面向激光干涉离焦图像的粒子定位方法

孙金露, 王晓阳, 武宇航, 郭志诚, 杜星诺, 石嘉

天津工业大学学报 ›› 2026, Vol. 45 ›› Issue (4) : 96 -104.

PDF (2627KB)
天津工业大学学报 ›› 2026, Vol. 45 ›› Issue (4) : 96 -104. DOI: 10.3969/j.issn.1671-024x.2026.04.012
电子信息与自动化

面向激光干涉离焦图像的粒子定位方法

    孙金露1,2, 王晓阳1,2, 武宇航1,2, 郭志诚1,2, 杜星诺2, 石嘉1,2
作者信息 +

Particle localization method for laser interferometric defocus images

    Sun Jinlu1,2, Wang Xiaoyang1,2, Wu Yuhang1,2, Guo Zhicheng1,2, Du Xingnuo2, Shi Jia1,2
Author information +
文章历史 +
PDF (2689K)

摘要

为了精确检测混合粒子场中的粒子位置,提出了面向激光干涉离焦图像的RFBCA-YOLO粒子定位方法,通过在YOLOv7网络中加入感受野(RFB)和坐标注意力(CA)模块实现任意粒子场内粒子的高精度定位。对比分析了腐蚀匹配、Hough变换和RFBCA-YOLO 3种方法对球形粒子场和混合粒子场粒子的定位结果。对仿真和实验干涉离焦图像中粒子中心点的定位结果表明:RFBCA-YOLO方法的定位精确度最高,漏检和错检的数量最少;通过交并比分析可知RFBCA-YOLO对仿真和实验图像的重叠率检测极限分别为42.87%和44.87%,表明通过RFBCA-YOLO可实现粒子的精准定位,为混合粒子场的测量提供研究基础。

Abstract

In order to accurately detect the localization of particles in a mixed particle field, an RFBCA-YOLO particle localization method based on laser interferometric defocus images is proposed. By adding the receptive field block(RFB)and the coordinate attention(CA)modules into the YOLOv7 network, the high-accuracy localization of particles in arbitrary particle field is realized. The particles localization results of spherical particle fields and mixed particle fields obtained by three methods, namely corrosion matching, Hough transform and RFBCA-YOLO, are compared and analyzed. In the analysis of the simulated interferometric defocus images, the localization results of the particle center points shows that there is a similar accuracy between RFBCA-YOLO and corrosion matching method, with the lowest miss and false detections. The localization results of particle centers in simulated and experimental interferometric defocus images indicate that the RFBCA-YOLO method has the highest localization accuracy, with the lowest miss and false detections. Additionally, the intersection over union analysis indicates that the detection limits of RFBCA-YOLO are 42.87% and 44.87% for the simulated and experimental images, respectively. These findings indicate that the RFBCA-YOLO method realizes high-accuracy localization of particles, providing a foundational basis for the measurement of mixed particle fields.

关键词

干涉离焦图像 / 粒子定位 / RFBCA-YOLO / 混合粒子场

Key words

interferometric defocus images / particle localization / RFBCA-YOLO / mixed particle fields

引用本文

引用格式 ▾
孙金露, 王晓阳, 武宇航, 郭志诚, 杜星诺, 石嘉. 面向激光干涉离焦图像的粒子定位方法[J]. 天津工业大学学报, 2026, 45(4): 96-104 DOI:10.3969/j.issn.1671-024x.2026.04.012

