Deep learning for position fixing in the micron scale by using convolutional neural networks

Hongye Li; Hu Liang; Qihao Hu; Meng Wang; Zefeng Wang

doi:10.3788/COL202018.050602

Journals >Chinese Optics Letters >Volume 18 >Issue 5 >Page 050602 > Article

Chinese Optics Letters
Vol. 18, Issue 5, 050602 (2020)

Deep learning for position fixing in the micron scale by using convolutional neural networks

Hongye Li¹, Hu Liang⁴, Qihao Hu¹, Meng Wang^1、2、3, and Zefeng Wang^{1、2、3、*}

Author Affiliations

¹College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, China

²State Key Laboratory of Pulsed Power Laser Technology, Changsha 410073, China

³Hunan Provincial Key Laboratory of High Energy Laser Technology, Changsha 410073, China

⁴Tianjin Navigation Instruments Research Institute, Tianjin 300131, China

show less

DOI: 10.3788/COL202018.050602 Cite this Article Set citation alerts

Hongye Li, Hu Liang, Qihao Hu, Meng Wang, Zefeng Wang. Deep learning for position fixing in the micron scale by using convolutional neural networks[J]. Chinese Optics Letters, 2020, 18(5): 050602 Copy Citation Text

EndNote(RIS)

BibTex

Plain Text

show less

Abstract

We propose here a novel method for position fixing in the micron scale by combining the convolutional neural network (CNN) architecture and speckle patterns generated in a multimode fiber. By varying the splice offset between a single mode fiber and a multimode fiber, speckles with different patterns can be generated at the output of the multimode fiber. The CNN is utilized to learn these specklegrams and then predict the offset coordinate. Simulation results show that predicted positions with the precision of 2 μm account for 98.55%. This work provides a potential high-precision two-dimensional positioning method.

Keywords

fiber optics fiber optics imaging fiber optics sensors

η_{μ} = \frac{{[\iint ({\vec{E}}_{in} \times {\vec{H}}_{μ}^{*}) \cdot \hat{z} d x d y]}^{2}}{[\iint ({\vec{E}}_{μ} \times {\vec{H}}_{μ}^{*}) \cdot \hat{z} d x d y] [\iint ({\vec{E}}_{in} \times {\vec{H}}_{in}^{*}) \cdot \hat{z} d x d y]} .

(1)

View in Article

I (x, y) = {| \sum_{ν = 1}^{110} \frac{η_{μ} {\vec{E}}_{μ} (x, y) e^{- j β_{μ} z}}{\sqrt{\iint ({\vec{E}}_{in} \times {\vec{H}}_{in}^{*}) \cdot \hat{z} d x d y}} |}^{2} .

(2)

View in Article

Ψ (d) = \frac{\iint i_{0} i_{d} d x d y}{{(\iint i_{0}^{2} d x d y \iint i_{d}^{2} d x d y)}^{1 / 2}},

(3)

View in Article

I_{c} (x, y) = \frac{I (x, y) - \min [I (x, y)]}{\max [I (x, y)] - \min [I (x, y)]},

(4)

View in Article

MSE = \frac{1}{m} \sum_{i = 1}^{m} [{(X_{p}^{(i)} - X_{l}^{(i)})}^{2} + {(Y_{p}^{(i)} - Y_{l}^{(i)})}^{2}] .

(5)

View in Article

d = \sqrt{{(x_{p} - x_{l})}^{2} + {(y_{p} - y_{l})}^{2}},

(6)

View in Article

Hongye Li, Hu Liang, Qihao Hu, Meng Wang, Zefeng Wang. Deep learning for position fixing in the micron scale by using convolutional neural networks[J]. Chinese Optics Letters, 2020, 18(5): 050602

Download Citation

EndNote(RIS)

BibTex

Plain Text

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information