Object Tracking System Using Image Sensors for Process Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for guiding users through complex processes involving object manipulation are often confusing and lack real-time feedback, making it difficult for users to perform tasks correctly.

Innovation Solution

A system that uses image sensors, such as depth cameras, to track user and object movements, compare them to predefined rules, and provide real-time feedback through augmented reality displays and audio instructions to ensure correct execution of process steps.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If traditional instructions (static diagrams, text, or video) are used to guide users through complex processes, then the instructions can be provided in advance, but the instructions become difficult to understand and follow, and users cannot determine if they are performing the process correctly

Engineering Contradiction:
Improvefeedback informationVSAvoidease of following instructions
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system continuously captures images of the physical scene, identifies objects and operations, compares actual operations to expected operations from process instructions, and provides real-time feedback to the user through a display device. This closed-loop feedback mechanism allows users to immediately determine whether they are performing the process correctly by comparing their actions against the system's analysis and guidance.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces static mechanical instruction methods (diagrams, text, video) with an intelligent system that uses image sensors, object identification algorithms, and real-time processing to dynamically generate and display guidance. This substitution transforms passive instruction delivery into an active, adaptive system that responds to user actions and provides contextualized feedback.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If detailed process instructions are provided to ensure correct execution of each step, then manufacturing precision can be improved, but the complexity of the system increases due to multiple sensors, processing units, and feedback mechanisms

Engineering Contradiction:
Improveprocess execution accuracyVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system employs a multi-functional integrated approach where image sensors serve both to capture the physical scene and to identify objects and operations. The same processing system that identifies objects also compares operations to instructions and generates feedback. This universal system performs multiple functions (detection, identification, comparison, guidance generation) through a unified architecture, reducing overall system complexity compared to separate specialized systems for each function.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system automatically captures images, identifies objects and operations, compares actual operations to expected operations, and generates feedback without requiring external intervention. The self-contained automated process reduces the need for complex external monitoring and control systems, as the system serves itself by autonomously performing the entire guidance workflow from image capture to feedback delivery.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3111297B1Tracking objects during processes
Publication Date: 2020.03.25 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3111297B1 patent drawingFigure 1
  • EP3111297B1 patent drawingFigure 2
  • EP3111297B1 patent drawingFigure 3

AI summary

Embodiments are disclosed that relate to tracking one or more objects during a process that utilizes the objects. For example, one embodiment provides a method for monitoring performance of a process involving one or more objects, wherein the method includes receiving a set of rules defining one or more portions of the process and receiving object identification information regarding the one or more objects. The method further includes, for a selected portion of the process, receiving image information of a physical scene, identifying from the image information and the object identification information an operation performed with an identified object in the physical scene, and taking an action based upon whether the operation satisfies a rule of the set of rules associated with the selected portion of the process.