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.

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.
SegmentDuration The maximum duration of a record in the SegmentedResult or SegmentedResultWithSource track.
Type The analysis engine to use. Set this parameter to Clothing.

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).
Data ClothingResult Contains one record, describing the analysis results, for each input record. No
DataWithSource ClothingResultAndImage

The same as the Data track, but each record also includes the source frame.

No
Result ClothingResult Contains one record, describing the analysis results, for each person. Yes
ResultWithSource ClothingResultAndImage

The same as the Result track, but each record also includes the best source frame.

No
SegmentedResult ClothingResult (Available only when processing video). Contains one or more records, describing the analysis results, for each person. The maximum duration of records in this track is limited by the parameter SegmentDuration, so multiple records are created with the same ID when a person remains in the scene for longer than this duration. Yes
SegmentedResultWithSource ClothingResultAndImage

(Available only when processing video). The same as the SegmentedResult track, but each record also includes the best 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

The same as ClothingResult records, with the following additional fields.

Field name Type Description
image ImageData The source frame.

_FT_HTML5_bannerTitle.htm