Image Attributes Proof of Delivery Model

AI Data Capture SDK 4.1

Overview

Model Name: image-attributes-proof-of-delivery

The Image Attributes Proof of Delivery (POD) model analyzes images at a fixed input size to detect a specific attribute. For each detected attribute, the model returns a confidence score between 0.0 and 1.0. For more details, see Image Attributes.

Note: Zebra strongly recommends updating to the latest models.


Version History

New in v2.3.3

  • Updated default values for Image Attributes:

    Metric Name Current Value New Value
    Image Quality Clear
    (ImageQualityClear)
    0.03 0.02
    Surround Visible
    (ImageTagSurroundVisible)
    0.57 0.71
    People Visible
    (ImageTagPeopleVisible)
    0.12 0.38
    Package Visible
    (ImageTagPackageVisible)
    0.28 0.38

New in v2.2.1

  • Updated default values for Image Attributes:

    Metric Name Current Value New Value
    Image Quality Clear
    (ImageQualityClear)
    0.08 0.03
    Surround Visible
    (ImageTagSurroundVisible)
    0.56 0.57
    People Visible
    (ImageTagPeopleVisible)
    0.55 0.12
    Package Visible
    (ImageTagPackageVisible)
    0.55 0.28

New in v2.1.0

  • Introduced more precise attribute detection and new default values, as detailed in the table below:

    Metric Name Current Value New Value
    Image Quality Clear
    (ImageQualityClear)
    0.06 0.08
    Surround Visible
    (ImageTagSurroundVisible)
    0.59 0.56
    People Visible
    (ImageTagPeopleVisible)
    0.09 0.55
    Package Visible
    (ImageTagPackageVisible)
    0.20 0.55

Requirements

  • License: A Picture Proof of Delivery License (AI Blueprint, Annual) is required. The SKU for this annual license is ZEBRA-AI-BP-PPOD. See Licensing for procurement and deployment instructions.
  • Supported Zebra Devices: Refer to the Zebra support portal for compatible hardware.
  • Operating System: Android 14 or higher. For specific OS versions, refer to the AI Data Capture SDK Release Notes on the Zebra support portal.
  • Minimum SDK Version: AI Data Capture SDK v4.0.0 or later.
  • Memory Requirements: Since running multiple on-device models concurrently is highly resource-intensive, using multiple models within the AI Data Capture SDK is recommended for high-memory devices only.

Resources