{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:57:09Z","timestamp":1779238629598,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,4]],"date-time":"2021-10-04T00:00:00Z","timestamp":1633305600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,4]],"date-time":"2021-10-04T00:00:00Z","timestamp":1633305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Conselho Nacional de Desenvolvimento Cient\\'{i}fico e Tecnol\\'{o}gico"},{"name":"Funda\\c{c}\\~{a}o de Amparo \\`{a} Pesquisa do Estado do Rio Grande do Sul"},{"name":"ANP-PRH 27"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Braz Comput Soc"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Image segmentation is an important step in many computer vision and image processing algorithms. It is often adopted in tasks such as object detection, classification, and tracking. The segmentation of underwater images is a challenging problem as the water and particles present in the water scatter and absorb the light rays. These effects make the application of traditional segmentation methods cumbersome. Besides that, to use the state-of-the-art segmentation methods to face this problem, which are based on deep learning, an underwater image segmentation dataset must be proposed. So, in this paper, we develop a dataset of real underwater images, and some other combinations using simulated data, to allow the training of two of the best deep learning segmentation architectures, aiming to deal with segmentation of underwater images in the wild. In addition to models trained in these datasets, fine-tuning and image restoration strategies are explored too. To do a more meaningful evaluation, all the models are compared in the testing set of real underwater images. We show that methods obtain impressive results, mainly when trained with our real dataset, comparing with manually segmented ground truth, even using a relatively small number of labeled underwater training images.<\/jats:p>","DOI":"10.1186\/s13173-021-00117-7","type":"journal-article","created":{"date-parts":[[2021,10,4]],"date-time":"2021-10-04T17:20:06Z","timestamp":1633368006000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Underwater image segmentation in the wild using deep learning"],"prefix":"10.1186","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4376-9544","authenticated-orcid":false,"given":"Paulo","family":"Drews-Jr","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isadora de","family":"Souza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor P.","family":"Maurell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eglen V.","family":"Protas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvia S.","family":"C. Botelho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,4]]},"reference":[{"key":"117_CR1","doi-asserted-by":"publisher","unstructured":"Fabic JN, Turla IE, Capacillo JA, David LT, Naval PC (2013) Fish population estimation and species classification from underwater video sequences using blob counting and shape analysis In: 2013 IEEE International Underwater Technology Symposium (UT), 1\u20136. https:\/\/doi.org\/10.1109\/UT.2013.6519876.","DOI":"10.1109\/UT.2013.6519876"},{"key":"117_CR2","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1071\/PC19019","volume":"26","author":"JA Donaldson","year":"2019","unstructured":"Donaldson JA, Drews-Jr P, Bradley M, Morgan DL, Baker R, Ebner BC (2019) Countering low visibility in video survey of an estuarine fish assemblage. Pac Conserv Biol 26:190\u2013200.","journal-title":"Pac Conserv Biol"},{"key":"117_CR3","doi-asserted-by":"publisher","unstructured":"Drews-Jr P, Hern\u00e1ndez E, Elfes A, Nascimento ER, Campos M (2016) Real-time monocular obstacle avoidance using underwater dark channel prior In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 4672\u20134677. https:\/\/doi.org\/10.1109\/IROS.2016.7759687.","DOI":"10.1109\/IROS.2016.7759687"},{"key":"117_CR4","doi-asserted-by":"publisher","unstructured":"Gaya