Material Flow Sorting With Dual-Resolution Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for sorting and analyzing material flows require separate devices for real-time sorting and non-real-time analysis, leading to high costs, delays, and mechanical complexity due to conflicting requirements for speed and accuracy.
Innovation Solution
A single-stage data processing apparatus with two entities: a first entity for sorting using lower resolution image data and a second entity for analysis using higher resolution data, facilitated by an image data resolution converter and neural networks, allowing simultaneous sorting and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate sorting and analysis systems are used, then sorting speed and analysis accuracy are both maintained, but device complexity and cost increase
Solution Approach 1:
The patent combines sorting and analysis functions into a single integrated system that processes image data through multiple processing entities. The first data processing entity handles sorting decisions while the second entity performs detailed analysis, both operating on the same image stream from a single imaging system, thereby reducing overall system complexity while maintaining both sorting speed and analysis accuracy
Solution Approach 2:
The patent segments the data processing into specialized entities: a first data processing entity for real-time sorting decisions and a second data processing entity for detailed analysis. This segmentation allows each entity to be optimized for its specific function while sharing the same image data source, resolving the contradiction between integrated system efficiency and specialized processing requirements
2Measurement precision
If high resolution image data is processed for sorting, then sorting accuracy is improved, but processing speed decreases
Solution Approach 1:
The patent applies local quality by processing different regions or aspects of image data at different resolution levels. The sorting entity processes data at sufficient resolution for classification decisions, while the analysis entity accesses higher resolution data only when needed for detailed examination, optimizing the balance between processing speed and accuracy
3Productivity
If real-time processing is implemented for sorting, then productivity is improved, but analysis depth is reduced
Solution Approach 1:
The patent implements preliminary action by having the first data processing entity perform sorting decisions in real-time based on initial image processing, while the second data processing entity performs deeper analysis on the same data stream. This allows sorting to proceed at full speed while analysis is conducted in parallel without blocking the primary sorting function
Data Source
AI summary
A data processing apparatus for a sorting apparatus, a method for sorting material and a sorting apparatus are disclosed. The data processing apparatus comprises a first data processing entity configured to operate a sorting application for processing of image data from a source of image data and a second data processing entity configured to operate an analysis application using a neural network for processing said image data from the source of image data, the second data processing entity being configured for processing of higher resolution image data than the first data processing entity. An image data resolution converter is provided to reduce the resolution of said image data from the source of image data prior to processing by the sorting application of the first data processing entity.