{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T15:43:21Z","timestamp":1764603801368,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T00:00:00Z","timestamp":1628726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["17H03314"],"award-info":[{"award-number":["17H03314"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Riverbed material has multiple functions in river ecosystems, such as habitats, feeding grounds, spawning grounds, and shelters for aquatic organisms, and particle size of riverbed material reflects the tractive force of the channel flow. Therefore, regular surveys of riverbed material are conducted for environmental protection and river flood control projects. The field method is the most conventional riverbed material survey. However, conventional surveys of particle size of riverbed material require much labor, time, and cost to collect material on site. Furthermore, its spatial representativeness is also a problem because of the limited survey area against a wide riverbank. As a further solution to these problems, in this study, we tried an automatic classification of riverbed conditions using aerial photography with an unmanned aerial vehicle (UAV) and image recognition with artificial intelligence (AI) to improve survey efficiency. Due to using AI for image processing, a large number of images can be handled regardless of whether they are of fine or coarse particles. We tried a classification of aerial riverbed images that have the difference of particle size characteristics with a convolutional neural network (CNN). GoogLeNet, Alexnet, VGG-16 and ResNet, the common pre-trained networks, were retrained to perform the new task with the 70 riverbed images using transfer learning. Among the networks tested, GoogleNet showed the best performance for this study. The overall accuracy of the image classification reached 95.4%. On the other hand, it was supposed that shadows of the gravels caused the error of the classification. The network retrained with the images taken in the uniform temporal period gives higher accuracy for classifying the images taken in the same period as the training data. The results suggest the potential of evaluating riverbed materials using aerial photography with UAV and image recognition with CNN.<\/jats:p>","DOI":"10.3390\/rs13163188","type":"journal-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T10:54:41Z","timestamp":1628765681000},"page":"3188","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Differentiation of River Sediments Fractions in UAV Aerial Images by Convolution Neural Network"],"prefix":"10.3390","volume":"13","author":[{"given":"Hitoshi","family":"Takechi","sequence":"first","affiliation":[{"name":"Blue Innovation Co., Ltd., Tokyo 113-0033, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5309-3149","authenticated-orcid":false,"given":"Shunsuke","family":"Aragaki","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, School of Engineering, University of Miyazaki, Miyazaki 889-2192, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5291-5435","authenticated-orcid":false,"given":"Mitsuteru","family":"Irie","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Miyazaki, Miyazaki 889-2192, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,12]]},"reference":[{"key":"ref_1","unstructured":"David, A.J., and Castillo, M.M. (2007). Stream Ecology: Structure and Function of Running Waters, Springer. [2nd ed.]."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"105726","DOI":"10.1016\/j.ecoleng.2020.105726","article-title":"Preliminary assessment of the impacts of sediment sluicing events on stream insects in the Mimi River, Japan","volume":"145","author":"Nukazawa","year":"2020","journal-title":"Ecol. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kang, T., Kimura, I., and Shimizu, Y. (2018). Responses of bed morphology to vegetation growth and flood discharge at a sharp river bend. Water, 10.","DOI":"10.3390\/w10020223"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1002\/2014WR016539","article-title":"Chute cutoff as a morphological response to stream reconstruction: The possible role of backwater","volume":"51","author":"Eekhout","year":"2015","journal-title":"Water Resour. Res."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Bunte, K., and Abt, S.R. (2001). Sampling Surface and Subsurface Particle-Size Distributions in Wadable Gravel- and Cobble-Bed Streams for Analyses in Sediment Transport, Hydraulics, and Streambed Monitoring, U. S. Department of Agriculture. General Technical Report RMRS-GTR-74.","DOI":"10.2737\/RMRS-GTR-74"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1061\/JYCEAJ.0003044","article-title":"Sampling procedure for Coarse Fluvial Sediments","volume":"97","author":"Kellerhals","year":"1971","journal-title":"J. Hydraul. Div. ASCE"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"W02508","DOI":"10.1029\/2008WR006940","article-title":"Maximizing the accuracy of image-based surface sediment sampling techniques","volume":"46","author":"Graham","year":"2010","journal-title":"Water Resour. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1599","DOI":"10.1577\/T04-146.1","article-title":"Comment: Photographic Techniques for Characterizing Streambed Particle Sizes","volume":"134","author":"Graham","year":"2005","journal-title":"Trans. Am. Fish. Soc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1061\/JYCEAJ.0005283","article-title":"Gravel size analysis from photographs","volume":"105","author":"Adams","year":"1979","journal-title":"J. Hydraul. Div. ASCE"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.sedgeo.2008.06.007","article-title":"Estimation of grain size distributions and associated parameters from digital images of sediment","volume":"210","author":"Buscombe","year":"2008","journal-title":"Sediment. Geol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1811","DOI":"10.1002\/esp.1877","article-title":"Cobble cam: Grain-size measurements of sand to boulder from digital photographs and autocorrelation analyses","volume":"34","author":"Warrick","year":"2009","journal-title":"Earth Surf. Process Landf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/S0168-1699(02)00101-1","article-title":"Inspection and grading of agricultural and food products by computer vision systems\u2014A review","volume":"36","author":"Brosnan","year":"2002","journal-title":"Comput. Electron. Agric."