JO, Gon\u00e7alves LT, Duarte AC, Zanchetta B, Drews-Jr P, Botelho SSC (2016) Vision-based obstacle avoidance using deep learning In: 2016 XIII Latin American Robotics Symposium and IV Brazilian Robotics Symposium (LARS\/SBR), 7\u201312. https:\/\/doi.org\/10.1109\/LARS-SBR.2016.9.","DOI":"10.1109\/LARS-SBR.2016.9"},{"key":"117_CR5","doi-asserted-by":"publisher","unstructured":"Schechner YY, Karpel N (2004) Clear underwater vision In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), I-I. https:\/\/doi.org\/10.1109\/CVPR.2004.1315078.","DOI":"10.1109\/CVPR.2004.1315078"},{"key":"117_CR6","doi-asserted-by":"publisher","unstructured":"Drews-Jr P, do Nascimento E, Moraes F, Botelho S, Campos M (2013) Transmission estimation in underwater single images In: 2013 IEEE International Conference on Computer Vision Workshops, 825\u2013830. https:\/\/doi.org\/10.1109\/ICCVW.2013.113.","DOI":"10.1109\/ICCVW.2013.113"},{"issue":"12","key":"117_CR7","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(12):2481\u20132495. https:\/\/doi.org\/10.1109\/TPAMI.2016.2644615.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"117_CR8","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big Data 3(1):9. https:\/\/doi.org\/10.1186\/s40537-016-0043-6.","journal-title":"J Big Data"},{"key":"117_CR9","doi-asserted-by":"publisher","unstructured":"Cimpoi M, Maji S, Vedaldi A (2015) Deep filter banks for texture recognition and segmentation In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3828\u20133836. https:\/\/doi.org\/10.1109\/CVPR.2015.7299007.","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"117_CR10","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"117_CR11","doi-asserted-by":"publisher","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431\u20133440. https:\/\/doi.org\/10.1109\/CVPR.2015.7298965.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"117_CR12","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick RB (2017) Mask R-CNN. CoRR abs\/1703.06870. http:\/\/arxiv.org\/abs\/1703.06870.","DOI":"10.1109\/ICCV.2017.322"},{"key":"117_CR13","first-page":"91","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1, NIPS\u201915","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks In: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1, NIPS\u201915, 91\u201399.. MIT Press, Cambridge. http:\/\/dl.acm.org\/citation.cfm?id=2969239.2969250."},{"key":"117_CR14","unstructured":"Chen L, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. CoRR abs\/1706.05587. http:\/\/arxiv.org\/abs\/1706.05587."},{"key":"117_CR15","doi-asserted-by":"publisher","unstructured":"Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation:801\u2013818. https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"117_CR16","first-page":"118","volume":"2","author":"RK Rai","year":"2012","unstructured":"Rai RK, Gour P, Singh B (2012) Underwater image segmentation using clahe enhancement and thresholding. Int J Emerging Technol Adv Eng 2:118\u2013123.","journal-title":"Int J Emerging Technol Adv Eng"},{"key":"117_CR17","first-page":"459","volume":"7","author":"E Kim","year":"2013","unstructured":"Kim E, Lee S (2013) Comparative studies of remove background algorithms for objects extraction of underwater images. Int J Softw Eng Appl 7:459\u2013468.","journal-title":"Int J Softw Eng Appl"},{"key":"117_CR18","doi-asserted-by":"publisher","unstructured":"Zhang R, Liu J (2006) Underwater image segmentation with maximum entropy based on particle swarm optimization (pso) In: First International Multi-Symposiums on Computer and Computational Sciences (IMSCCS\u201906), 360\u2013636. https:\/\/doi.org\/10.1109\/IMSCCS.2006.280.","DOI":"10.1109\/IMSCCS.2006.280"},{"issue":"1","key":"117_CR19","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/s11804-011-1043-8","volume":"10","author":"S Wang","year":"2011","unstructured":"Wang S, Xu Y, Pang Y (2011) A fast underwater optical image