BLOCKS Reference

Machine Learning

Video analysis

Overview

This BLOCK is currently in beta. The beta version will become unusable after the official version is released.

Some functions may not work properly during the beta. We appreciate your feedback regarding bugs or ways to improve MAGELLAN BLOCKS.

You must enable the Cloud Video Intelligence API open_in_new to use this BLOCK. Refer to Basic Guide > Hints > Enabling Google APIs for details.

This BLOCK uses the Google Cloud Video Intelligence serviceopen_in_new to analyze a video stored in Google Cloud Storage (GCS). Results of the analysis are stored into the variable designated in the Results variable property.

Properties

Property Explanation
BLOCK name

Configure the name displayed on this BLOCK.

GCP service account

Select the GCP service account to use with this BLOCK.

Video file GCS URL

Designate the GCS URL of the video file to be analyzed.

Features to detect

Select the types of features to detect in the video. You can select multiple at once from among the following:

  • Objects (dogs, flowers, people, etc.)
  • Scene changes
  • Adult content
Results variable

Designate the variable that will store the video analysis results.

Refer to Output specifications > Video analysis for details on the contents of the results variable.

BLOCK memos

Make any notes about this BLOCK.

Stationary camera

Designate whether or not the video was shot by a stationary camera.

Label detection level

Select the level at which labels in the video will be detected. You can select from the following:

  • Detect shot-level labels
  • Detect frame-level labels
  • Detect both shot and frame-level labels