Clothing Analysis

Clothing analysis finds the location of the clothing worn by a person. The person must have been identified by face detection, or an object detection task that was configured to use the pre-trained person detector.

After finding the location of a person's clothing, you can use other tasks to extract more information, for example use a color cluster task to identify the color of the clothing.

This section describes the parameters that you can set to configure clothing analysis.

Configuration Parameter Description
ClothingMode A comma-separated list of regions to identify (full, upper, lower).
Input The track to process.
NumParallel The maximum number of video frames to analyze simultaneously.
Type The analysis engine to use. Set this parameter to Clothing.

A Clothing analysis task produces the following output tracks.

Output track Type Description Output1This column indicates whether the information contained in the track is included by default in the output created by an output task (when you don't set the Input parameter for the output task).
Result ClothingResult A record for each analyzed frame that includes a bounding box describing the location of the clothing in the frame. Yes
ResultWithSource ClothingResultAndImage A record for each analyzed frame that describes the location of the clothing and includes the source frame. No

ClothingResult

Field name Type Description
id UUIDData A universally unique identifier to identify the detected face or person (the UUID is supplied by the face detection or object detection engine).
region RectangleData A bounding box describing the location of the clothing in the frame.
regiontype String 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.

ClothingResultAndImage

Field name Type Description
id UUIDData A universally unique identifier to identify the detected face or person (the UUID is supplied by the face detection or object detection engine).
region ImageMaskData The location of the clothing in the source frame.
regiontype String 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.
image ImageData The source frame.

_HP_HTML5_bannerTitle.htm