3D Sensor Segmentation of Planar Objects Using Transparent Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotics systems face challenges in detecting and segmenting planar objects with unknown or novel appearances, particularly in dynamic environments, due to similarities between the objects and their supporting surfaces, and are complicated by ambient lighting conditions and shades.
Innovation Solution
The use of a three-dimensional (3D) sensor system that includes a reflective or transparent surface to support planar objects, allowing the sensor to detect the object without detecting the surface, and employing depth maps and edge detection algorithms to accurately segment and estimate the pose of the object.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If a sensor detects planar objects on a supporting surface, then object detection is enabled, but the surface is also detected creating segmentation difficulty
Solution Approach 1:
A transparent support surface acts as an intermediary between the planar object and the sensor. The surface allows sensor signals to pass through while supporting the object, enabling the sensor to detect only the object without detecting the surface itself. This mediator resolves the conflict between needing surface support and avoiding surface detection interference.
2Measurement precision
If complex surface engineering is used to distinguish objects from surfaces, then detection accuracy improves, but system complexity and cost increase
Solution Approach 1:
The patent uses a simple, inexpensive transparent surface (such as clear acrylic or glass) instead of complex engineered surfaces. This disposable-like approach with basic transparent materials achieves the detection goal without requiring sophisticated surface treatments, patterns, or materials, thereby reducing system complexity and cost while maintaining detection accuracy.
Solution Approach 2:
The invention changes the optical parameter of the support surface by making it transparent. This parameter change allows the sensor to see through the surface to detect the object, eliminating the need for complex surface engineering while improving detection accuracy. The transparency parameter resolves the detection challenge simply.
3Reliability
If ambient lighting conditions vary, then detection robustness decreases, but adding lighting control increases system complexity
Solution Approach 1:
The patent replaces complex mechanical lighting control systems with an optical solution using a transparent surface. The transparent surface consistently transmits light regardless of ambient conditions, providing inherent lighting invariance. This substitution of optical design for mechanical lighting control achieves detection robustness without increasing system complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables robust detection and segmentation of planar objects with unknown appearances, reducing the complexity of image processing and eliminating the need for complex surface engineering, thereby simplifying pose estimation and reducing engineering costs and computing overhead.
Implementation Method 1
the first surface can be configured to allow light to pass through the first surface such that the first surface defines a transparent surface
Implementation Method 2
the first surface is configured to reflect light such that the first surface defines a reflective surface
Data Source
AI summary
Robots might interact with planar objects (e.g., garments) for process automation, quality control, to perform sewing operations, or the like. It is recognized herein that robots interacting with such planar objects can pose particular problems, for instance problems related to detecting the planar object and estimating the pose of the detected planar object. A system can be configured to detect or segment planar objects, such as garments. The system can include a three-dimensional (3D) sensor positioned to detect a planar object along a transverse direction. The system can further include a first surface that supports the planar object. The first surface can be positioned such that the planar object is disposed between the first surface and the 3D sensor along the transverse direction. In various examples, the 3D sensor is configured to detect the planar object without detecting the first surface.