Conveyor Object Tracking for Bulk Sorting Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing bulk sorting systems using linear imaging sensors struggle with accurately predicting the position of uncooperative bulk goods, such as peas or rounded granules, due to their geometry and movement relative to the conveyor belt, leading to incorrect ejection of both bad and good materials.

Innovation Solution

A conveyor system that uses image processing and object tracking to determine the movement path of individual objects, allowing for precise prediction of their future location by employing motion models and multiple position determinations at different times, enabling accurate sorting even for uncooperative materials.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If linear imaging sensors are used for image acquisition on the conveyor belt, then automatic sorting of bulk goods becomes possible, but accurate prediction of object position fails for uncooperative bulk goods due to their inherent movement relative to the belt

Engineering Contradiction:
Improveautomatic sortingVSAvoidobject position prediction
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The system transitions from assuming static object positions on the conveyor belt to dynamically tracking object movements through multiple image acquisitions. By capturing images at different time points and calculating actual displacement, the system adapts to the dynamic behavior of uncooperative bulk goods that move independently of the belt

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary tracking and prediction of object positions before the actual sorting decision is made. By acquiring multiple images in advance and calculating predicted positions at the moment of ejection, the system prepares the accurate position data needed for precise sorting operation

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If the blow-out unit is spatially separated from the line-of-sight camera to enable correct ejection, then ejection can be performed, but the observation time cannot coincide with the ejection time requiring estimation

Engineering Contradiction:
Improveejection capabilityVSAvoidtime estimation delay
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary tracking of object positions during the time between observation and ejection. By continuously monitoring object movement in multiple images and extrapolating the trajectory, the system predicts where the object will be at the moment of ejection, compensating for the time delay caused by spatial separation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from multiple image acquisitions to continuously update the predicted object position. By comparing actual positions across time points with predicted positions, the system refines its trajectory calculation to improve accuracy at the ejection moment

Inventive Principle:
Principle #23Feedback

3Device complexity

If constant linear motion assumption is used for bulk material, then simple prediction calculation is possible, but prediction accuracy deteriorates for uncooperative bulk goods with additional inherent movement

Engineering Contradiction:
Improveprediction calculationVSAvoidposition prediction accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system replaces the static constant velocity assumption with dynamic motion tracking. By measuring actual displacement between multiple image acquisitions and updating the velocity calculation accordingly, the system captures the true motion behavior of uncooperative bulk goods including their inherent movement relative to the belt

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system adds the time dimension to position measurement by acquiring images at multiple time points. This temporal dimension allows calculation of actual velocity and acceleration, transforming the prediction from a simple linear extrapolation to a more accurate motion model that accounts for changing velocities

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

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 allows for high-precision prediction and sorting of uncooperative bulk objects, reducing mechanical effort and enabling the sorting of previously unsortable materials, while also optimizing the separation of good and bad fractions with reduced energy consumption.

Implementation Method 1

the spatial position of optically recorded individual objects in the material flow can be determined at several different points in time by means of image processing

Methodology Applied
Scientific EffectImage processing: Image Processing

Data Source

PatentEP3122479B1Conveyor system, device for sorting bulk material using such a con conveyor system, and method for transporting
Publication Date: 2018.04.11 FRAUNHOFER GESELLSCHAFT ZUR FORDERUNG DER ANGEWANDTEN FORSCHUNG EV
  • EP3122479B1 patent drawingFigure 1
  • EP3122479B1 patent drawingFigure 2
  • EP3122479B1 patent drawingFigure 3

AI summary

The invention relates to a conveying system for transporting a material stream (M) comprising a plurality of individual objects (O1, O2,...), characterised in that, using the conveying system and by optically detecting individual objects (O1, O2,...) in the material stream (M), the respective local positions (x(t), y(t)) of these objects (O1, O2,...) are determined at several different times (t-4, t-3,...), and on the basis of the local positions (x(t), y(t)) determined for these objects (O1, O2,...) at the different times (t-4, t-3,...), it is possible to calculate their respective position (xb(tb), yb(tb)) at at least one defined time (tb) after the respective latest time of the different times (t-4, t-3,...).