Robust non-intrusive interpretation of occupant thermal comfort in built environments with low-cost networked thermal cameras
Robust non-intrusive interpretation of occupant thermal comfort in built environments with low-cost networked thermal cameras
复制标题
DOI：
10.1016/j.apenergy.2019.113336
复制
发表时间：
2019-10-01
期刊：
影响因子：
11.2
通讯作者：
Kamat, Vineet R.
中科院分区：
文献类型：
--
作者：
Li, Da;Menassa, Carol C.;Kamat, Vineet R.
全球约40%的能源消耗在建筑物内，主要用于为居住者提供舒适的工作和生活空间。然而，尽管此类能源消耗对环境产生重大影响，但居住者缺乏热舒适性是一个常见问题，可能导致健康并发症和生产力下降。为了解决这个问题，实时了解居住者的热舒适性以动态地控制环境是特别重要的。本研究利用红外线热感摄影机网路来撷取皮肤温度特徴，并预测使用者在不同距离与角度下的热偏好。这项研究在两个方面区别于现有的方法：（1）所提出的方法是一种非侵入式数据收集方法，不需要人类参与或个人设备;（2）它使用低成本的热成像相机和RGB-D传感器，可以快速重新配置以适应各种设置，并且很少或没有硬件基础设施的依赖性。建议的摄像机网络进行了验证，使用面部皮肤温度收集16个科目在多占用实验。结果表明，所有16名受试者都观察到随着室温升高，皮肤温度在统计学上更高。皮肤温度的变化也对应于受试者报告的不同舒适状态。实验后评估表明，联网的热成像摄像机对建筑物占用者的干扰最小。所提出的方法展示了将人体生理数据收集从侵入式和基于可穿戴设备的方法转变为真正非侵入式和可扩展的方法的潜力。
About 40% of the energy produced globally is consumed within buildings, primarily for providing occupants with comfortable work and living spaces. However, despite the significant impacts of such energy consumption on the environment, the lack of thermal comfort among occupants is a common problem that can lead to health complications and reduced productivity. To address this problem, it is particularly important to understand occupants' thermal comfort in real-time to dynamically control the environment. This study investigates an infrared thermal camera network to extract skin temperature features and predict occupants' thermal preferences at flexible distances and angles. This study distinguishes from existing methods in two ways: (1) the proposed method is a non-intrusive data collection approach which does not require human participation or personal devices; (2) it uses low-cost thermal cameras and RGB-D sensors which can be rapidly reconfigured to adapt to various settings and has little or no hardware infrastructure dependency. The proposed camera network is verified using the facial skin temperature collected from 16 subjects in a multi-occupancy experiment. The results show that all 16 subjects observed a statistically higher skin temperature as the room temperature increases. The variations in skin temperature also correspond to the distinct comfort states reported by the subjects. The post-experiment evaluation suggests that the networked thermal cameras have a minimal interruption of building occupants. The proposed approach demonstrates the potential to transition the human physiological data collection from an intrusive and wearable device-based approach to a truly non-intrusive and scalable approach.