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.powtec.2009.07.024","article-title":"Machine vision based particle size and size distribution determination of airborne dust particles of wood and bark pellets","volume":"196","author":"Igathinathane","year":"2009","journal-title":"Powder Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"19461","DOI":"10.1039\/D0NR04140H","article-title":"Machine vision-driven automatic recognition of particle size and morphology in SEM images","volume":"12","author":"Kim","year":"2020","journal-title":"Nanoscale"},{"key":"ref_15","unstructured":"Bankman, I.N. (2009). Handbook of Medical Imaging: Processing and Analysis, Elsevier."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1186\/s40537-019-0276-2","article-title":"Deep convolutional neural network based medical image classification for disease diagnosis","volume":"6","author":"Yadav","year":"2019","journal-title":"J. Big Data"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sarvamangala, D.R., and Kulkarni, R.V. (2021). Convolutional neural networks in medical image understanding: A survey. Evol. Intell.","DOI":"10.1007\/s12065-020-00540-3"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kandel, I., and Castelli, M. (2020). Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification. A Review. Appl. Sci., 10.","DOI":"10.3390\/app10062021"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Gilcher, M., and Udelhoven, T. (2021). Field Geometry and the Spatial and Temporal Generalization of Crop Classification Algorithms\u2014A Randomized Approach to Compare Pixel Based and Convolution Based Methods. Remote Sens., 13.","DOI":"10.3390\/rs13040775"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Taravat, A., Wagner, M.P., Bonifacio, R., and Petit, D. (2021). Advanced Fully Convolutional Networks for Agricultural Field Boundary Detection. Remote Sens., 13.","DOI":"10.3390\/rs13040722"},{"key":"ref_21","first-page":"59","article-title":"Vegetation classification using a small UAV based on superpixel segmentation and machine learning","volume":"36","author":"Suzuki","year":"2016","journal-title":"J. Remote Sens. Soc. Jpn."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Takahashi, H., Tampo, H., Arai, Y., Inoue, Y., and Kawashima, H. (2017). Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0179790"},{"key":"ref_23","unstructured":"(2020, September 28). Technical Standards for River Erosion Control\u2014Research Version-4. Available online: https:\/\/www.mlit.go.jp\/river\/shishin_guideline\/gijutsu\/gijutsukijunn\/chousa\/."},{"key":"ref_24","first-page":"141","article-title":"Grain size distribution research method, in rivers having wide grain distribution, including cobbles and boulders","volume":"13","author":"Yamazaki","year":"2007","journal-title":"Adv. River Eng."},{"key":"ref_25","first-page":"351","article-title":"Possibility of bed material investigation using image analysis","volume":"6","author":"Okada","year":"2000","journal-title":"Proc. River Eng. JSCE"},{"key":"ref_26","unstructured":"Mu\u00f1os, R.M. (2012). Automatic object detection to analyze the geometry of gravel grains\u2014A free stand-alone tool. River Flow 2012, Taylor & Francis Group."},{"key":"ref_27","first-page":"67","article-title":"Development of bed topography survey technique by underwater imaging progress for UAV photogrammetry","volume":"22","author":"Harada","year":"2016","journal-title":"Proc. River Eng."},{"key":"ref_28","first-page":"I_919","article-title":"Measurement of grain size distributions of a cobble bar before and after flood by using images taken from an UAV","volume":"71","author":"Terada","year":"2015","journal-title":"Annu. J. Hydraul. Eng. JSCE"},{"key":"ref_29","unstructured":"Sumi, T., Yoshimura, T., Asazaki, K., Kaku, M., Kashiwai, J., and Sato, T. (2015, January 14\u201320). Retrofitting and change in operation of cascade dams to facilitate sediment sluicing in the Mimikawa river basin. Proceedings of the 25rd Congress of International Commission on Large Dams, Stavanger, Norway. Q99-R45."},{"key":"ref_30","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). ImageNet classification with deep convolutional neural networks. Proceedings of the 25th Intl. Conference on Neural Inform. Process. Sys. (NIPS\u201912), Lake Tahoe, NV, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_32","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very deep convolution network for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA. arXiv:1409.1556."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7\u201312). Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","unstructured":"(2020, September 28). ImageNet Website. Available online: http:\/\/image-net.org\/."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L., Malik, J., and Savarese, S. (2018, January 18\u201323). Taskonomy: Disentangling Task Transfer Learning. Proceedings of the 2018 IEEE\/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref_36","first-page":"1104","article-title":"Einfache Bestimmung der Korngr\u00f6ssenverteilung von Geschiebematerial mit Hilfe der Linienzahlanalyse (Simple detection of grain size distribution of sediment material using line-count analysis)","volume":"105","author":"Fehr","year":"1987","journal-title":"Schweiz. Ing. Architekt."},{"key":"ref_37","unstructured":"Lillesand, M.T., and Ralph, K.W. (1994). Remote Sensing and Image Interpretation, John Wiley & Sons, Inc."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, X., Hui, L., and Yang, J. (2018, January 18\u201323). Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00192"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Qu, L., Tian, J., He, S., Tang, Y., and Lau, R.W.H. (2017, January 21\u201326). DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.248"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/16\/3188\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:44:34Z","timestamp":1760165074000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/16\/3188"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,12]]},"references-count":39,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["rs13163188"],"URL":"https:\/\/doi.org\/10.3390\/rs13163188","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2021,8,12]]}}}