Skip to main content

Advertisement

Log in

Automatic estimation of clothing insulation rate and metabolic rate for dynamic thermal comfort assessment

  • Original Article
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Existing heating, ventilation, and air-conditioning systems have difficulties in considering occupants’ dynamic thermal needs, thus resulting in overheating or overcooling with huge energy waste. This situation emphasizes the importance of occupant-oriented microclimate control where dynamic individual thermal comfort assessment is the key. Therefore, in this paper, a vision-based approach to estimate individual clothing insulation rate (\(I_{\rm{cl}}\)) and metabolic rate (M), the two critical factors to assess personal thermal comfort level, is proposed. Specifically, with a thermal camera as the input source, a convolutional neural network (CNN) is implemented to recognize an occupant’s clothes type and activity type simultaneously. The clothes type then helps to differentiate the skin region from the clothing-covered region, allowing to calculate the skin temperature and the clothes temperature. With the two recognized types and the two computed temperatures, \(I_{\rm{cl}}\) and M can be estimated effectively. In the experimental phase, a novel thermal dataset is introduced, which allows evaluations of the CNN-based recognizer module, the skin and clothes temperatures acquisition module, as well as the \(I_{\rm{cl}}\) and M estimation module, proving the effectiveness and automation of the proposed approach.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. EIA U (2005) Residential energy consumption survey. US Energy Information Administration2009

  2. Fanger PO (1973) Assessment of man’s thermal comfort in practice. Occup Environ Med 30(4):313–324

    Article  Google Scholar 

  3. Organization IS (2020) Ergonomics of the thermal environment: analytical determination and interpretation of thermal comfort using calculation of the pmv and ppd indices and local thermal comfort criteria. https://www.iso.org/standard/39155.html/ Accessed May 20

  4. Liang J, Du R (2005) Thermal comfort control based on neural network for hvac application. In: Proceedings of 2005 IEEE Conference on control applications, 2005. CCA 2005., pp. 819–824. IEEE

  5. Hwang RL, Shu SY (2011) Building envelope regulations on thermal comfort in glass facade buildings and energy-saving potential for pmv-based comfort control. Build Environ 46(4):824–834

    Article  Google Scholar 

  6. Kuzuhara K, Nishi H (2013) Accurate indoor condition control based on pmv prediction in bems environments. In: IECON 2013-39th Annual Conference of the IEEE Industrial Electronics Society, pp. 8142–8147. IEEE

  7. Conceição EZ, Gomes JM, Ruano AE (2018) Application of hvac systems with control based on pmv index in university buildings with complex topology. IFAC-PapersOnLine 51(10):20–25

    Article  Google Scholar 

  8. Conceição EZ, Sousa AF, Gomes JM, Ruano AE (2019) Hvac systems applied in university buildings with control based on pmv and apmv indexes. Inventions 4(1):3

    Article  Google Scholar 

  9. Wu J, Li X, Tu J, Yang L, Yan Y (2020) A pmv-based hvac control strategy for office rooms subjected to solar radiation. Build Environ 177:106863

    Article  Google Scholar 

  10. Cao Z, Simon T, Wei S.E, Sheikh Y (2017) Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291–7299

  11. ASHRAE (2020) Thermal environmental conditions for human occupancy. https://www.ashrae.org/technical-resources/bookstore/standard-55-thermal-environmental-conditions-for-human-occupancy/. Accessed May 20, 2020

  12. Ngarambe J, Yun GY, Kim G (2019) Prediction of indoor clothing insulation levels: a deep learning approach. Energy Build 202:109402

    Article  Google Scholar 

  13. Nicol F, Roaf S (1996) Pioneering new indoor temperature standards: the Pakistan project. Energy Build 23(3):169–174

    Article  Google Scholar 

  14. De Carli M, Olesen BW, Zarrella A, Zecchin R (2007) People’s clothing behaviour according to external weather and indoor environment. Build Environ 42(12):3965–3973

    Article  Google Scholar 

  15. Haldi F, Robinson D (2011) Modelling occupants’ personal characteristics for thermal comfort prediction. Int J Biometeorol 55(5):681–694

    Article  Google Scholar 

  16. de Carvalho PM, da Silva MG, Ramos JE (2013) Influence of weather and indoor climate on clothing of occupants in naturally ventilated school buildings. Build Environ 59:38–46

    Article  Google Scholar 

  17. Liu W, Yang D, Shen X, Yang P (2018) Indoor clothing insulation and thermal history: a clothing model based on logistic function and running mean outdoor temperature. Build Environ 135:142–152

