Structured-Light Hand-Eye Camera With ROI Depth Sensing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robotic systems face computational inefficiencies and light interference issues when using structured light to determine the position and depth of objects within a large field of view, leading to increased power requirements and potential eye injuries.

Innovation Solution

A robotic system that projects structured light only onto a determined region of interest within the field of view, reducing computational analysis and light interference by using a control system to identify and illuminate a specific area, allowing for faster and more precise depth determination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If structured light is projected onto the entire field of view to aid depth sensing, then the robot can determine object locations across the full scene, but computational time and processing power increase significantly

Engineering Contradiction:
Improvefield of view coverageVSAvoidcomputational time
Core Design Contradiction:
Area of stationary objectVSLoss of time

Solution Approach 1:

The patent divides the field of view into multiple regions of interest (ROIs) and processes only those specific areas rather than the entire scene. This segmentation allows the system to maintain comprehensive monitoring capability while reducing computational burden by focusing processing resources on relevant portions of the scene.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies different processing quality levels to different regions of the field of view. High-depth-precision regions receive full structured light processing, while other areas use reduced processing, optimizing the balance between computational efficiency and measurement accuracy where it matters most.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If structured light is projected onto the entire field of view, then depth sensing is enhanced, but power consumption increases

Engineering Contradiction:
Improvedepth sensing accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the field of view into regions requiring depth sensing and those that do not, projecting structured light only onto the necessary regions. This reduces overall power consumption while maintaining depth sensing accuracy where required.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies structured light illumination partially rather than fully across the entire field of view, using just enough light projection to achieve the required depth measurement precision in critical areas without wasting energy on unnecessary regions.

Inventive Principle:
Principle #16Partial or excessive action

3Area of stationary object

If structured light is projected onto the entire field of view, then complete scene coverage is achieved, but light reflection interference increases

Engineering Contradiction:
Improvescene coverageVSAvoidlight reflection interference
Core Design Contradiction:
Area of stationary objectVSObject-generated harmful factors

Solution Approach 1:

The patent divides the scene into regions of interest and processes only those areas with structured light, minimizing the total light projection area. This reduces light reflection interference from non-critical areas while maintaining complete scene coverage through selective processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system extracts and processes only the relevant portions of the scene that contain objects of interest, removing unnecessary light projection from areas without target objects. This eliminates sources of light reflection interference while preserving the ability to monitor the entire scene.

Inventive Principle:
Principle #2Taking out (Extraction)

4Adaptability or versatility

If structured light is projected onto the entire field of view, then all objects are detectable, but system complexity increases

Engineering Contradiction:
Improveobject detection capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a multi-stage processing system that segments the field of view into regions of interest, reducing the complexity of depth calculation by limiting structured light processing to specific areas rather than the entire scene, while maintaining the ability to detect all objects.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary processing to identify regions of interest before applying structured light depth sensing. This preliminary action simplifies the overall system complexity by pre-filtering the scene and preparing only the necessary regions for detailed depth analysis.

Inventive Principle:
Principle #10Preliminary action

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 reduces computational time, minimizes light reflection interference, and enhances safety by focusing analysis on a smaller area, thereby improving the speed and accuracy of robotic tasks while reducing power consumption and preventing eye injuries.

Implementation Method 1

a light system for projecting structured light onto an object located within the region of interest

Methodology Applied
Scientific EffectStructured light projection: Light

Data Source

PatentUS11040452B2Depth sensing robotic hand-eye camera using structured light
Publication Date: 2021.06.22 ABB (SCHWEIZ) AG
  • US11040452B2 patent drawing
  • US11040452B2 patent drawing
  • US11040452B2 patent drawing

AI summary

The disclosed system includes a robot configured to perform a task on a workpiece. A camera having a field of view is operably connected to the robot. A light system is configured to project structured light onto a region of interest having a smaller area within the field of view. A control system is operably coupled to the robot and the camera is configured to determine a depth of the workpiece relative to a position of the robot using the structured light projected onto the workpiece within the region of interest.