[1]王孝艳,柴瑜蔓,蒲继雄.浑浊水体中模拟水生动物的识别[J].华侨大学学报(自然科学版),2025,46(4):442-447.[doi:10.11830/ISSN.1000-5013.202501016]
　WANG Xiaoyan,CHAI Yuman,PU Jixiong.Recognition of Simulated Aquatic Animal in Turbid Water Environments[J].Journal of Huaqiao University(Natural Science),2025,46(4):442-447.[doi:10.11830/ISSN.1000-5013.202501016]
点击复制

浑浊水体中模拟水生动物的识别()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第46卷
期数:
2025年第4期
页码:
442-447
栏目:
出版日期:
2025-07-16

文章信息/Info

Title:
Recognition of Simulated Aquatic Animal in Turbid Water Environments
文章编号:
1000-5013(2025)04-0442-06
作者:
王孝艳1; 2;  柴瑜蔓1; 2;  蒲继雄1; 2
1. 华侨大学 信息科学与工程学院, 福建 厦门 361021;2. 华侨大学 福建省光传输与变换重点实验室, 福建 厦门 361021
Author(s):
WANG Xiaoyan1; 2;  CHAI Yuman1; 2;  PU Jixiong1; 2
1. College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China; 2. Fujian Key Laboratory of Light Propagation and Transformation, Huaqiao University, Xiamen 361021, China
关键词:
水生动物;  图像识别;  动态散射;  浑浊水体;  深度学习;  神经网络
Keywords:
aquatic animals;  image recognition;  dynamic scattering;  turbid water;  deep learning;  neural network
分类号:
O436
DOI:
10.11830/ISSN.1000-5013.202501016
文献标志码:
A
摘要:
以浑浊水体作为模型,研究动态散射场景中的物体识别。以模拟水生动物为例,搭建并训练神经网络,利用深度学习技术对水生动物的种类与数量进行识别。将未经训练的散斑图像输入训练好的神经网络,可以输出水生动物的种类和数目。实验结果表明:利用深度学习技术可以从浑浊水体中成功识别水生动物的种类与数量,水生动物的数量识别准确率为 100%,水生动物的种类识别准确率均大于99%。
Abstract:
Using turbid water as a model, this study investigates object recognition in dynamic scattering environments.. Taking simulated aquatic animal as an example, a neural network is constructed and trained to identify the species and quantity of aquatic animals through deep learning techniques. When untrained speckle images are input into a trained neural network, it outputs the categories and number of aquatic animals. The experiment results demonstrate that deep learning techniques can successfully identify both the categories and quantity of aquatic animals in turbid water. The accuracy of quantity recognition reaches 100%, while the accuracy for species recognition exceeds 99% across all tested categories.

参考文献/References:

