Object detection and anchor position and orientation resolution for augmented reality (ar) applications

A method, comprising:

• identifying features associated with a real-world object in a video feed during an augmented reality (AR) session initiation within a physical environment that includes the real-world object;
• maintaining coordinates for the features within the video feed;
• maintaining dimensions of the features based on a model comprising dimensions of the real-world object;
• and
• estimating a position and orientation of the real-world object depicted in the video feed based on the coordinates and dimensions.

A method, comprising:

• receiving a video feed of a physical environment during an augmented reality (AR) session that is initiation;
• obtaining a model for a real-world object located within the physical environment;
• detecting features of the real-world object from the video feed;
• mapping screen positions of the features to model dimensions;
• and
• resolving a pose of the real-world object within the video feed based on the mapping.

A system, comprising:

• a cloud comprising at least one processor and a non-transitory computer-readable storage medium;
• the non-transitory computer-readable storage medium comprising executable instructions;
• the executable instructions when executed by the at least one processor from the non-transitory computer-readable storage medium cause the at least one processor to perform operations comprising:
• maintaining a model for a real-world object;
• providing an application programming interface (API) to an augmented reality (AR) application;
• and
• interacting with an AR application through the API to provide AR session initialization and AR session tracking from a video feed based on detected features in the video feed for the real-world object located within a physical environment during an AR session.