MWIR-4-Plastic：用中波红外高光谱成像与机器学习识别复杂的报废工业塑料
MWIR-4-Plastic: The Identification of Complex End-of-Life Industrial Plastic using Mid-wave Infrared Hyperspectral Imaging and Machine Learning
浏览论文内容
中文总结 AI 辅助
本研究针对报废工业黑色塑料分拣难题，构建首个公开粉碎黑色塑料高光谱数据集，开发多模态光谱-空间框架，结合高光谱Transformer与化学计量学波段选择，建立含9种方法的综合基准。
中文摘要 AI 辅助
从报废（EOF）工业废料中自动分拣粉碎后的黑色塑料，对回收设施而言是一项重大挑战，主要源于现有传感与分析方法的局限。现有研究主要依赖单点接触式中红外光谱或实验室高光谱成像（HSI）装置，无法提供快速批量处理所需的空间分辨率分析；且现有数据集为实验室控制环境下构建，聚焦完整塑料而非粉碎塑料，阻碍了回收工艺的进一步优化。黑色工业塑料的相关研究尤为不足，多数分类流程依赖手动区域选择与基于规则的光谱匹配，忽略了空间信息与现代深度学习（DL）方法。为解决这些缺口，我们推出首个公开可用的报废车辆粉碎黑色塑料高光谱数据集，包含4种工业聚合物，涉及13个配准的RGB、VNIR、SWIR及MWIR场景，并提供其分割流程。我们开发了多模态光谱-空间框架，整合前景隔离、像素级分类与对象级多数投票；通过适配地球观测领域的先进高光谱Transformer并结合化学计量学波段选择，实现复杂黑色塑料的精准分类。本研究构建了首个包含9种处理方法（涵盖化学计量学、机器学习与DL架构）的综合基准；为确保可复现性，完整数据集与方法已公开，为工业检测中的高光谱对象分析流程建立了基准。
英文摘要
The automated sorting of shredded black plastics from end-of-life (EOF) industrial waste presents a significant challenge in recycling facilities, primarily due to the limitations of current sensing and analytical approaches. Existing studies predominantly rely on single-point contact-based mid-infrared spectroscopy or laboratory hyperspectral imaging (HSI) setups, which fail to provide the spatially resolved analysis necessary for fast, bulk processing. Moreover, available datasets are laboratory-controlled and focus on intact rather than shredded plastics, hindering further recycling refinement. Black industrial plastics, in particular, are underrepresented, while most classification pipelines depend on manual region selection and rule-based spectral matching, neglecting spatial information and modern deep learning (DL) methods. To address these gaps, we introduce the first publicly available HSI dataset of shredded black plastics from EOF vehicle, comprising four industrial polymers across 13 co-registered RGB, VNIR, SWIR, and MWIR scenes and their segmentation pipeline. We developed a multi-modal spectral-spatial framework that integrates foreground isolation, pixel-wise classification, and object-level majority voting. By adapting advanced hyperspectral transformers from earth observation and incorporating chemometric band selection, we achieve accurate classification of complex black plastics. The study establishes the first comprehensive benchmark using nine processing methods, including chemometric, machine learning, and DL architectures. To ensure reproducibility, the complete dataset and methodologies are publicly released, establishing a benchmark for a hyperspectral object-analysis pipeline in industrial inspection.
发表机构
- Helmholtz-Zentrum Dresden-Rossendorf (HZDR)（德累斯顿-罗森多夫亥姆霍兹中心）
- Helmholtz Institute Freiberg for Resource Technology (HIF)（弗莱贝格亥姆霍兹资源技术研究所）
- University of Antwerp（安特卫普大学）
- Freie Universität Berlin（柏林自由大学）
- University of Iceland（冰岛大学）
- TU Bergakademie Freiberg（弗莱贝格工业大学）
机构由 AI 辅助整理，请以论文原文为准。