segmentation algorithm based on a histogram weighted fuzzy c-means improved by pso. J Mar Sci Appl 10(1):70\u201375. https:\/\/doi.org\/10.1007\/s11804-011-1043-8.","journal-title":"J Mar Sci Appl"},{"key":"117_CR20","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.future.2016.03.004","volume":"65","author":"X Li","year":"2016","unstructured":"Li X, Song J, Zhang F, Ouyang X, Khan SU (2016) Mapreduce-based fast fuzzy c-means algorithm for large-scale underwater image segmentation. Futur Gener Comput Syst 65:90\u2013101. https:\/\/doi.org\/10.1016\/j.future.2016.03.004. Special Issue on Big Data in the Cloud.","journal-title":"Futur Gener Comput Syst"},{"key":"117_CR21","first-page":"2166","volume":"23","author":"M Rajasekar","year":"2015","unstructured":"Rajasekar M, Aruldoss CK, Anto Bennet M (2015) Underwater k-means clustering segmentation using svm classification. Middle-East J Sci Res 23:2166\u20132172.","journal-title":"Middle-East J Sci Res"},{"key":"117_CR22","first-page":"1","volume":"80","author":"W Chen","year":"2021","unstructured":"Chen W, He C, Ji C, Zhang M, Chen S (2021) An improved k-means algorithm for underwater image background segmentation. Multimedia Tools Appl 80:1\u201325.","journal-title":"Multimedia Tools Appl"},{"key":"117_CR23","doi-asserted-by":"publisher","unstructured":"Liu Y, Li H (2020) Design of refined segmentation model for underwater images In: 2020 5th International Conference on Communication, Image and Signal Processing (CCISP), 282\u2013287. https:\/\/doi.org\/10.1109\/CCISP51026.2020.9273503.","DOI":"10.1109\/CCISP51026.2020.9273503"},{"key":"117_CR24","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/978-3-319-54430-4_25","volume-title":"Intelligent Information and Database Systems","author":"AB Labao","year":"2017","unstructured":"Labao AB, Naval PC (2017) Weakly-labelled semantic segmentation of fish objects in underwater videos using a deep residual network. In: Nguyen NT, Tojo S, Nguyen LM, Trawi\u0144ski B (eds)Intelligent Information and Database Systems, 255\u2013265.. Springer, Cham."},{"key":"117_CR25","doi-asserted-by":"publisher","unstructured":"Zivkovic Z (2004) Improved adaptive gaussian mixture model for background subtraction In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, 28\u2013312. https:\/\/doi.org\/10.1109\/ICPR.2004.1333992.","DOI":"10.1109\/ICPR.2004.1333992"},{"key":"117_CR26","doi-asserted-by":"publisher","unstructured":"Chen Z, Zhang Z, Bu Y, Dai F, Fan T, Wang H (2018) Underwater object segmentation based on optical features. Sensors 18(1). https:\/\/doi.org\/10.3390\/s18010196.","DOI":"10.3390\/s18010196"},{"issue":"2","key":"117_CR27","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1109\/TIP.2010.2066982","volume":"20","author":"MB Salah","year":"2011","unstructured":"Salah MB, Mitiche A, Ayed IB (2011) Multiregion image segmentation by parametric kernel graph cuts. IEEE Trans Image Process 20(2):545\u2013557. https:\/\/doi.org\/10.1109\/TIP.2010.2066982.","journal-title":"IEEE Trans Image Process"},{"key":"117_CR28","doi-asserted-by":"publisher","unstructured":"Ancuti C, Ancuti CO, Haber T, Bekaert P (2012) Enhancing underwater images and videos by fusion In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 81\u201388. https:\/\/doi.org\/10.1109\/CVPR.2012.6247661.","DOI":"10.1109\/CVPR.2012.6247661"},{"key":"117_CR29","doi-asserted-by":"publisher","unstructured":"McGlamery BL (1980) A computer model for underwater camera systems In: Proceedings of SPIE, 221\u2013231. https:\/\/doi.org\/10.1117\/12.958279.","DOI":"10.1117\/12.958279"},{"issue":"2","key":"117_CR30","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/48.50695","volume":"15","author":"JS Jaffe","year":"1990","unstructured":"Jaffe JS (1990) Computer modeling and the design of optimal underwater imaging systems. IEEE J Ocean Eng 15(2):101\u2013111. https:\/\/doi.org\/10.1109\/48.50695.","journal-title":"IEEE J Ocean