发表机构
University of Genoa; DITEN（热那亚大学; DITEN（热那亚大学电子、电信和工程系））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对嵌入式设备RGB-D相机的affordance分割，提出硬件感知神经架构搜索与专用微调方法，生成平衡泛化性能和硬件需求的帕累托最优解，原型在Jetson Nano上实现实时性能。
AI 中文摘要
深度传感器有潜力补充RGB数据用于可穿戴机器人的 affordance 分割，但目前其应用仍未得到充分探索。本文提出两种方法：一是重新设计硬件感知神经架构搜索，赋予其新的搜索空间以将深度（D）信息集成到小型深度网络中；二是专用微调方法，包含预处理层以融合深度信息与RGB数据，使其适配传统架构。两种方法均旨在生成可受益于现代（便携式）硬件加速器的解决方案，克服现有微型方法因支持硬件的严格约束而无法处理关键场景的问题。在一对真实世界数据集上开展的大量实验表明，与现有方案相比，所提方法具有有效性。该方法在多数情况下可生成识别帕累托最优前沿的解决方案，以平衡泛化性能与硬件需求。本文还描述了配套原型，包括Jetson Nano开发板与RealSense RGB-D相机。考虑设备的能耗特性，整个系统可在与智能手机等标准电池兼容的能耗预算内达到实时性能。
英文摘要
While depth sensors have the potential to complement RGB data for affordance segmentation in wearable robots, their usage seems to remain underexplored. The paper proposes two approaches: a reformulated version of hardware-aware neural architecture search, endowed with a newly designed search space to integrate depth (D) information into small-sized deep networks, and a dedicated fine-tuning approach, including a preprocessing layer to merge depth information with RGB data and make it compatible with conventional architectures. In both cases, those methods aim to generate solutions that benefit from modern (portable) hardware accelerators and overcome existing tiny-like approaches, which often fail to tackle critical scenarios due to the severe constraints set by the supporting hardware. Extensive experiments on a pair of real-world datasets demonstrate the effectiveness of the proposed method as compared with existing solutions. The approach presented in the paper generates, in most cases, solutions that identify the Pareto optimal front to balance generalization performance and hardware requirements. The paper also describes the supporting prototype, including a Jetson Nano board and a RealSense RGB-D camera. When considering the energy profile of the device, the overall system can attain real-time performances within an energy budget that is compatible with standard batteries, such as those used in smartphones.
Journal refIEEE Internet of Things Journal, vol. 12, no. 21, pp. 44492-44501, 2025
