Information-Client Server for Deterministic Plastic Waste Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing recycling technologies struggle with the inefficiency and inaccuracy of identifying plastic waste, particularly in mixed and contaminated streams, leading to low recycling rates and economic barriers, as they rely on probabilistic methods that fail to determine the precise material type and history of plastics, limiting their recyclability and market value.
Innovation Solution
A platform-based system combining deterministic and probabilistic identification methods, using a SpectraTopo Camera Module (STCM) to accurately identify materials at a fine level of granularity, incorporating digital watermarking and GTIN encoding, with an information-client server architecture to manage and distribute this data to various clients.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If probabilistic identification methods (near infrared, hyperspectral) are used to identify plastic materials, then identification speed is improved, but measurement precision deteriorates because these methods cannot deterministically determine precise material type and history
Solution Approach 1:
The identification process is segmented into multiple stages: initial probabilistic identification using near-infrared and hyperspectral imaging for rapid sorting, followed by deterministic verification using digital watermarking and GTIN code reading for precise material type and history determination. This segmentation allows the system to benefit from both fast probabilistic screening and accurate deterministic verification.
Solution Approach 2:
Digital watermarking technology serves as an intermediary that bridges the gap between probabilistic optical identification and deterministic material verification. The watermark embedded in the plastic packaging contains precise material information that validates and supplements the probabilistic identification results, enabling accurate material type and history determination while maintaining high identification speed.
2Measurement precision
If careful presorting is required at materials recovery facilities, then measurement precision of material identification is improved, but device complexity and labor requirements worsen
Solution Approach 1:
The system employs self-service identification where plastic packaging automatically presents its digital watermark and GTIN code to the scanning system during conveyor belt transport. The embedded digital identifiers autonomously provide material identification information without requiring manual inspection or complex sorting infrastructure, thereby maintaining high sorting accuracy while reducing device complexity and labor requirements.
Solution Approach 2:
Digital watermarking and GTIN encoding are applied to plastic packaging during the manufacturing process, before the packaging enters the recycling stream. This preliminary action ensures that material identification information is already embedded and ready for rapid retrieval at materials recovery facilities, eliminating the need for complex real-time analysis and simplifying the sorting system architecture.
3Ease of operation
If probabilistic identification methods are used, then ease of operation is improved, but reliability deteriorates because many plastic classes remain unidentified and are burned as refuse
Solution Approach 1:
The system dynamically adapts its identification approach by first attempting rapid probabilistic identification and then automatically verifying ambiguous cases using deterministic digital watermarking and GTIN reading. This dynamic strategy maintains ease of operation for clearly identifiable materials while ensuring high reliability for ambiguous or contaminated items, preventing misidentification and ensuring proper recycling of all plastic classes.
Solution Approach 2:
The system incorporates feedback loops where digital watermark and GTIN code verification results feed back into the identification process to confirm or correct probabilistic identification outcomes. This feedback mechanism ensures high reliability by validating material identification through multiple independent verification channels, while the automated nature of the feedback maintains ease of operation without requiring manual intervention.
Data Source
AI summary
Items are identified in a waste stream for purposes of recycling, using deterministic and/or probabilistic techniques. Imagery of the waste stream from multiple viewpoints permit creation of a 3D depth draped image representation, from which one or more 2D planes can be synthesized. Phase-coherent patches of recoverable encoded data can be identified from among soiled and crumpled object surfaces, and used in combination to recover object identification information. Recognition of certain items can trigger further image processing that is specific to such items. (Detection of a catsup bottle, for example, can trigger image analysis to discern the presence of catsup residue.) Information about recognized objects can be provided to external data customers, e.g., to track grey market diversion of particular products into unlicensed territories. These and other features and advantages, which can be used alone or in combination, are detailed herein.