Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment

Jinsong Liu; Isak Worre Foged; Thomas B. Moeslund

doi:10.1109/FG47880.2020.00057

Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment

Jinsong Liu, Isak Worre Foged, Thomas B. Moeslund

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

7 Citations (Scopus)

Abstract

To maintain satisfactory chamber thermal environments for occupants, heating, ventilation and air conditioning (HVAC) systems have to work frequently. However, the
room conditions especially the temperatures are usually set
empirically which fail to consider occupants’ real needs, not
to mention personalized thermal comfort, therefore, the HVAC
systems are underutilized and unavoidably induce energy waste.
To solve this problem, a vision-based method to acquire multiple
individual factors that are critical for assessing personalized
thermal sensation is proposed. Specifically, with the indoor
videos captured by a thermal camera as inputs, a convolutional neural network (CNN) is implemented to recognize
an occupant’s clothes and action type simultaneously. With a
dataset of 20 persons, the experimental results show an average
classification rate of 95.14% on 4 dataset partitions for a 15-
category scenario, which prove the effectiveness of the proposed
method.

Original language	English
Title of host publication	2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
Number of pages	5
Publisher	IEEE
Publication date	2020
Pages	372-376
ISBN (Electronic)	978-1-7281-3079-8
DOIs	https://doi.org/10.1109/FG47880.2020.00057
Publication status	Published - 2020
Event	2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) - Buenos Aires, Argentina Duration: 16 Nov 2020 → 20 Nov 2020

Conference

Conference	2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
Country/Territory	Argentina
City	Buenos Aires
Period	16/11/2020 → 20/11/2020

Access to Document

10.1109/FG47880.2020.00057

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{ca58eb2a75554334937224563020a176,

title = "Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment",

abstract = "To maintain satisfactory chamber thermal environments for occupants, heating, ventilation and air conditioning (HVAC) systems have to work frequently. However, theroom conditions especially the temperatures are usually setempirically which fail to consider occupants{\textquoteright} real needs, notto mention personalized thermal comfort, therefore, the HVACsystems are underutilized and unavoidably induce energy waste.To solve this problem, a vision-based method to acquire multipleindividual factors that are critical for assessing personalizedthermal sensation is proposed. Specifically, with the indoorvideos captured by a thermal camera as inputs, a convolutional neural network (CNN) is implemented to recognizean occupant{\textquoteright}s clothes and action type simultaneously. With adataset of 20 persons, the experimental results show an averageclassification rate of 95.14% on 4 dataset partitions for a 15-category scenario, which prove the effectiveness of the proposedmethod.",

author = "Jinsong Liu and Foged, {Isak Worre} and Moeslund, {Thomas B.}",

year = "2020",

doi = "10.1109/FG47880.2020.00057",

language = "English",

pages = "372--376",

booktitle = "2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)",

publisher = "IEEE",

address = "United States",

note = "2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) ; Conference date: 16-11-2020 Through 20-11-2020",

}

Liu, J, Foged, IW & Moeslund, TB 2020, Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment. in 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). IEEE, pp. 372-376, 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), Buenos Aires, Argentina, 16/11/2020. https://doi.org/10.1109/FG47880.2020.00057

Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment. / Liu, Jinsong; Foged, Isak Worre ; Moeslund, Thomas B.
2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). IEEE, 2020. p. 372-376.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment

AU - Liu, Jinsong

AU - Foged, Isak Worre

AU - Moeslund, Thomas B.

PY - 2020

Y1 - 2020

N2 - To maintain satisfactory chamber thermal environments for occupants, heating, ventilation and air conditioning (HVAC) systems have to work frequently. However, theroom conditions especially the temperatures are usually setempirically which fail to consider occupants’ real needs, notto mention personalized thermal comfort, therefore, the HVACsystems are underutilized and unavoidably induce energy waste.To solve this problem, a vision-based method to acquire multipleindividual factors that are critical for assessing personalizedthermal sensation is proposed. Specifically, with the indoorvideos captured by a thermal camera as inputs, a convolutional neural network (CNN) is implemented to recognizean occupant’s clothes and action type simultaneously. With adataset of 20 persons, the experimental results show an averageclassification rate of 95.14% on 4 dataset partitions for a 15-category scenario, which prove the effectiveness of the proposedmethod.

AB - To maintain satisfactory chamber thermal environments for occupants, heating, ventilation and air conditioning (HVAC) systems have to work frequently. However, theroom conditions especially the temperatures are usually setempirically which fail to consider occupants’ real needs, notto mention personalized thermal comfort, therefore, the HVACsystems are underutilized and unavoidably induce energy waste.To solve this problem, a vision-based method to acquire multipleindividual factors that are critical for assessing personalizedthermal sensation is proposed. Specifically, with the indoorvideos captured by a thermal camera as inputs, a convolutional neural network (CNN) is implemented to recognizean occupant’s clothes and action type simultaneously. With adataset of 20 persons, the experimental results show an averageclassification rate of 95.14% on 4 dataset partitions for a 15-category scenario, which prove the effectiveness of the proposedmethod.

UR - https://www.computer.org/csdl/proceedings-article/fg/2020/307900a372/1kecId0SP28

U2 - 10.1109/FG47880.2020.00057

DO - 10.1109/FG47880.2020.00057

M3 - Article in proceeding

SP - 372

EP - 376

BT - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)

PB - IEEE

T2 - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)

Y2 - 16 November 2020 through 20 November 2020

ER -

Vision-Based Individual Factors Acquisition for Thermal Comfort Assessment in a Built Environment

Abstract

Conference

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this