[1] 左超,陈钱.计算光学成像:何来,何处,何去,何从?[J].红外与激光工程,2022,51(2):158-341.DOI:10.3788/IRLA20220110.
[2] 卞耀明,司徒国海.透过散射介质光学成像技术的研究进展[J].中国激光,2024,51(11):256-283.DOI:10.3788/CJL240678.
[3] 刘飞,吴晓琴,段景博,等.浅谈计算成像在光电探测中的应用(特邀)[J].光子学报,2021,50(10):1011001.DOI:10.3788/gzxb20215010.1011001.
[4] 陈子阳,陈丽,范伟如,等.基于相关全息原理的散射成像技术及其进展[J].激光与光电子学进展,2021,58(2):9-22.DOI:10.3788/LOP202158.0200001.
[5] 程雪岷,罗烈玉,张泽森,等.计算光学框架下的抗散射成像技术研究(特邀)[J].红外与激光工程,2025,54(1):36-45.DOI:10.3788/IRLA20240298.
[6] KANG S,KWON Y,LEE H,et al.Tracing multiple scattering trajectories for deep optical imaging in scattering media[J].Nature Communication,2023,14(1):6871.DOI:10.1038/s41467-023-42525-7.
[7] BAEK W J,PARK J,CIAO L.Depth-resolved imaging through scattering media using time-gated light field tomography[J].Optics Letters,2024,49(22):6581-6584.DOI:10.1364/OL.541549.
[8] WANG Q Z,LIANG X,WANG L,et al.Fourier spatial filter acts as a temporal gate for light propagating through a turbid medium[J].Optics Letters,1995,20(13):1498-1500.DOI:10.1364/OL.20.001498.
[9] BERTOLOTTI J,VAN PUTTEN E G,BLUM C,et al.Non-invasive imaging through opaque scattering layers[J].Nature,2012,491(4721):232-234.DOI:10.1038/nature11578.
[10] KATZ O,HEIDMANN P,FINK M,et al.Non-invasive single-shot imaging through scattering layers and around corners via speckle correlations[J].Nature Photonics,2014,8:784-790.DOI:10.1038/nphoton.2014.189.
[11] POPOFF S M,LEROSEY G,CARMINATI R, et al.Measuring the transmission matrix in optics: An approach to the study and control of light propagation in disordered media[J].Physics Review Letters,2010,104:100601.DOI:10.1103/PhysRevLett.104.100601.
[12] VELLEKOOP I M,MOSK A P.Focusing coherent light through opaque strongly scattering media[J].Optics Letters,2007,32(16):2309-2311.DOI:10.1364/OL.32.002309.
[13] WOO C M,ZHAO Qi,ZHONG Tianting,et al.Optimal efficiency of focusing diffused light through scattering media with iterative wavefront shaping[J].APL Photonics,2022,7:046109.DOI:10.1063/5.0085943.
[14] ZHAO Wenjing,DU Ziheng,ZHAI Aiping,et al.Wavefront imaging of a biological sample using DMD-based single-pixel phase-shifting interferometric techniques: An experimental comparison[J].Optics & Laser Technology,2024,172:110483.DOI:10.1016/j.optlastec.2023.110483.
[15] TANG Pusong,ZHENG Kanpei,YUAN Weiming,et al.Learning to transmit images through optical speckle of a multimode fiber with high fidelity[J].Applied Physics Letters,2022,121(8):081107.DOI:10.1063/5.0099159.
[16] LI S,DENG M,LEE J,et al. Imaging through glass diffusers using densely connected convolutional networks[J].Optica,2018,5:803-813.DOI:10.1364/OPTICA.5.000803.
[17] YANG Kui,HAN Pingli,GONG Rui,et al.High-quality 3D shape recovery from scattering scenario via deep polarization neural networks[J].Optics and Laser in Engineering,2023,173:107934.DOI:10.1016/j.optlaseng.2023.107934.
[18] CHEN Musheng,JI Xin,LIN Shunda,et al.Image reconstruction of scattered vortex light field based on deep learning[J].Optics and Laser Technology,2023,163:109347.DOI:10.1016/j.optlastec.2023.109347.

相似文献/References:

[1]龚冬梅.大型仪器设备可视化管理系统的设计[J].华侨大学学报(自然科学版),2005,26(3):243.[doi:10.3969/j.issn.1000-5013.2005.03.005]
　Gong Dongmei.A Study on Visualized Management System for Large-Scale Instruments and Equipments[J].Journal of Huaqiao University(Natural Science),2005,26(4):243.[doi:10.3969/j.issn.1000-5013.2005.03.005]
[2]张学英,韩广良.空间划分的目标图像识别与跟踪技术[J].华侨大学学报(自然科学版),2017,38(2):257.[doi:10.11830/ISSN.1000-5013.201702023]
　ZHANG Xueying,HAN Guangliang.Target Image Recognition and Tracking Technology Based on Space Partition[J].Journal of Huaqiao University(Natural Science),2017,38(4):257.[doi:10.11830/ISSN.1000-5013.201702023]
[3]余乐,郑力新,杜永兆,等.采用部分灰度压缩扩阶共生矩阵的煤和煤矸石图像识别[J].华侨大学学报(自然科学版),2018,39(6):906.[doi:10.11830/ISSN.1000-5013.201610012]
　YU Le,ZHENG Lixin,DU Yongzhao,et al.Image Recognition Method of Coal and Coal Gangue Based on Partial Grayscale Compression Extended Coexistence Matrix[J].Journal of Huaqiao University(Natural Science),2018,39(4):906.[doi:10.11830/ISSN.1000-5013.201610012]

备注/Memo

备注/Memo:
收稿日期: 2025-01-09
通信作者: 王孝艳(1986-),女,实验师,主要从事人工智能与光学技术结合的研究。E-mail:xiaoyan_wang_3@foxmail.com。
基金项目: 国家自然科学基金资助项目(62375092)
更新日期/Last Update: 2025-07-20