{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T10:49:02Z","timestamp":1776768542988,"version":"3.51.2"},"reference-count":41,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB4201603"],"award-info":[{"award-number":["2022YFB4201603"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate measurements of the bubble size distribution (BSD) are crucial for investigating gas\u2013liquid mass transfer mechanisms and describing the characteristics of chemical production. However, measuring the BSD in high-density bubbly flows remains challenging due to limited image algorithms and high data densities. Therefore, an end-to-end BSD detection method in dense bubbly flows based on deep learning is proposed in this paper. The bubble detector locates the positions of dense bubbles utilizing objection detection networks and simultaneously performs ellipse parameter fitting to measure the size of the bubbles. Different You Only Look Once (YOLO) architectures are compared, and YOLOv7 is selected as the backbone network. The complete intersection over union calculation method is modified by the circumferential horizontal rectangle of bubbles, and the loss function is optimized by adding L2 constraints of ellipse size parameters. The experimental results show that the proposed technique surpasses existing methods in terms of precision, recall, and mean square error, achieving values of 0.9871, 0.8725, and 3.8299, respectively. The proposed technique demonstrates high efficiency and accuracy when measuring BSDs in high-density bubbly flows and has the potential for practical applications.<\/jats:p>","DOI":"10.3390\/s23146582","type":"journal-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T03:03:25Z","timestamp":1690167805000},"page":"6582","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["End-to-End Bubble Size Distribution Detection Technique in Dense Bubbly Flows Based on You Only Look Once Architecture"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5507-3141","authenticated-orcid":false,"given":"Mengchi","family":"Chen","sequence":"first","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Luzhou Laojiao Co., Ltd., Luzhou 646000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Luzhou Laojiao Co., Ltd., Luzhou 646000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7807-8703","authenticated-orcid":false,"given":"Wenjun","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"key":"ref_1","first-page":"5005110","article-title":"Bubble image segmentation based on a novel watershed algorithm with an optimized mark and edge constraint","volume":"71","author":"Peng","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"055405","DOI":"10.1088\/1361-6501\/acb2e1","article-title":"Spirits quality classification based on machine vision technology and expert knowledge","volume":"34","author":"Chen","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1007\/s11517-022-02562-8","article-title":"Deep learning approach for bubble segmentation from hysteroscopic images","volume":"60","author":"Wang","year":"2022","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1088\/0957-0233\/2\/4\/009","article-title":"A capillary suction prove for bubble size measurement","volume":"2","author":"Barigou","year":"1991","journal-title":"Meas. Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1016\/S0017-9310(05)80290-X","article-title":"Structure of air-water bubbly flow in a vertical pipe\u2014II. Void fraction, bubble velocity and bubble size distribution","volume":"36","author":"Liu","year":"1993","journal-title":"Int. J. Heat Mass Transf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1002\/cjce.5450730213","article-title":"Bubble size and velocity measurement in gas\u2014liquid systems: Application of fiber optic technique to pilot plant scale","volume":"73","author":"Saberi","year":"1995","journal-title":"Can. J. Chem. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.nucengdes.2007.02.050","article-title":"Novel experimental measuring techniques required to provide data for CFD validation","volume":"238","author":"Prasser","year":"2008","journal-title":"Nucl. Eng. Des."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1205\/cherd.04122","article-title":"Local bubble size distributions in agitated vessel: Comparison of three experimental techniques","volume":"83","author":"Laakkonen","year":"2005","journal-title":"Chem. Eng. Res. Des."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"108418","DOI":"10.1016\/j.measurement.2020.108418","article-title":"Interferometric laser imaging for droplet sizing method for long range measurements","volume":"168","author":"Sor","year":"2021","journal-title":"Measurement"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1088\/0957-0233\/16\/9\/007","article-title":"Recognition of highly overlapping ellipse-like bubble images","volume":"16","author":"Honkanen","year":"2005","journal-title":"Meas. Sci. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Talbot, H. (2006, January 25\u201327). Elliptical distance transforms and applications. Proceedings of the International Conference on Discrete Geometry for Computer Imagery, Szeged, Hungary.","DOI":"10.1007\/11907350_27"},{"key":"ref_12","unstructured":"Hukkanen, J., Hategan, A., Sabo, E., and Tabus, I. (2010, January 23\u201327). Segmentation of cell nuclei from histological images by ellipse fitting. Proceedings of the 18th European Signal Processing Conference, Aalborg, Denmark."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5942","DOI":"10.1109\/TIP.2015.2492828","article-title":"Segmentation of overlapping elliptical objects in silhouette images","volume":"24","author":"Zafari","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.ces.2013.02.043","article-title":"Development of an image measurement technique for size distribution in dense bubbly flows","volume":"94","author":"Lau","year":"2013","journal-title":"Chem. Eng. