20240046481. Physical Object Boundary Detection Techniques and Systems simplified abstract (eBay Inc.)
Contents
Physical Object Boundary Detection Techniques and Systems
Organization Name
Inventor(s)
Patrick Ryan Nelson of San Carlos CA (US)
Jinrong Xie of San Jose CA (US)
Randall Chall Fry of Portland OR (US)
Physical Object Boundary Detection Techniques and Systems - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240046481 titled 'Physical Object Boundary Detection Techniques and Systems
Simplified Explanation
The patent application describes techniques and systems for detecting physical object boundaries using augmented reality and point cloud data. Here is a simplified explanation of the abstract:
- An augmented reality module generates three-dimensional point cloud data that represents depths within a physical environment.
- A physical object boundary detection module filters the point cloud data by removing points corresponding to the ground plane.
- The module performs a nearest neighbor search to locate a subset of points that correspond to the physical object.
- Based on this subset, the module projects the points onto the ground plane to generate a two-dimensional boundary.
- The two-dimensional boundary is then extruded based on the height determined from a point with the maximum distance from the ground plane.
Potential Applications:
- Augmented reality applications for object recognition and tracking.
- Robotics and autonomous systems for object detection and navigation.
- Virtual reality simulations for realistic environment rendering.
Problems Solved:
- Accurate detection and delineation of physical object boundaries in a real-world environment.
- Filtering out irrelevant points corresponding to the ground plane.
- Generating a two-dimensional boundary representation of physical objects.
Benefits:
- Improved object recognition and tracking in augmented reality applications.
- Enhanced navigation and obstacle avoidance for robotics and autonomous systems.
- Realistic rendering of physical objects in virtual reality simulations.
Original Abstract Submitted
physical object boundary detection techniques and systems are described. in one example, an augmented reality module generates three dimensional point cloud data. this data describes depths at respective points within a physical environment that includes the physical object. a physical object boundary detection module is then employed to filter the point cloud data by removing points that correspond to a ground plane. the module then performs a nearest neighbor search to locate a subset of the points within the filtered point cloud data that correspond to the physical object. based on this subset, the module projects the subset of points onto the ground plane to generate a two-dimensional boundary. the two-dimensional boundary is then extruded based on a height determined from a point having a maximum distance from the ground plane from the filtered cloud point data.