Amazon Video Rekognition

S3 Volume

The S3 remote volume identifier is required to access the S3 bucket. If you haven't set up a remote volume yet, please refer to the Authentication section.

Note: The identifier must be enclosed in square brackets [].

AWS Access Key (optional)

Define only if you wish to use a different account to perform the operation.

AWS Secret Key (required)

Used as part of the authentication.

Action

Submit Job.

Submit a video rekognition request to AWS.

Retrieve Job.

Get video rekognition result from AWS.

Set Parameters

Define the request parameters using CatDV fields or set them manually on the worker.

Detection Types

Specifies what Amazon Rekognition looks for in a video—such as objects, faces, text, or unsafe content—to generate useful metadata for tagging and analysis.

Label: Detects objects, scenes, and concepts in the video(e.g., car, tree, wedding).

Faces: Detects faces and facial attributes like age range, emotions, or gender.

Celebrities: Identifies well-known people in the video using Amazon’s celebrity database.

Text: Detects and extracts text from video (printed or handwritten).

Unsafe Images: Flags potentially inappropriate or unsafe content (e.g., nudity or violence).

Technical Cues: Identifies content structure like black frames, color bars, or end credits.

Scene Description: Generates natural-language descriptions of scenes to improve content understanding.

Custom Faces: Matches detected faces against a custom face collection you’ve indexed. See Index Faces.

S3 Volume

The S3 remote volume identifier is required to access the S3 bucket. If you haven't set up a remote volume yet, please refer to the Authentication section.

Note: The identifier must be enclosed in square brackets [].

AWS Access Key (optional)

Define only if you wish to use a different account to perform the operation.

AWS Secret Key (required)

Used as part of the authentication.

Action

Submit Job.

Submit a video rekognition request to AWS.

Retrieve Job.

Get video rekognition result from AWS.

Set Parameters

Define the request parameters using CatDV fields or set them manually on the worker.

Detection Types

Specifies what Amazon Rekognition looks for in a video—such as objects, faces, text, or unsafe content—to generate useful metadata for tagging and analysis.

Label: Detects objects, scenes, and concepts in the video(e.g., car, tree, wedding).

Faces: Detects faces and facial attributes like age range, emotions, or gender.

Celebrities: Identifies well-known people in the video using Amazon’s celebrity database.

Text: Detects and extracts text from video (printed or handwritten).

Unsafe Images: Flags potentially inappropriate or unsafe content (e.g., nudity or violence).

Technical Cues: Detects structural elements such as black frames, color bars, end credits, and distinct shots or scene changes. For this detection type, minimum marker interval and allow repeat matches settings are ignored to ensure full coverage of detected cues.

Scene Description: Generates natural-language descriptions of scenes to improve content understanding.

Custom Faces: Matches detected faces against a custom face collection you’ve indexed. See Index Faces.

Minimum Confidence

Sets the threshold (0–100) to filter results based on Amazon Rekognition's confidence score.

Minimum Marker Interval (secs)

Displays only the first detected instance within each marker interval. To show every instance, set the interval to 0.

Allow Repeat Matches

When enabled, allows multiple instances of the same detection to appear, even if they occur close together.

Show Confidence in Marker Name

Set confidence score as Marker name. e.g. ‘Confidence 83.55’

Draw Bounding Boxes

Bounding boxes are used to visually highlight detected elements—such as objects, faces, or celebrities—by drawing rectangles around them in the video. For the bounding box to appear, a color must be specified using a valid CSS color name (e.g., “lightblue”) or hex code (e.g., “#3698CF”).

This feature is supported for detection types like Labels, Faces, Celebrities, and Custom Faces and is available in the CatDV Web Client as part of its marker annotation feature. Each detected instance is given its own marker with a bounding box, making it easier to identify and track movement within the video.

Note: Bounding boxes are not yet supported in the CatDV Desktop Client. Editing clip markers in the Desktop Client (13.0.12 as of this writing) will remove any bounding box data.

Bounding Box Colour

Sets the color of the rectangle used to highlight detections. Choose a distinct color to ensure visibility against the video content.

Property key

Valid range (default)

Description

amazonAI.outputRawResponseDataToField

<field identifer>

Writes a JSON object to the field of your choosing e.g. clip[ai.json] - note these responses can be half a megabyte or larger which doesn’t sound like much but can crowd your database if you’re not careful, so it is recommended only to use this feature in a transient nature and then remove the extra data when finished.

amazonAI.outputRawResponseDataToFile

<path>

Writes a JSON object to an external text file of your choosing (e.g. /Volumes/MyData/myResponse.txt) which you could parse separately and then toss away, rather than keeping all of the raw response data in the CatDV database.

amazonAI.transcodeSizeThreshold

Any number (250)

In megabytes; set this to 0 to always transcode media for analysis.