三、标注标准及 XML 解析
标注标准:VOC2011 Annotation Guidelines
标注信息是用 xml 文件组织的如下:
<annotation>
<folder>VOC2007</folder>
<filename>000001.jpg</filename> # 文件名
<source>
<database>The VOC2007 Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
<flickrid>341012865</flickrid>
</source>
<owner>
<flickrid>Fried Camels</flickrid>
<name>Jinky the Fruit Bat</name>
</owner>
<size> # 图像尺寸, 用于对 bbox 左上和右下坐标点做归一化操作
<width>353</width>
<height>500</height>
<depth>3</depth>
</size>
<segmented>0</segmented> # 是否用于分割
<object>
<name>dog</name> # 物体类别
<pose>Left</pose> # 拍摄角度:front, rear, left, right, unspecified
<truncated>1</truncated> # 目标是否被截断(比如在图片之外),或者被遮挡(超过15%)
<difficult>0</difficult> # 检测难易程度,这个主要是根据目标的大小,光照变化,图片质量来判断
<bndbox>
<xmin>48</xmin>
<ymin>240</ymin>
<xmax>195</xmax>
<ymax>371</ymax>
</bndbox>
</object>
<object>
<name>person</name>
<pose>Left</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>8</xmin>
<ymin>12</ymin>
<xmax>352</xmax>
<ymax>498</ymax>
</bndbox>
</object>
</annotation>