Eng"},{"key":"117_CR31","doi-asserted-by":"publisher","unstructured":"Gon\u00e7alves L, Gaya J, Drews-Jr P, Botelho S (2017) Deepdive: an end-to-end dehazing method using deep learning In: 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 436\u2013441. https:\/\/doi.org\/10.1109\/SIBGRAPI.2017.64.","DOI":"10.1109\/SIBGRAPI.2017.64"},{"issue":"3","key":"117_CR32","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1109\/JOE.2005.850871","volume":"30","author":"YY Schechner","year":"2005","unstructured":"Schechner YY, Karpel N (2005) Recovery of underwater visibility and structure by polarization analysis. IEEE J Ocean Eng 30(3):570\u2013587.","journal-title":"IEEE J Ocean Eng"},{"key":"117_CR33","doi-asserted-by":"publisher","unstructured":"Duarte A, Codevilla F, Gaya JDO, Botelho SSC (2016) A dataset to evaluate underwater image restoration methods In: OCEANS 2016 - Shanghai, 1\u20136. https:\/\/doi.org\/10.1109\/OCEANSAP.2016.7485524.","DOI":"10.1109\/OCEANSAP.2016.7485524"},{"key":"117_CR34","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C (eds)Computer Vision \u2013 ECCV 2012, 746\u2013760.. Springer, Berlin."},{"key":"117_CR35","unstructured":"Simonyan K, Zisserman A (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. In: Bengio Y LeCun Y (eds)3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409.1556. Accessed 17 July 2019."},{"key":"117_CR36","unstructured":"Kingma DP, Ba J (2015) Adam: A Method for Stochastic Optimization. In: Bengio Y LeCun Y (eds)3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1412.6980. Accessed 25 July 2019."},{"issue":"2","key":"117_CR37","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The Pascal Visual Object Classes (VOC) Challenge. Int J Comput Vis 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4.","journal-title":"Int J Comput Vis"},{"key":"117_CR38","doi-asserted-by":"publisher","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr.2017.195.","DOI":"10.1109\/cvpr.2017.195"},{"issue":"2","key":"117_CR39","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/MCG.2016.26","volume":"36","author":"P Drews-Jr","year":"2016","unstructured":"Drews-Jr P, Nascimento E, Botelho S, Campos M (2016) Underwater depth estimation and image restoration based on single images. IEEE Comput Graphics Appl 36(2):24\u201335. https:\/\/doi.org\/10.1109\/MCG.2016.26.","journal-title":"IEEE Comput Graphics Appl"},{"key":"117_CR40","doi-asserted-by":"publisher","unstructured":"Fabbri C, Islam MJ, Sattar J (2018) Enhancing underwater imagery using generative adversarial networks In: 2018 IEEE International Conference on Robotics and Automation (ICRA), 7159\u20137165.. IEEE. https:\/\/doi.org\/10.1109\/icra.2018.8460552.","DOI":"10.1109\/icra.2018.8460552"},{"key":"117_CR41","doi-asserted-by":"publisher","unstructured":"Ledig C, Theis L, Huszar F, Caballero J, Aitken A, Tejani A, Totz J, Wang Z, Shi WE (2016) Photo-realistic single image super-resolution using a generative adversarial network. CoRR abs\/1609.04802. https:\/\/doi.org\/10.1109\/cvpr.2017.19.","DOI":"10.1109\/cvpr.2017.19"}],"container-title":["Journal of the Brazilian Computer Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13173-021-00117-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13173-021-00117-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13173-021-00117-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T10:46:13Z","timestamp":1723545973000},"score":1,"resource":{"primary":{"URL":"https:\/\/journal-bcs.springeropen.com\/articles\/10.1186\/s13173-021-00117-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,4]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["117"],"URL":"https:\/\/doi.org\/10.1186\/s13173-021-00117-7","relation":{},"ISSN":["0104-6500","1678-4804"],"issn-type":[{"value":"0104-6500","type":"print"},{"value":"1678-4804","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,4]]},"assertion":[{"value":"29 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12"}}