-
The wide range, high precision, and dynamic real-time measurement of diameter are crucial for achieving low loss transmission and controlling dispersion in the preparation process of micro-/nanofiber. In view of the problems of small diameter regulation range, complex operation and long-time consumption of the existing preparation methods, this paper firstly realizes the automatic detection system of micro-/nanofiber based on deep learning neural network algorithm. In this paper, the image segmentation method in computer vision is used to make high-quality multi-scale micro-/nanofiber datasets, and the improved YOLOv8-FD(You Only Look Once version 8-Fiber Detection) algorithm based on small target detection is used to automatically detect the diameter of micro-/nanofiber.
Through image segmentation and identification of the target of single pixel size in the microscopic image, the diameter detection of micro-/nanofiber is finally realized. In this process, the real-time diameter of micro-/nanofiber is obtained through image information, and then the micro-/nanofiber small target is accurately segmented to achieve the precise detection of mAPIoU=50=0.995 and mAPIoU=50:95=0.765 on the micro-/nanofiber multi-scale target dataset with extremely high accuracy. The algorithm-based construction of a high-precision micro-/nanofiber automatic preparation system enables real-time accurate segmentation of fiber edges, calculation of fiber diameter, and feedback to the control system for achieving automated preparation of fibers with arbitrary diameters. Additionally, it facilitates detection of micro-/nanofiber within the range of 462 nm to 125 μm. The average response time for reasoning is 9.6 ms, while maintaining a detection error below 2.95%.
In addition, compared with other micro-/nanofiber diameter detection methods based on optical imaging and mode cutoff, this method shows advantages of high precision, high speed and arbitrary diameter preparation for diameter detection based on deep learning neural networks. The system is well-suited for high-precision real-time measurement and automated, precise preparation of micro-/nanofiber, thereby offering a novel approach for the development of low-loss transmission and adjustable dispersion micro-/nanofiber devices.
-
Keywords:
- micro-/nanofiber /
- diameter measurement /
- deep learning /
- image segmentation
-
[1] Tong L M 2022Acta Opt. Sin. 42 17(in Chinese)[童利民2022光学学报42 17]
[2] Zhang L, Pan J, Zhang Z 2020Opto-Electron Adv. 3 190022
[3] Yan Z Y, Wang J J, Wang C Y, Yu R W, Shi L, Xiao L M 2012Opt. Express 30 18044
[4] Cen Q Q, Pian S J, Liu X H, Tang Y W, He X Y, Ma Y G 2023eLight 3 9
[5] Li Y H, Wang L Z, Li L J, Tong L M 2019Appl. Phys. B 125192
[6] Lu J S, Li Q, Qiu C W, Hong Y, Ghosh P, Qiu M 2019Sci. Adv. 58271
[7] Tkachenko G, Toftul I, Esporlas C, Maimaiti A, Kien F L, Truong V G, Chormaic S N 2020Optica 759
[8] Linghu S Y, Gu Z Q, Lu J S, Fang W, Yang Z Y, Yu H K, Li Z Y, Zhu R L, Peng J, Zhan Q W, Zhuang S L, Gu M, Gu F X 2021Nat. Commun. 12, 385
[9] Hao Z, Jiang B Q, Ma Y X, Yi R X, Gan X T, Zhao J L 2023Opto-Electron Adv. 6 230012
[10] Zhang J B, Kang Y, Guo X, Li Y H, Liu K Y, Xie Y, Wu H, Cai D W, Gong J, Shi Z X, Jin Y Y, Wang P, Fang W, Zhang L, Tong L M 2023Light:Sci. Appl. 12 89
[11] Chen J H, Xiong Y F, Xu F, Lu Y Q 2021Light:Sci. Appl. 10 78
[12] Zhou J, Li Y, Ma Y, Yang Q, Liu Q 2021Opt. Lett. 46 1570
[13] Linghu S Y, Ma Y N, Gu Z Q, Zhu R L, Liu Y F, Liu H J, Gu F X 2022Opt. Express 30 22755
[14] Liao F, Yu J X, Gu Z Q, Yang Z Y, Hasan T, Linghu S Y, Pang J, Fang W, Zhuang S L, Gu M, Gu F X 2019Sci. Adv. 57398
[15] Kang Y, Liu K Y, Xie Y, Gong Y, Yao N, Fang W, Guo X, Zhang L, Wang P, Tong L M 2020Sci. Sin. Phys. Mech.& As. 50 084212(in Chinese)[康仪,刘可盈,谢宇,龚珏,姚妮,方伟,郭欣,张磊,王攀,童利民2020中国科学:物理学,力学,天文学50 084212]
[16] Ni Y, Linghu S L, Xu Y X, Zhu R L, Zhou N, Gu F X, Zhang L, Fang W, Ding W, Tong L M 2020IEEE Photon. Technol. Lett. 32 1069
[17] Warken F, Giessen H 2004Opt. Lett. 291727
[18] Little D J, Kane D M 2014Opt. Lett. 395196
[19] Yu Y, Zhang X, Song Z 2014Appl. Opt. 53 8222
[20] Xu Y, Fang W, Tong L 2017Opt. Express 25 10434
[21] Kang Y, Gong J, Xu Y 2020IEEE Photon. Technol. Lett.2020, 32 219
[22] Azzoune A, Delaye P, Pauliat G 2019Opt. Express 27 24403
[23] Li H, Ma Y N, Gu F X 2022Opt. Instruments 44 1005(in Chinese)[李华,麻艳娜,谷付星2022光学仪器44 1005]
[24] Woo S, Park J, Lee J Y 2017ECCV 319
[25] Ying D W, Zhang S H, Deng S J, Wu H B 2023Acta Phys. Sin.72 14 in Chinese)[应大卫,张思慧,邓书金,武海斌2023物理学报72 14]
[26] Nan H, Ma X J, Zhao H B, Tang S J, Liu W H, Wang D W, Jia C L 2021Acta Phys. Sin. 70 7(in Chinese)[南虎,麻晓晶,赵海博,汤少杰,刘卫华,王大威,贾春林2021物理学报70 7]
[27] He K M, Gkioxari G, Dollar P, Girshick R 2017ICCV 17 2980
[28] Gu Z, Zhu R L, Shen T C, Dou L, Liu H J, Liu Y F, Liu X, Liu J, Zhuang S L, Gu F X 2023Nat. Commun. 14 7663
Metrics
- Abstract views: 281
- PDF Downloads: 7
- Cited By: 0