The following XML shows a single record produced by clothing analysis.
<record>
...
<trackname>Clothing.Result</trackname>
<ClothingResult>
<id>63f77e13-e916-4528-acfb-559e1db28574</id>
<region>
<left>116</left>
<top>190</top>
<width>248</width>
<height>480</height>
</region>
<regiontype>Full</regiontype>
</ClothingResult>
</record>
The record contains the following information:
The id element contains an identifier which is the same as that in the input record. This means that if the person was identified by face detection the identifier matches the ID for the detected face, and if the person was identified by object detection the identifier matches the ID for the detected person.
The region element contains the location of the clothing. The values are in pixels. The left and top elements give the position of the top-left corner of a rectangle, and width and height provide its width and height.
regiontype element specifies whether the region represents clothing covering the full body (Full), upper body (Upper), or lower body (Lower). These values correspond to those for the configuration parameter ClothingMode.Clothing analysis can produce several records for each detected face. For example, if you set ClothingMode=Full,Upper,Lower, HPE Media Server might produce three records. One contains the location of the clothing covering the full body, one contains the location of the clothing covering the upper body, and one contains the location of the clothing covering the lower body. HPE Media Server does not produce a record if the region is outside the boundary of the image or clothing analysis cannot find the region.
|
|