SpectralWaste Dataset: Multimodal Data for Waste Sorting Automation
This work addresses the lack of labeled data for robust perception systems in waste recycling automation, though it is incremental as it applies existing segmentation methods to a new dataset.
The authors tackled the problem of automating waste sorting by introducing SpectralWaste, the first multimodal dataset from an operational plastic waste facility, and demonstrated that hyperspectral imaging (HSI) combined with RGB improves object segmentation in real-time industrial settings with minimal computational overhead.
The increase in non-biodegradable waste is a worldwide concern. Recycling facilities play a crucial role, but their automation is hindered by the complex characteristics of waste recycling lines like clutter or object deformation. In addition, the lack of publicly available labeled data for these environments makes developing robust perception systems challenging. Our work explores the benefits of multimodal perception for object segmentation in real waste management scenarios. First, we present SpectralWaste, the first dataset collected from an operational plastic waste sorting facility that provides synchronized hyperspectral and conventional RGB images. This dataset contains labels for several categories of objects that commonly appear in sorting plants and need to be detected and separated from the main trash flow for several reasons, such as security in the management line or reuse. Additionally, we propose a pipeline employing different object segmentation architectures and evaluate the alternatives on our dataset, conducting an extensive analysis for both multimodal and unimodal alternatives. Our evaluation pays special attention to efficiency and suitability for real-time processing and demonstrates how HSI can bring a boost to RGB-only perception in these realistic industrial settings without much computational overhead.