Open World Object Detection

Overview

The Open World Object Detection plugin allows you to detect a great variety of objects on image files in your project. The plugin will draw a bounding box around each object type it can find, and it will write the type of object in a nested text classification in the box itself.

Plugin Functionality

The Open World Object Detection Plugin automatically detects objects in images using a open world object detection model. It draws bounding boxes, and provides confidence scores, making it easy to annotate existing categories while flagging new or unexpected objects for review.

The plugin will create unknown bounding boxes not belonging to any class.

Supported Data Types

• Image

Supported Annotation Tools

• Bounding Box

Plugin Configuration

The Overwrite setting in model plugins controls whether existing annotations are replaced or kept. When enabled, the plugin replaces all existing annotations with new model predictions; when disabled, it simply adds the new results without deleting what’s already there.

YOLO | Open World Object Detection plugin integration to the workflow

You may vary a number of settings related to your export from the Config JSON field. Each option is detailed below:

{
  "threshold": 0.3
}

• "threshold": The confidence score threshold for object detection. Detections with a confidence score below this value will be filtered out. A higher threshold reduces false positives but may miss low-confidence detections.

  • Example:

    • "threshold": 0.3

Detection Classes

The following are the classes of objects this plugin will detect:

10KB

class_names.txt

Open