轻量级网络提升移动机器人对细长物体的分割精度
ASC-SW: A Lightweight Atrous Strip Convolution Network for DLOs Segmentation on Edge mobile Robots
- 用空洞条状卷积捕捉细长结构，计算开销低
- 在真实机器人数据上达74.1% mIoU，推理速度261 FPS
- 适合资源受限的边缘移动机器人部署
检测可变形线状物体（如地板电缆）对移动机器人安全导航至关重要，但因视角倾斜、结构细长及边缘设备资源有限而面临挑战。现有方法多针对固定俯视视角的机械臂平台设计，模型庞大，难以部署于移动机器人。本文提出跨视角DLO分割问题，要求在机械臂视角数据上训练的模型能泛化至移动机器人视角。为此，我们提出ASC-SW轻量级几何感知分割框架。核心网络ASCNet引入空洞条状卷积，结合方向性条状滤波与空洞感受野，在低计算成本下增强对细长结构的敏感性；设计空洞条状卷积空间金字塔池化模块实现多尺度各向异性特征聚合；并采用时间滑动窗口优化抑制视角带来的误检。在真实移动机器人数据上评估，ASC-SW达到74.1% mIoU，推理速度261 FPS，可在边缘设备上部署。
原文摘要 · Abstract (English)
Detecting deformable linear objects (DLOs), such as floor cables, is essential for safe mobile robot navigation but remains challenging due to oblique viewpoints, thin structures, and limited edge-device resources. Existing DLO segmentation methods are primarily designed for manipulator platforms with fixed top-down views and often require heavy models, limiting their deployment on mobile robots. We formulate a cross-view DLO segmentation problem, where models trained on manipulator-view data must generalize to mobile robot perspectives. To address this, we propose ASC-SW, a lightweight and geometry-aware segmentation framework. The core network, ASCNet, introduces Atrous Strip Convolution, combining directional strip filtering with dilated receptive fields to enhance sensitivity to elongated structures at low computational cost. An Atrous Strip Convolution Spatial Pyramid Pooling module enables multi-scale anisotropic feature aggregation, while a temporal Sliding Window refinement suppresses viewpoint-induced false positives. Evaluated on real-world mobile robot data, ASC-SW achieves 74.1% mIoU at 261 FPS and remains deployable on edge devices.
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。