An Ensemble Learning Approach towards Waste Segmentation in Cluttered Environment
Maimoona Jafar, Syed Imran Ali, Ahsan Saadat, Muhammad Bilal, Shah Khalid
TL;DR
Waste segmentation in cluttered conveyor-belt scenes at Material Recovery Facilities is challenging due to deformities and occlusions. The authors propose an ensemble EL-4 that fuses U-Net and FPN predictions with EfficientNet backbones to enhance pixel-wise waste segmentation on the ZeroWaste-f dataset. Baseline evaluation of seven segmentation models shows U-Net achieves the highest IoU among single models while FPN minimizes Dice Loss, motivating a combined approach. The EL-4 ensemble achieves substantial gains (IoU up to $IoU=0.8306$, Dice Loss down to $Dice\ Loss=0.09019$), indicating improved accuracy and generalization with potential to increase sorting throughput and reduce human intervention at MRFs.
Abstract
Environmental pollution is a critical global issue, with recycling emerging as one of the most viable solutions. This study focuses on waste segregation, a crucial step in recycling processes to obtain raw material. Recent advancements in computer vision have significantly contributed to waste classification and recognition. In waste segregation, segmentation masks are essential for robots to accurately localize and pick objects from conveyor belts. The complexity of real-world waste environments, characterized by deformed items without specific patterns and overlapping objects, further complicates waste segmentation tasks. This paper proposes an Ensemble Learning approach to improve segmentation accuracy by combining high performing segmentation models, U-Net and FPN, using a weighted average method. U-Net excels in capturing fine details and boundaries in segmentation tasks, while FPN effectively handles scale variation and context in complex environments, and their combined masks result in more precise predictions. The dataset used closely mimics real-life waste scenarios, and preprocessing techniques were applied to enhance feature learning for deep learning segmentation models. The ensemble model, referred to as EL-4, achieved an IoU value of 0.8306, an improvement over U-Net's 0.8065, and reduced Dice loss to 0.09019 from FPN's 0.1183. This study could contribute to the efficiency of waste sorting at Material Recovery Facility, facilitating better raw material acquisition for recycling with minimal human intervention and enhancing the overall throughput.