Object Detector Model

Overview

Model Name: FCN-ResNet50-object-segmentation

The Image Transform Detector's Object Detector model provides object detection functionality using an FCN-ResNet50 implementation, which has been optimized for efficient execution within the AI Data Capture SDK. It is trained to detect multiple distinct object classes. The underlying implementation is derived from the PyTorch vision library and is licensed under BSD-3-CLAUSE.

Note: Zebra strongly recommends updating to the latest models.

Requirements

• 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.

• 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:

  Features	Platform	Device Model
  Products with DSP Fastest and most battery efficient	QC6490	TC53, TC58, TC73, TC78, ET60, ET65
  	Q-6690	ET401

  For more information on devices based on platform, see Zebra Platform Devices.

• 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

Related Guides

• About
• Setup
• Localizer
  • Models: Barcode, Product & Shelf
• Product Recognition - Model: Model
  • Feature Extractor
  • Feature Storage
  • Recognizer
• Barcode Decoder
• Text OCR
  • Model
• CameraX
  • EntityTrackerAnalyzer
  • Detectors
  • EntityViewfinder
• Image Attributes Detector
• Image Transform Detector
• Entity
• Data Types