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1] Cao Y H, Wu Z L, Su Y, et al.Aircraft flight characteristics in icing conditions[J]. Progress in Aerospace Sciences, 2015, 74: 62-80.
[2] Sun J L, Zhang H X, Li J, et al.Hybrid spherical particle field measurement based on interference technology[J]. Measurement Science and Technology, 2017, 28(3): 035204.
[3] Lu Q N, Li Z X, Fu C S, et al.Simultaneous retrieval of particle size and refractive index by extended interferometric particle imaging technique[J]. Optics Express, 2020, 28(2): 2192.
[4] 吕且妮, 葛宝臻, 陈益亮, 等. 激光干涉粒子成像测量干涉图处理算法研究[J]. 光学学报, 2011, 31(4): 308003.
Lü Qieni, Ge Baozhen, Chen Yiliang, et al.An algorithm for interferometric image processing of interferometric particle imaging[J]. Acta Optica Sinica, 2011, 31(4): 308003(in Chinese).
[5] Fu Y S, Zhang H X, Hou J H, et al.Uncertainty elimination in 2D shape reconstruction of irregular particles in interferometric particle imaging[J]. Measurement, 2024, 231: 114571.
[6] Park J S, Lee I B, Hong S C, et al.Label-free interference imaging of intracellular trafficking[J]. Accounts of Chemical Research, 2024, 57(11): 1565-1576.
[7] Song T H, Lu Q N, Liu H, et al.Characterization of nasal spray aerosol fields using the extended interferometric particle imaging technique[J]. Measurement, 2024, 233: 114733.
[8] Rostami A, Mohammadnejad S, Li R, et al.Astigmatic interferometric particle imaging of reacting jet A-1 sprays: Joint droplet and cluster characteristics[J]. Proceedings of the Combustion Institute, 2024, 40(1/2/3/4): 105600.
[9] Lu Q N, Yu X X, Ge B Z, et al.Simultaneous location and size measurement of particles using extended glare-point imaging technique[J]. Optics Express, 2018, 26(2): 1038.
[10] Abad A, Fahy A, Frodello Q, et al.Particle shape recognition with interferometric particle imaging using a convolutional neural network in polar coordinates[J]. Photonics, 2023, 10(7): 779.
[11] Lü Q N, Jin W H, Lü T, et al.High-accuracy particle sizing by interferometric particle imaging[J]. Optics Communications, 2014, 312: 312-318.
[12] 吕且妮, 高岩, 葛宝臻, 等. 基于霍夫变换的数字全息粒子尺寸测量[J]. 中国激光, 2009, 36(4): 940-944.
Lü Qieni, Gao Yan, Ge Baozhen,et al.Digital holographic particle sizing with Hough transform[J]. Chinese Journal of Lasers, 2009, 36(4): 940-944(in Chinese).
[13] Wu Y C, Zhao X X, Zhang H Y, et al.Discrimination and measurement of droplet and ice crystal by combining digital inline holography with interferometric particle imaging with single color camera[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 5015208.
[14] Lü Q N, Wang X, Lü T, et al.Linear interferometric image processing for analysis of a particle in a volume[J]. Journal of Optics, 2014, 16(4): 045703.
[15] Zhang Z W, Zhang C J, Li M Y, et al.Target positioning based on particle centroid drift in large-scale WSNs[J]. IEEE Access, 2020, 8: 127709-127719.
[16] Lu Q N, Yu X X, Xu J.Detection of particle position from a linear interferometric out-of-focus image[J]. Optics & Laser Technology, 2019, 115: 81-89.
[17] Ma Y R, Cui J W, Tan J B.Interferometric laser imaging for droplet-size measurement in spray[J]. Applied Optics, 2022, 61(18): 5496-5506.
[18] Sun J L, Wu Y H, Qiu Y, et al.Position and morphology detection of mixed particles based on IPI and YOLOv7[J]. Optics Communications, 2024, 554: 130158.
[19] Lambert A J, Fraser D.Linear systems approach to simulation of optical diffraction[J]. Applied Optics, 1998, 37(34): 7933-7939.
[20] Shen H H, Coëtmellec S, Gréhan G, et al.Interferometric laser imaging for droplet sizing revisited: Elaboration of transfer matrix models for the description of complete systems[J]. Applied Optics, 2012, 51(22): 5357-5368.
[21] Hennelly B M, Sheridan J T.Generalizing, optimizing, and inventing numerical algorithms for the fractional Fourier, Fresnel, and linear canonical transforms[J]. Journal of the Optical Society of America A, 2005, 22(5): 917-927.
[22] Brunel M, Shen H H, Coëtmellec S, et al.Determination of the size of irregular particles using interferometric out-of-focus imaging[J]. International Journal of Optics, 2014, 2014: 143904.
[23] Xiao H X, Zhang F, He Q S, et al.Classification of ice crystal habits observed from airborne cloud particle imager by deep transfer learning[J]. Earth and Space Science, 2019, 6(10): 1877-1886.
[24] Huang H Y, You Z J, Cai H Y, et al.Fast detection method for prostate cancer cells based on an integrated ResNet50 and YOLOv5 framework[J]. Computer Methods and Programs in Biomedicine, 2022, 226: 107184.
[25] Dos Reis D H, Welfer D, De Souza Leite Cuadros M A, et al. Mobile robot navigation using an object recognition software with RGBD images and the YOLO algorithm[J]. Applied Artificial Intelligence, 2019, 33(14): 1290-1305.
[26] Yang W N, Chen M Y, Wu H, et al.Deep learning-based weak micro-defect detection on an optical lens surface with micro vision[J]. Optics Express, 2023, 31(4):5593-5608.
[27] Tang H Y, Liang S.A visual defect detection for optics lens based on the YOLOv5-C3CA-SPPF network model[J]. Optics Express, 2023, 31(2): 2628-2643.
[28] Kaushal M.Rapid-YOLO: A novel YOLO based architecture for shadow detection[J]. Optik, 2022, 260: 169084.
[29] 郑玉珩, 黄德启. 改进MobileViT与YOLOv4的轻量化车辆检测网络[J]. 电子测量技术, 2023(2): 175-183.
Zheng Yuheng, Huang Deqi.Lightweight vehicle detection network based on MobileViT and YOLOv4[J]. Electronic Measurement Technology, 2023(2): 175-183(in Chinese).
[30] Zhou X, Yi J P, Xie G K, et al.Human detection algorithm based on improved YOLOv4[J]. Information Technology and Control, 2022, 51(3): 485-498.

基金资助

国家自然科学基金项目(42005066); 天津市自然科学基金项目(22JCQNJC01380,23JCYBJC00300); 天津市科技支撑重点研发计划项目(23YFZCSN00090)

AI Summary AI Mindmap
PDF (2627KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