针对杂乱场景中垃圾物体分割难题，提出融合边界信息的COSNet模型。
COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes
- 引入特征锐化与边界增强模块，强化不规则垃圾的边缘特征
- 在ZeroWaste-f和SpectralWaste数据集上分别提升1.8%和2.1% mIoU
- 特别适用于材质复杂、透明塑料多的垃圾分拣场景
自动化垃圾分类旨在通过视觉系统高效分离可回收物。然而，形状多样、材质各异的物体在杂乱环境中使分割任务极具挑战性，尤其透明塑料进一步增加难度。现有方法虽在标准语义分割数据集表现良好，但在实际垃圾场景中性能下降。为此，本文提出COSNet，通过融合多尺度上下文信息与边界线索，精准分割杂乱场景中的垃圾物体。模型引入特征锐化块（FSB）和边界增强模块（BEM），有效增强特征表达并突出不规则物体的边界。在ZeroWaste-f、SpectralWaste和ADE20K三个挑战性数据集上的实验表明，所提方法显著有效：在ZeroWaste-f上mIoU提升1.8%，在SpectralWaste上提升2.1%。
原文摘要 · Abstract (English)
Automated waste recycling aims to efficiently separate the recyclable objects from the waste by employing vision-based systems. However, the presence of varying shaped objects having different material types makes it a challenging problem, especially in cluttered environments. Existing segmentation methods perform reasonably on many semantic segmentation datasets by employing multi-contextual representations, however, their performance is degraded when utilized for waste object segmentation in cluttered scenarios. In addition, plastic objects further increase the complexity of the problem due to their translucent nature. To address these limitations, we introduce an efficacious segmentation network, named COSNet, that uses boundary cues along with multi-contextual information to accurately segment the objects in cluttered scenes. COSNet introduces novel components including feature sharpening block (FSB) and boundary enhancement module (BEM) for enhancing the features and highlighting the boundary information of irregular waste objects in cluttered environment. Extensive experiments on three challenging datasets including ZeroWaste-f, SpectralWaste, and ADE20K demonstrate the effectiveness of the proposed method. Our COSNet achieves a significant gain of 1.8% on ZeroWaste-f and 2.1% on SpectralWaste datasets respectively in terms of mIoU metric.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。