    Article  Google Scholar 

  18. Organization IS (2020) Ergonomics of the thermal environment: estimation of thermal insulation and water vapour resistance of a clothing ensemble. https://www.iso.org/standard/39257.html/ Accessed May 20

  19. Konarska M, Soltynski K, Sudol-Szopinska I, Chojnacka A (2007) Comparative evaluation of clothing thermal insulation measured on a thermal manikin and on volunteers. Fibres Text East Eur 15(2):73

    Google Scholar 

  20. Lu S, Hameen C, (2018) E Integrated ir vision sensor for online clothing insulation measurement

  21. Olesen B, Nielsen R (1983) Thermal insulation of clothing measured on a movable thermal manikin and on human subjects. ECSC Program Res (7206/00):914

  22. McCullough EA, Jones BW, Huck J (1985) A comprehensive data base for estimating clothing insulation. Ashrae Trans 91(2):29–47

    Google Scholar 

  23. Matsumoto H, Iwai Y, Ishiguro, H (2011) Estimation of thermal comfort by measuring clo value without contact. In: MVA, pp. 491–494. Citeseer

  24. Lee JH, Kim YK, Kim KS, Kim S (2016) Estimating clothing thermal insulation using an infrared camera. Sensors 16(3):341

    Article  Google Scholar 

  25. Miura J, Demura M, Nishi K, Oishi S (2019) Thermal comfort measurement using thermal-depth images for robotic monitoring. Pattern Recognit Lett 137:108

    Article  Google Scholar 

  26. Lee K, Choi H, Kim H, Kim DD, Kim T (2020) Assessment of a real-time prediction method for high clothing thermal insulation using a thermoregulation model and an infrared camera. Atmosphere 11(1):106

    Article  Google Scholar 

  27. Luo M, Zhou X, Zhu Y, Sundell J (2016) Revisiting an overlooked parameter in thermal comfort studies, the metabolic rate. Energy Build 118:152–159

    Article  Google Scholar 

  28. Zhai Y, Li M, Gao S, Yang L, Zhang H, Arens E, Gao Y (2018) Indirect calorimetry on the metabolic rate of sitting, standing and walking office activities. Build Environ 145:77–84

    Article  Google Scholar 

  29. Ji W, Luo M, Cao B, Zhu Y, Geng Y, Lin B (2018) A new method to study human metabolic rate changes and thermal comfort in physical exercise by co2 measurement in an airtight chamber. Energy Build 177:402–412

    Article  Google Scholar 

  30. Calvaresi A, Arnesano M, Pietroni F, Revel GM (2018) Measuring metabolic rate to improve comfort management in buildings. Environ Eng Manag J 17(10):2287

    Article  Google Scholar 

  31. Casaccia S, Pietroni F, Calvaresi A, Revel G.M, Scalise, L (2016) Smart monitoring of userp s health at home: Performance evaluation and signal processing of a wearable sensor for the measurement of heart rate and breathing rate. Biosignals pp. 175–182

  32. Na H, Choi JH, Kim H, Kim T (2019) Development of a human metabolic rate prediction model based on the use of kinect-camera generated visual data-driven approaches. Build Environ 160:106216

    Article  Google Scholar 

  33. Hasan MH, Alsaleem F, Rafaie M (2016) Sensitivity study for the pmv thermal comfort model and the use of wearable devices biometric data for metabolic rate estimation. Build Environ 110:173–183

    Article  Google Scholar 

  34. Gilani SH, Khan MH, Ali M (2016) Revisiting fanger’s thermal comfort model using mean blood pressure as a bio-marker: an experimental investigation. Appl Therm Eng 109:35–43

    Article  Google Scholar 

  35. Organization I.S (2020) Ergonomics of the thermal environment: determination of metabolic rate. https://www.iso.org/standard/34251.html/. Accessed May 20

  36. Organization I.S (2020) Ergonomics of the thermal environment: analytical determination and interpretation of heat stress using calculation of the predicted heat strain. https://www.iso.org/standard/37600.html/ Accessed May 20

  37. Cheng X, Yang B, Olofsson T, Liu G, Li H (2017) A pilot study of online non-invasive measuring technology based on video magnification to determine skin temperature. Build Environ 121:1–10

    Article  Google Scholar 

  38. Cheng X, Yang B, Hedman A, Olofsson T, Li H, Van Gool L (2018) Non-invasive thermal comfort perception based on subtleness magnification and deep learning for energy efficiency. arXiv preprint arXiv:1811.08006

  39. Jazizadeh F, Jung W (2018) Personalized thermal comfort inference using rgb video images for distributed hvac control. Appl Energy 220:829–841

