arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.10541cs.LGeess.SP
收藏

在具有低分辨率红外传感器和CNN的微控制器上进行隐私保护社交距离监控

Privacy-preserving Social Distance Monitoring on Microcontrollers with Low-Resolution Infrared Sensors and CNNs

Politecnico di Torino(都灵理工大学);STMicroelectronics(意法半导体)

Chen Xie, Francesco Daghero, Yukai Chen, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

摘要:

低分辨率红外(IR)阵列传感器为光学相机和智能手机/可穿戴设备提供了一种低成本、低功耗和隐私保护的替代方案,用于室内空间的社交距离监控,允许识别基本形状,而不会泄露个人的个人细节。在这项工作中,我们证明了一个准确的检测社会距离违规可以实现处理的原始输出的8 × 8红外阵列传感器与一个小尺寸的卷积神经网络(CNN)。此外,CNN可以直接在基于微控制器(MCU)的传感器节点上执行。通过对新收集的开放数据集的结果,我们表明,我们最好的CNN达到了86.3%的平衡准确率,显著优于最先进的确定性算法所达到的61%。改变CNN的结构参数,我们获得了丰富的Pareto模型集,精度为70.5-86.3%,参数为0.18- 75 k。部署在STM32 L476 RG MCU上,这些模型的延迟为0.73-5.33ms,每次推理的能耗为9.38-68.57μJ。

英文摘要:

Low-resolution infrared (IR) array sensors offer a low-cost, low-power, and privacy-preserving alternative to optical cameras and smartphones/wearables for social distance monitoring in indoor spaces, permitting the recognition of basic shapes, without revealing the personal details of individuals. In this work, we demonstrate that an accurate detection of social distance violations can be achieved processing the raw output of a 8x8 IR array sensor with a small-sized Convolutional Neural Network (CNN). Furthermore, the CNN can be executed directly on a Microcontroller (MCU)-based sensor node. With results on a newly collected open dataset, we show that our best CNN achieves 86.3% balanced accuracy, significantly outperforming the 61% achieved by a state-of-the-art deterministic algorithm. Changing the architectural parameters of the CNN, we obtain a rich Pareto set of models, spanning 70.5-86.3% accuracy and 0.18-75k parameters. Deployed on a STM32L476RG MCU, these models have a latency of 0.73-5.33ms, with an energy consumption per inference of 9.38-68.57μJ.

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。

↑