # (shape: (batch_size, img_h, img_w)) print(label_imgs.shape)

使用前根据自己数据集存放的路径修改base_dir 变量。