用多视角图像自动数清堆叠零件，解决工业质检中看不见的计数难题。
Automated Counting of Stacked Objects in Industrial Inspection
- 通过多视角图像重建堆叠3D结构并分析占据率
- 在真实和合成数据上实现高精度计数，即使零件不规则堆叠
- 适合工业质检、仓储管理等需要高通量计数的场景
视觉计数是工业质检中的基础任务，准确高效的库存追踪与质量保证至关重要。由于零件过轻无法靠重量估算，或过重难以安全称重，自动化视觉计数成为更可靠的解决方案。然而，现有方法难以处理容器、托盘或料箱中堆叠的3D物品，因大部分被遮挡，仅少数可见。为此，我们提出一种新型3D计数方法，将任务分解为两个互补子问题：从多视角图像中估计堆叠的3D几何结构及其占据率。结合几何重建与基于深度学习的深度分析，该方法可准确计数容器内相同制造零件，即使堆叠不规则且部分遮挡。我们在大规模合成数据和多样真实世界数据上验证了该3D计数流程，所有总数经人工确认，证明其在真实检测条件下具有鲁棒性。
原文摘要 · Abstract (English)
Visual object counting is a fundamental computer vision task in industrial inspection, where accurate, high-throughput inventory tracking and quality assurance are critical. Moreover, manufactured parts are often too light to reliably deduce their count from their weight, or too heavy to move the stack on a scale safely and practically, making automated visual counting the more robust solution in many scenarios. However, existing methods struggle with stacked 3D items in containers, pallets, or bins, where most objects are heavily occluded and only a few are directly visible. To address this important yet underexplored challenge, we propose a novel 3D counting approach that decomposes the task into two complementary subproblems: estimating the 3D geometry of the stack and its occupancy ratio from multi-view images. By combining geometric reconstruction with deep learning-based depth analysis, our method can accurately count identical manufactured parts inside containers, even when they are irregularly stacked and partially hidden. We validate our 3D counting pipeline on large-scale synthetic and diverse real-world data with manually verified total counts, demonstrating robust performance under realistic inspection conditions.
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。