EgoCHARM：使用自我中心IMU传感器的资源高效分层活动识别
EgoCHARM: Resource-Efficient Hierarchical Activity Recognition using an Egocentric IMU Sensor
AI总结：
本文提出资源高效的EgoCHARM算法，利用单个头戴IMU和半监督分层学习，以少量参数实现高层级与低层级活动的高F1识别，并可直接部署于IMU芯片。
摘要：
智能眼镜上的人类活动识别（HAR）有多种应用场景，包括健康/健身追踪以及为情境感知AI助手提供输入。然而，当前的自我中心活动识别方法要么性能较低，要么资源密集。在这项工作中，我们引入了一种资源（内存、计算、功耗、样本）高效的机器学习算法EgoCHARM，用于使用单个自我中心（头戴式）惯性测量单元（IMU）识别高层级和低层级活动。我们的分层算法采用半监督学习策略，主要需要高层级活动标签进行训练，以学习可泛化的低层级运动嵌入，这些嵌入可有效用于低层级活动识别。我们在9种高层级和3种低层级活动上评估了我们的方法，在高层级和低层级活动识别上分别达到了0.826和0.855的F1分数，仅使用63k高层级和22k低层级模型参数，使得低层级编码器可以直接部署在具有计算能力的当前IMU芯片上。最后，我们展示了敏感性分析的结果和见解，并强调了使用自我中心IMU进行活动识别的机遇与局限性。
英文摘要：
Human activity recognition (HAR) on smartglasses has various use cases, including health/fitness tracking and input for context-aware AI assistants. However, current approaches for egocentric activity recognition suffer from low performance or are resource-intensive. In this work, we introduce a resource (memory, compute, power, sample) efficient machine learning algorithm, EgoCHARM, for recognizing both high level and low level activities using a single egocentric (head-mounted) Inertial Measurement Unit (IMU). Our hierarchical algorithm employs a semi-supervised learning strategy, requiring primarily high level activity labels for training, to learn generalizable low level motion embeddings that can be effectively utilized for low level activity recognition. We evaluate our method on 9 high level and 3 low level activities achieving 0.826 and 0.855 F1 scores on high level and low level activity recognition respectively, with just 63k high level and 22k low level model parameters, allowing the low level encoder to be deployed directly on current IMU chips with compute. Lastly, we present results and insights from a sensitivity analysis and highlight the opportunities and limitations of activity recognition using egocentric IMUs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
