目标检测：数据增强方法及代码实现

数据增强 :
生成数据增强后的图像和对应的xml

• 高斯模糊
• 调整亮度
• 平移
• cutout
• 裁剪

# -*- coding=utf-8 -*-
import os
import time
import random
import cv2
import numpy as np
from skimage import exposure
import xml.etree.ElementTree as ET
import xml.dom.minidom as DOC

# 从xml文件中提取bounding box信息, 格式为[[x_min, y_min, x_max, y_max, name]]
def parse_xml(xml_path):
    '''
    输入：
        xml_path: xml的文件路径
    输出：
        从xml文件中提取bounding box信息, 格式为[[x_min, y_min, x_max, y_max, name]]
    '''
    tree = ET.parse(xml_path)
    root = tree.getroot()
    objs = root.findall('object')
    coords = list()
    for ix, obj in enumerate(objs):
        name = obj.find('name').text
        box = obj.find('bndbox')
        x_min = int(box[0].text)
        y_min = int(box[1].text)
        x_max = int(box[2].text)
        y_max = int(box[3].text)
        coords.append([x_min, y_min, x_max, y_max, name])
    return coords

#将bounding box信息写入xml文件中, bouding box格式为[[x_min, y_min, x_max, y_max, name]]
def generate_xml(img_name,coords,img_size,out_root_path,cnt):
    '''
    输入：
        img_name：图片名称，如a.jpg
        coords:坐标list，格式为[[x_min, y_min, x_max, y_max, name]]，name为概况的标注
        img_size：图像的大小,格式为[h,w,c]
        out_root_path: xml文件输出的根路径
    '''
    doc = DOC.Document()  # 创建DOM文档对象

    annotation = doc.createElement('annotation')
    doc.appendChild(annotation)

    title = doc.createElement('folder')
    title_text = doc.createTextNode('Tianchi')
    title.appendChild(title_text)
    annotation.appendChild(title)

    title = doc.createElement('filename')
    title_text = doc.createTextNode(img_name)
    title.appendChild(title_text)
    annotation.appendChild(title)

    source = doc.createElement('source')
    annotation.appendChild(source)

    title = doc.createElement('database')
    title_text = doc.createTextNode('The Tianchi Database')
    title.appendChild(title_text)
    source.appendChild(title)

    title = doc.createElement('annotation')
    title_text = doc.createTextNode('Tianchi')
    title.appendChild(title_text)
    source.appendChild(title)

    size = doc.createElement('size')
    annotation.appendChild(size)

    title = doc.createElement('width')
    title_text = doc.createTextNode(str(img_size[1]))
    title.appendChild(title_text)
    size.appendChild(title)

    title = doc.createElement('height')
    title_text = doc.createTextNode(str(img_size[0]))
    title.appendChild(title_text)
    size.appendChild(title)

    title = doc.createElement('depth')
    title_text = doc.createTextNode(str(img_size[2]))
    title.appendChild(title_text)
    size.appendChild(title)

    for coord in coords:

        object = doc.createElement('object')
        annotation.appendChild(object)

        title = doc.createElement('name')
        title_text = doc.createTextNode(coord[4])
        title.appendChild(title_text)
        object.appendChild(title)

        pose = doc.createElement('pose')
        pose.appendChild(doc.createTextNode('Unspecified'