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1016\/j.patrec.2012.03.027","article-title":"A method for recognizing overlapping elliptical bubbles in bubble image","volume":"33","author":"Zhang","year":"2012","journal-title":"Pattern Recognit. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zafari, S., Eerola, T., Sampo, J., K\u00e4lvi\u00e4inen, H., and Haario, H. (2017, January 20\u201324). Segmentation of partially overlapping convex objects using branch and bound algorithm. Proceedings of the Asian Conference on Computer Vision, Taiwan, China.","DOI":"10.1007\/978-3-319-54526-4_6"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.ifacol.2016.10.101","article-title":"Flotation froth image analysis by use of a dynamic feature extraction algorithm","volume":"49","author":"Fu","year":"2016","journal-title":"IFAC PapersOnLine"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s00348-006-0159-0","article-title":"Semi-automatic image analysis methodology for the segmentation of bubbles and drops in complex dispersions occurring in bioreactors","volume":"41","author":"Taboada","year":"2006","journal-title":"Exp. Fluids"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.patrec.2017.11.014","article-title":"Comparison of bubble detectors and size distribution estimators","volume":"101","author":"Ilonen","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"072002","DOI":"10.1088\/1742-6596\/754\/7\/072002","article-title":"Artificial neural network for bubbles pattern recognition on the images","volume":"754","author":"Poletaev","year":"2016","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"103194","DOI":"10.1016\/j.ijmultiphaseflow.2019.103194","article-title":"Bubble patterns recognition using neural networks: Application to the analysis of a two-phase bubbly jet","volume":"126","author":"Poletaev","year":"2020","journal-title":"Int. J. Multiph. Flow"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"115467","DOI":"10.1016\/j.ces.2019.115467","article-title":"BubCNN: Bubble detection using Faster RCNN and shape regression network","volume":"216","author":"Haas","year":"2020","journal-title":"Chem. Eng. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"116163","DOI":"10.1016\/j.ces.2020.116163","article-title":"Development of a deep learning-based image processing technique for bubble pattern recognition and shape reconstruction in dense bubbly flows","volume":"230","author":"Cerqueira","year":"2021","journal-title":"Chem. Eng. Sci."},{"key":"ref_24","unstructured":"Hernandez, J. (2002, January 22\u201324). A technique for the direct measurement of bubble size distributions in industrial flotation cells. Proceedings of the 34th Annual Meeting of the Canadian Mineral Processors, Ottawa, ON, Canada."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1860","DOI":"10.1007\/s00348-014-1860-z","article-title":"Size distribution measurement for densely binding bubbles via image analysis","volume":"55","author":"Ma","year":"2014","journal-title":"Exp. Fluids"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.minpro.2007.03.002","article-title":"Correspondence of gas holdup and bubble size in presence of different frothers","volume":"83","author":"Azgomi","year":"2007","journal-title":"Int. J. Miner. Process."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Vinnett, L., Urriola, B., Orellana, F., Guajardo, C., and Esteban, A. (2022). Reducing the presence of clusters in bubble size measurements for gas dispersion characterizations. Minerals, 12.","DOI":"10.3390\/min12091148"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"9618","DOI":"10.1109\/TIM.2020.3006629","article-title":"Online monitoring of flotation froth bubble-size distributions via multiscale deblurring and multistage jumping feature-fused full convolutional networks","volume":"69","author":"Liu","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.ces.2019.04.004","article-title":"BubGAN: Bubble generative adversarial networks for synthesizing realistic bubbly flow images","volume":"204","author":"Fu","year":"2019","journal-title":"Chem. Eng. Sci."},{"key":"ref_30","unstructured":"Farhadi, A., and Redmon, J. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_31","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_36","unstructured":"Jocher, G. (2022, November 15). YOLOv5 by Ultralytics. Available online: https:\/\/zenodo.org\/record\/4418161."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_38","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 7\u201312 February 2020."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"106636","DOI":"10.1016\/j.mineng.2020.106636","article-title":"Assessment of two automated image processing methods to estimate bubble size in industrial flotation machines","volume":"159","author":"Vinnett","year":"2020","journal-title":"Miner. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., and Huang, T. (2016, January 15\u201319). Unitbox: An advanced object detection network. Proceedings of the 24th ACM International Conference on Multimedia, Amsterdam, The Netherlands.","DOI":"10.1145\/2964284.2967274"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15\u201320). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE conference on computer vision and pattern recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00075"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6582\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:16:42Z","timestamp":1760127402000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6582"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":41,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23146582"],"URL":"https:\/\/doi.org\/10.3390\/s23146582","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,21]]}}}