3D ROI to 2D ROI

Description

This operator is used to project a Region of Interest defined in 3D space (3D ROI) onto the camera’s 2D image plane, thereby obtaining a corresponding 2D Region of Interest (2D ROI).

Overview

Projects visible corners of 3D ROIs into 2D image ROIs.

Scenarios

  • 3D and 2D Linkage: After determining an analysis region in the 3D point cloud (for example, via the "Dynamic ROI Generation" operator), this operator can be used to find the exact same region on the original 2D color or grayscale image for subsequent 2D image processing.

  • Visualization and Debugging: On the user interface, the highlighted 3D ROI and its corresponding 2D ROI can be displayed simultaneously, making it convenient for users to intuitively understand the mapping relationship between the 3D spatial region and 2D image pixels.

Inputs and Outputs

Inputs

3D ROI: 3D ROI in the format [{"min": [min_x, min_y, min_z], "max": [max_x, max_y, max_z], "transform": cam2ROIFrame}].

Camera parameters: Camera intrinsics, distortion, color-camera, and passive-stereo parameters.

Image (Optional): Color image used to determine image size.

Outputs

2D ROI: A list composed of one or more 2D ROIs.

Parameters

Image Source

Description

Selects which camera calibration is used for projection or reconstruction. Auto infers it from the input image where supported.

Tuning Instructions

Use Auto when an image is available and identification is reliable; otherwise choose the camera to which the pixels, depth, or desired projection belong.

Parameter Range

Options: Auto, Texture camera, depth camera, Default: Auto

Parameter Range

Values/Range:

  • Auto

  • Texture Camera

  • Depth Camera

Default: Auto