|
|
|
Deep learning-assisted common temperature measurement based on visible light imaging |
| Jia-Yi Zhu(朱佳仪)1, Zhi-Min He(何志民)1, Cheng Huang(黄成)1, Jun Zeng(曾峻)1, Hui-Chuan Lin(林惠川)1,†, Fu-Chang Chen(陈福昌)1, Chao-Qun Yu(余超群)1, Yan Li(李燕)1, Yong-Tao Zhang(张永涛)1, Huan-Ting Chen(陈焕庭)1, and Ji-Xiong Pu(蒲继雄)1,2 |
1 College of Physics and Information Engineering, Minnan Normal University, Zhangzhou 363000, China;
2 Fujian Provincial Key Laboratory of Light Propagation and Transformation, College of Information Science & Engineering, Huaqiao University, Xiamen 361021, China |
|
|
|
|
Abstract Real-time, contact-free temperature monitoring of low to medium range (30 $^\circ$C-150 $^\circ$C) has been extensively used in industry and agriculture, which is usually realized by costly infrared temperature detection methods. This paper proposes an alternative approach of extracting temperature information in real time from the visible light images of the monitoring target using a convolutional neural network (CNN). A mean-square error of $<1.119 ^\circ$C was reached in the temperature measurements of low to medium range using the CNN and the visible light images. Imaging angle and imaging distance do not affect the temperature detection using visible optical images by the CNN. Moreover, the CNN has a certain illuminance generalization ability capable of detection temperature information from the images which were collected under different illuminance and were not used for training. Compared to the conventional machine learning algorithms mentioned in the recent literatures, this real-time, contact-free temperature measurement approach that does not require any further image processing operations facilitates temperature monitoring applications in the industrial and civil fields.
|
Received: 02 April 2024
Revised: 26 April 2024
Accepted manuscript online:
|
|
PACS:
|
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
| |
07.07.Df
|
(Sensors (chemical, optical, electrical, movement, gas, etc.); remote sensing)
|
| |
78.20.Ci
|
(Optical constants (including refractive index, complex dielectric constant, absorption, reflection and transmission coefficients, emissivity))
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 61975072 and 12174173) and the Natural Science Foundation of Fujian Province, China (Grant Nos. 2022H0023, 2022J02047, ZZ2023J20, and 2022G02006). |
Corresponding Authors:
Hui-Chuan Lin
E-mail: lhc1810@mnnu.edu.cn
|
Cite this article:
Jia-Yi Zhu(朱佳仪), Zhi-Min He(何志民), Cheng Huang(黄成), Jun Zeng(曾峻), Hui-Chuan Lin(林惠川), Fu-Chang Chen(陈福昌), Chao-Qun Yu(余超群), Yan Li(李燕), Yong-Tao Zhang(张永涛), Huan-Ting Chen(陈焕庭), and Ji-Xiong Pu(蒲继雄) Deep learning-assisted common temperature measurement based on visible light imaging 2024 Chin. Phys. B 33 080701
|
[1] Li B J 2007 Study on the relationship between land use and ecological environment, Ph.D Dissertation (Nanjing: Nanjing Agricultural University) (in Chinese)
[2] Guo F 2016 Chemical Engineering Management 29 269 (in Chinese)
[3] Zhang H R 2022 Fault diagnosis and health assessment of power transformers based on data information mining, M.S. Thesis (Jinan: Shandong University) (in Chinese)
[4] Li T F 2020 High Voltage Apparatus 56 246 (in Chinese)
[5] Zhao H 2015 Science and Technology Wind 262 118 (in Chinese)
[6] Li W M 2021 Research on the mechanism and method optimization of artificial intelligence temperature measurement based on visible light images, M.S. Thesis (Wuhan: Huazhong University of Science and Technology) (in Chinese)
[7] Houchens A F and Hering R G 1967 Houchens A F and Hering R G 1967 Proceedings of 2nd Thermophysics Specialist Conference, April 17-20, 1967, New Orleans, LA, USA, pp. 65-89
[8] Torrance K E and Sparrow E M 1967 J. Opt. Soc. Am. 57 1105
[9] Zha Z W, Zhu J Y, Yang X F, Huang X, Guo H X, Xie A, Lu X J and Fu Z W 2022 Proceedings of 23rd International Conference on Electronic Packaging Technology, August 10-13, 2022, Dalian, China, pp. 1-5
[10] He Y, Wang D Z, Yin Q Y, Gao Y Y and Zheng L B 2022 Proceedings of 23rd International Conference on Electronic Packaging Technology, August 10-13, 2022, Dalian, China, pp. 1-6
[11] Farbaniec L and Eakins D E 2023 Rev. Sci. Instrum. 94 034902
[12] Alajlouni S, Maize K and Shakouri A 2022 Proceedings of 21st IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, May 31-June 03, 2022, San Diego, CA, USA, pp. 1-10
[13] Wang M 2020 Research on temperature measurement method based on visible image and machine learning, M.S. Thesis (Wuhan: Huazhong University of Science and Technology) (in Chinese)
[14] Du W J, Ye Q Z, Yuan Z and Li C M 2022 High Voltage Electronics 58 221 (in Chinese)
[15] Nie X F, Ye Q Z, Yuan Z and Han M T 2021 Proceedings of the 16th Annual Conference of China Electrotechnical Society, September 24- 26, 2021, Springer, Singapore, pp. 616-627
[16] Yang J F, Qiao P R, Li Y M and Wang N 2019 Statistics and Decision Making 35 36 (in Chinese)
[17] Yu K, Jia L, Chen Y Q and Xu W 2013 Proceedings of CCF Conference on Artificial Intelligence, July 31-August 2, 2013, Beijing,China, pp.65-89
[18] Zheng Y P, Li G Y and Li Y 2019 Computer Engineering and Applications 55 12 (in Chinese)
[19] Li J, Yang L Z, Ding W, Mao X Z, Fan J J, Wang J F, Shang H F and Ti G 2021 Appl. Opt. 60 4004
[20] Lai X L, Li Q Y, Wu X Y, Liu G D, Chen Z Y and Pu J X 2021 IEEE Access 9 68387
[21] Fan W R, Chen T R, Xu X Q, Chen Z Y, Hu H Z, Zhang D L, Wang D W, Pu J X and Zhu S Y 2022 Laser & Photonics Reviews 16 2100719 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
