Augmented Reality Camera

Capture images and depth data, display object detection bounding boxes, and set location markers in the real world.

Functionality

The Augmented Reality Camera component in the Cloneable platform serves two main functions that enable various augmented reality capabilities. The augmented reality camera has multiple configurations that you can choose from. These configurations determine how the component works.

Image Capture Configuration

This configuration allows you to use the augmented reality camera like a regular camera. You can capture photos while simultaneously collecting real-world depth data. In addition, you can apply object detection and display bounding boxes on top of the camera view. This helps you visualize and obtain information about the detected objects.

Inputs	Outputs
Camera configuration: Choose the image capture mode.	Captured photo: Obtain a photo of the scene.
	Depth data: Retrieve the underlying depth information of the captured scene.

Location Marker Configuration

With this configuration, you can input a specific location or define a fixed location marker in the real world. The augmented reality camera will provide visual cues to help you navigate to that location. The marker's size varies based on the distance, appearing smaller when far away and larger when closer. Additionally, a mini-map may display the general direction and distance of the marker at the top of the screen.

Inputs	Outputs
Camera configuration: Select the location marker mode.	Visual cues: Receive on-screen cues, such as a marker and a mini-map, guiding you towards the specified location.
Location information: Input the desired location or set a fixed marker.

The Augmented Reality Camera component offers these two configurations currently, but additional configurations may be added in the future. These configurations allow users to perform various specialized tasks and explore augmented reality possibilities within the Cloneable platform.