    Article  Google Scholar 

  40. Li D, Menassa CC, Kamat VR (2019) Feasibility of low-cost infrared thermal imaging to assess occupants’ thermal comfort. Computing in Civil Engineering 2019: Smart Cities. Sustainability, and Resilience. American Society of Civil Engineers Reston, VA, pp 58–65

  41. Li D, Menassa CC, Kamat VR (2019) Robust non-intrusive interpretation of occupant thermal comfort in built environments with low-cost networked thermal cameras. Appl Energy 251:113336

    Article  Google Scholar 

  42. Lu S, Wang W, Wang S, Cochran Hameen E (2019) Thermal comfort-based personalized models with non-intrusive sensing technique in office buildings. Appl Sci 9(9):1768

    Article  Google Scholar 

  43. Qian J, Cheng X, Yang B, Li Z, Ren J, Olofsson T, Li H (2020) Vision-based contactless pose estimation for human thermal discomfort. Atmosphere 11(4):376

    Article  Google Scholar 

  44. Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. Adv Neural Inf Process Syst pp. 568–576

  45. Zhu Y, Lan Z, Newsam S, Hauptmann A (2018) Hidden two-stream convolutional networks for action recognition. In: Asian Conference on Computer Vision pp. 363–378

  46. Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L(2016) Temporal segment networks: Towards good practices for deep action recognition. In: European conference on computer vision, pp. 20–36. Springer

  47. Zach C, Pock T, Bischof H (2007)A duality based approach for realtime tv-l 1 optical flow. In: Joint pattern recognition symposium, pp. 214–223. Springer

  48. Liu J, Foged I W, Moeslund T B (2020) Vision-based individual factors acquisition for thermal comfort assessment in a built environment. In: Proceedings of the 15th IEEE international conference on automatic face and gesture recognition (FG 2020), pp. 372–376

  49. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1–9

  50. Ioffe S, Szegedy C(2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167

  51. Dai C, Zhang H, Arens E, Lian Z (2017) Machine learning approaches to predict thermal demands using skin temperatures: Steady-state conditions. Build Environ 114:1–10

    Article  Google Scholar 

  52. Cosma AC, Simha R (2018) Thermal comfort modeling in transient conditions using real-time local body temperature extraction with a thermographic camera. Build Environ 143:36–47

    Article  Google Scholar 

  53. Deng J, Dong W, Socher R, Li L.J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248–255

  54. Liu Z, Luo P, Qiu S, Wang X, Tang X (2016) Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1096–1104

  55. Kawashima T, Kawanishi Y, Ide I, Murase H, Deguchi D, Aizawa T, Kawade M (2017) Action recognition from extremely low-resolution thermal image sequence. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1–6. IEEE

  56. Morawski I, Lie W.N (2020)Two-stream deep learning architecture for action recognition by using extremely low-resolution infrared thermopile arrays. In: International Workshop on Advanced Imaging Technology (IWAIT) 2020, 11515: 115150Y

  57. Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 3686–3693

  58. Hoyt T, Schiavon S, Tartarini F, Cheung T, Steinfeld K, Piccioli A, Moon D (2020) Cbe thermal comfort tool. https://comfort.cbe.berkeley.edu/EN Accessed Nov 11,

  59. Tartarini F, Schiavon S, Cheung T, Hoyt T (2020) Cbe thermal comfort tool: online tool for thermal comfort calculations and visualizations. SoftwareX 12:100563

    Article  Google Scholar 

  60. Jiao Y, Yu H, Wang T, An Y, Yu Y (2017) The relationship between thermal environments and clothing insulation for elderly individuals in shanghai, china. J Therm Biol 70:28–36

    Article  Google Scholar 

  61. Angelova R.A, Georgieva E, Markov D, Bozhkov T, Simova I, Kehaiova N, Stankov P (2018) Estimating the effect of torso clothing insulation on body skin and clothing temperatures in a cold environment using infrared thermography. Fibres & Textiles in Eastern Europe

  62. Salata F, Golasi I, Ciancio V, Rosso F (2018) Dressed for the season: clothing and outdoor thermal comfort in the mediterranean population. Build Environ 146:50–63

    Article  Google Scholar 

  63. Xi T, Wang Q, Qin H, Jin H (2020) Influence of outdoor thermal environment on clothing and activity of tourists and local people in a severely cold climate city. Build Environ 173:106757

    Article  Google Scholar 

Download references

Acknowledgements

We would like to thank the test subjects from Visual Analysis and Perception Laboratory and Audio Analysis Lab, CREATE, Aalborg University, Denmark.

