data augmentation for object detecting目标检测xml文件扩增（旋转实现）

1. 背景描述：

在利用CNN做目标检测时，数据量不足时，旋转源图像进行数据的扩充。

例：

源图像如下图所示：



标记所得xml文件中目标信息如下：

<object>
<name>airplane</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>431</xmin>
<ymin>367</ymin>
<xmax>607</xmax>
<ymax>453</ymax>
</bndbox>
</object>
<object>
<name>airplane</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>570</xmin>
<ymin>419</ymin>
<xmax>768</xmax>
<ymax>512</ymax>

想要将源图像旋转任意角度，相对应xml文件中的bndbox信息则需要更新。

2. 思路：

参考博客(http://blog.csdn.net/u014540717/article/details/53301195)

找到原图中标记方框的四个边中点坐标，计算其旋转后的坐标位置，然后利用cv2.boundingRect函数找到四个新坐标的外接矩形作为新的xml文件中的bndbox值写入。

3. 代码实现过程：

# coding:utf-8
# Copyright@hitzym, Dec,09,2017 at HIT
# blog:http://blog.csdn.net/yinhuan1649/article/category/7330626
import cv2
import math
import numpy as np
import xml.etree.ElementTree as ET
import os

def rotate_image(src, angle, scale=1):
w = src.shape[1]
h = src.shape[0]
# 角度变弧度
rangle = np.deg2rad(angle)  # angle in radians
# now calculate new image width and height
nw = (abs(np.sin(rangle) * h) + abs(np.cos(rangle) * w)) * scale
nh = (abs(np.cos(rangle) * h) + abs(np.sin(rangle) * w)) * scale
# ask OpenCV for the rotation matrix
rot_mat = cv2.getRotationMatrix2D((nw * 0.5, nh * 0.5), angle, scale)
# calculate the move from the old center to the new center combined
# with the rotation
rot_move = np.dot(rot_mat, np.array([(nw - w) * 0.5, (nh - h) * 0.5, 0]))
# the move only affects the translation, so update the translation
# part of the transform
rot_mat[0, 2] += rot_move[0]
rot_mat[1, 2] += rot_move[1]
dst = cv2.warpAffine(src, rot_mat, (int(math.ceil(nw)), int(math.ceil(nh))), flags=cv2.INTER_LANCZOS4)
# 仿射变换
return dst

# 对应修改xml文件
def rotate_xml(src, xmin, ymin, xmax, ymax, angle, scale=1.):
w = src.shape[1]
h = src.shape[0]
rangle = np.deg2rad(angle)  # angle in radians
# now calculate new image width and height
# 获取旋转后图像的长和宽
nw = (abs(np.sin(rangle)*h) + abs(np.cos(rangle)*w))*scale
nh = (abs(np.cos(rangle)*h) + abs(np.sin(rangle)*w))*scale
# ask OpenCV for the rotation matrix
rot_mat = cv2.getRotationMatrix2D((nw*0.5, nh*0.5), angle, scale)
# calculate the move from the old center to the new center combined
# with the rotation
rot_move = np.dot(rot_mat, np.array([(nw-w)*0.5, (nh-h)*0.5,0]))
# the move only affects the translation, so update the translation
# part of the transform
rot_mat[0, 2] += rot_move[0]
rot_mat[1, 2] += rot_move[1]                                   # rot_mat是最终的旋转矩阵
# point1 = np.dot(rot_mat, np.array([xmin, ymin, 1]))          #这种新画出的框大一圈
# point2 = np.dot(rot_mat, np.array([xmax, ymin, 1]))
# point3 = np.dot(rot_mat, np.array([xmax, ymax, 1]))
# point4 = np.dot(rot_mat, np.array([xmin, ymax, 1]))
point1 = np.dot(rot_mat, np.array([(xmin+xmax)/2, ymin, 1]))   # 获取原始矩形的四个中点，然后将这四个点转换到旋转后的坐标系下
point2 = np.dot(rot_mat, np.array([xmax, (ymin+ymax)/2, 1]))
point3 = np.dot(rot_mat, np.array([(xmin+xmax)/2, ymax, 1]))
point4 = np.dot(rot_mat, np.array([xmin, (ymin+ymax)/2, 1]))
concat = np.vstack((point1, point2, point3, point4))            # 合并np.array
# 改变array类型
concat = concat.astype(np.int32)
rx, ry, rw, rh = cv2.boundingRect(concat)                        #rx,ry,为新的外接框左上角坐标，rw为框宽度，rh为高度，新的xmax=rx+rw,新的ymax=ry+rh
return rx, ry, rw, rh

# 使图像旋转60,90,120,150,210,240,300度
xmlpath = './xml/'          #源图像路径
imgpath = './imgs/'         #源图像所对应的xml文件路径
rotated_imgpath = './rotatedimg/'
rotated_xmlpath = './rotatedxml/'
for angle in (60, 90, 120, 150, 180, 210, 240, 300):
for i in os.listdir(imgpath):
a, b = os.path.splitext(i)                            #分离出文件名a
img = cv2.imread(imgpath + a + '.jpg')
rotated_img = rotate_image(img,angle)
cv2.imwrite(rotated_imgpath + a + '_'+ str(angle) +'d.jpg',rotated_img)
print str(i) + ' has been rotated for '+ str(angle)+'°'
tree = ET.parse(xmlpath + a + '.xml')
root = tree.getroot()
for box in root.iter('bndbox'):
xmin = float(box.find('xmin').text)
ymin = float(box.find('ymin').text)
xmax = float(box.find('xmax').text)
ymax = float(box.find('ymax').text)
x, y, w, h = rotate_xml(img, xmin, ymin, xmax, ymax, angle)
# cv2.rectangle(rotated_img, (x, y), (x+w, y+h), [0, 0, 255], 2)   #可在该步骤测试新画的框位置是否正确
# cv2.imshow('xmlbnd',rotated_img)
# cv2.waitKey(200)
box.find('xmin').text = str(x)
box.find('ymin').text = str(y)
box.find('xmax').text = str(x+w)
box.find('ymax').text = str(y+h)
tree.write(rotated_xmlpath + a + '_'+ str(angle) +'d.xml')
print str(a) + '.xml has been rotated for '+ str(angle)+'°'

4. 测试旋转结果

将xml中的bounding box 显示在图片上用来测试旋转后结果是否正确

注：

- xml文件需要和其对应的jpg文件文件名一样

- e.g. monkey001.jpg 对应 monkey001.xml

- 上代码

# coding:utf-8
# Copyright@hitzym, Dec,09,2017 at HIT
# blog:http://blog.csdn.net/yinhuan1649/article/category/7330626
import cv2
import xml.etree.ElementTree as ET
import os

imgpath = './testimgs/'          #旋转后的图像路径
xmlpath = './testxml/'           #旋转后的xml文件路径
for img in os.listdir(imgpath):
a, b = os.path.splitext(img)
img = cv2.imread(imgpath + a +'.jpg')
tree = ET.parse(xmlpath + a + '.xml')
root = tree.getroot()
for box in root.iter('bndbox'):
x1 = int(box.find('xmin').text)
y1 = int(box.find('ymin').text)
x2 = int(box.find('xmax').text)
y2 = int(box.find('ymax').text)
cv2.rectangle(img,(x1,y1),(x2, y2), [0,255,0], 2)
cv2.imshow("test", img)
# cv2.waitKey(1000)
if 1 == cv2.waitKey(0):
pass

原图：


结果图：


这是旋转60°的结果图

主要参考了博客(http://blog.csdn.net/u014540717/article/details/53301195)

稍有改动

感谢！