Funding

This work is funded by Realdania and the Obel Foundation as part of the project Thermal Adaptive Architecture.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jinsong Liu.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

According to Annex H of ISO 9920 [18], \(I_{\rm{cl}}\) can be calculated from the mass of the clothes and the body surface area covered by clothing, that is

$$\begin{aligned} \begin{aligned} I_{\rm{cl}}\,=&0.919+0.255 \times 10^{-3}\cdot m-0.00874\cdot A_{\rm{cov}, 0}\\&-0.00510\cdot A_{\rm{cov}, 1} \end{aligned} \end{aligned}$$
(9)

where m is the mass of the clothes, without shoes, in grams; \(A_{cov,0}\) is the body surface area not covered by clothing; \(A_{cov,1}\) is the body surface area covered by a single clothing layer; both \(A_{cov,0}\) and \(A_{\rm{cov},1}\) are expressed as percentages of the total body surface area shown in Table 13.

Table 13 Body surface area percentage [18]

When a person rolls up the sleeves or unzips the zipper, the mass of the clothes remains the same, while the \(A_{cov,0}\) or the \(A_{cov,1}\) is changed, leading to a correction in \(I_{\rm{cl}}\) by Eqs. (4, 5 or 6) in Sect. 3.3.

According to Section 9 of ISO 9920, when a person is sitting, the compressed air between the body and the clothes leads to a decrease in \(I_{\rm{cl}}\) by 6–18%. Office chairs introduce an increase in \(I_{\rm{cl}}\) of 0.04–0.17 clo. We use the median values of these fluctuations as 12% and 0.105 clo, respectively, and get Eq. (7) in Sect. 3.3.

According to Section 8.2 of ISO 9920, the dynamic clothing insulation rate \(I_{cl,d}\) under a condition having air and body movement can be calculated from

$$\begin{aligned}I_{cl,d}=\frac{(0.6-I_{cl,s})\cdot I_{a,d}+I_{cl,s}\cdot I_{t,d}}{0.6}-I_{a,d}\,\,(0< I_{cl,s} \le 0.6) \end{aligned}$$
(10)
$$\begin{aligned}I_{cl,d}=I_{t,d}-I_{a,d}\,(0.6< I_{cl,s} < 1.4) \end{aligned}$$
(11)
$$\begin{aligned}&I_{t,d}=I_{t,s}\cdot C_{t} \end{aligned}$$
(12)
$$\begin{aligned}&I_{a,d}=I_{a,s}\cdot C_{a} \end{aligned}$$
(13)
$$\begin{aligned}&I_{t,s}=I_{cl,s}+I_{a,s} \end{aligned}$$
(14)
$$\begin{aligned}&C_{t}=e^{\left[ -0.281\cdot \left( v_{\rm{{a}}}-0.15\right) +0.044\cdot \left( v_{\rm{{a}}}-0.15\right) ^{2}-0.492\cdot v_{\rm {w}}+0.176\cdot v_{\rm{{w}}}^{2}\right] } \end{aligned}$$
(15)
$$\begin{aligned}&C_{a}=e^{\left[ -0.533\cdot \left( v_{\rm{{a}}}-0.15\right) +0.069\cdot \left( v_{\rm{{a}}}-0.15\right) ^{2}-0.462\cdot v_{\rm{{w}}}+0.201\cdot v_{\rm{{w}}}^{2}\right] } \end{aligned}$$
(16)

where \(I_{t,d}\), \(I_{a,d}\), \(I_{cl,s}\), \(I_{t,s}\), \(I_{a,s}\), \(v_{a}\), and \(v_{w}\) are the dynamic total thermal insulation, the dynamic air insulation, the static clothes insulation, the static total insulation, the static air insulation, the relative air velocity in relation to human motion, and the human motion velocity, respectively.

As Section 6 of ISO 9920 mentions, the static air insulation \(I_{a,s}\) in most studies is around 0.7 clo. When the human motion velocity is \(\hbox {1}\rm{m/s}\), for a wind-free environment (air velocity is smaller than \(\hbox {0.2}\rm{m/s}\)), the relative air velocity in relation to human motion is about \(\hbox {1}{m/s}\), and then from Eqs. (10)–(16), Eq. (8) in Sect. 3.3 is derived.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, J., Foged, I.W. & Moeslund, T.B. Automatic estimation of clothing insulation rate and metabolic rate for dynamic thermal comfort assessment. Pattern Anal Applic 25, 619–634 (2022). https://doi.org/10.1007/s10044-021-00961-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-021-00961-5

Keywords

Navigation