{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:44:20Z","timestamp":1777704260333,"version":"3.51.4"},"reference-count":38,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2018,6,20]],"date-time":"2018-06-20T00:00:00Z","timestamp":1529452800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2018,10]]},"abstract":"<jats:p>Image segmentation, which becomes more and more prevalent in computer vision, plays a requisite part in the fields of object detection, tracking and even virtual or augmented reality. Early segmentation methods that relied on hand-crafted features have fast been superseded by deep learning algorithms. Nonetheless, deep learning algorithms are hardly applied in real object segmentation because of a lack of ground truth labels. This work introduces the use of 3D models to generate segmentation training dataset. This system projects 3D models to the 2D plane and merges 2D images with different backgrounds to obtain training images. In this process, the ground truth labels would be allowed to obtain automatically without manual annotation, since the position of objects is known in the picture. Experimental results indicate that synthetic images can be used to train on existed networks such as FCNs and DeepLab and trained models achieve relatively accurate segmentation results on real images. Moreover, the modified model based on DeepLab-CRF-LargeFOV achieves more precise segmentation results by strengthening its localization and edge performance.<\/jats:p>","DOI":"10.3233\/jifs-171675","type":"journal-article","created":{"date-parts":[[2018,10,2]],"date-time":"2018-10-02T14:32:37Z","timestamp":1538490757000},"page":"3233-3242","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Object segmentation using FCNs trained on synthetic images"],"prefix":"10.1177","volume":"35","author":[{"given":"Bowen","family":"Yang","sequence":"first","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"given":"Xiaosheng","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]}],"member":"179","published-online":{"date-parts":[[2018,6,20]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"549","article-title":"Whats the point: Semantic segmentation with point supervision","author":"Bearman A.","year":"2016","unstructured":"BearmanA., RussakovskyO., FerrariV. and LiF.F., Whats the point: Semantic segmentation with point supervision, In European Conference on Computer Vision (2016), pp. 549\u2013565.","journal-title":"In European Conference on Computer Vision"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050290"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"FulkersonB. VedaldiA. and SoattoS. Class segmentation and object localization with superpixel neighborhoods (2009) pp. 670\u2013677.","DOI":"10.1109\/ICCV.2009.5459175"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"HariharanB. ArbelaezP. BourdevL.D. MajiS. and MalikJ. Semantic contours from inverse detectors (2011) pp. 991\u2013998.","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/360825.360839"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"e_1_3_2_8_2","unstructured":"WuC. Visualsfm: A visual structure from motion system http:\/\/ccwu.me\/vsfm\/ 2013."},{"key":"e_1_3_2_9_2","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy C.","year":"2015","unstructured":"SzegedyC., LiuW., JiaY., SermanetP., ReedS.E., AnguelovD., ErhanD., VanhouckeV. and RabinovichA., Going deeper with convolutions, Computer Vision and Pattern Recognition (2015), 1\u20139.","journal-title":"Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"KuettelD. GuillauminM. and FerrariV. Segmentation propagation in imagenet In European Conference on Computer Vision 2012 459\u2013473.","DOI":"10.1007\/978-3-642-33786-4_34"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"LinD. DaiJ. JiaJ. HeK. and SunJ. Scribblesup: Scribblesupervised convolutional networks for semantic segmentation (2016) pp. 3159\u20133167.","DOI":"10.1109\/CVPR.2016.344"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"RosG. SellartL. MaterzynskaJ. VazquezD. and LopezA.M. The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes (2016) pp. 3234\u20133243.","DOI":"10.1109\/CVPR.2016.352"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"RahmaniH. and MianA. 3d action recognition from novel viewpoints In Computer Vision and Pattern Recognition (2016) 1506\u20131515.","DOI":"10.1109\/CVPR.2016.167"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"LongJ. ShelhamerE. and DarrellT. Fully convolutional networks for semantic segmentation Computer Vision and Pattern Recognition 79(10) (2015) 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"PaponJ. and SchoelerM. Semantic pose using deep networks trained on synthetic rgb-d 8(8) (2015) 774\u2013782.","DOI":"10.1109\/ICCV.2015.95"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0109-1"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"ShottonJ. JohnsonM. and CipollaR. Semantic texton forests for image categorization and segmentation (2008) pp. 1\u20138.","DOI":"10.1109\/CVPR.2008.4587503"},{"key":"e_1_3_2_18_2","unstructured":"SimonyanK. and ZissermanA. Very deep convolutional networks for large-scale image recognition Computer Science (2014)."},{"key":"e_1_3_2_19_2","first-page":"3570","article-title":"Parsing clothing in fashion photographs","author":"Yamaguchi K.","year":"2012","unstructured":"YamaguchiK., KiapourM.H., OrtizL.E. and BergT.L., Parsing clothing in fashion photographs, In IEEE Conference on Computer Vision and Pattern Recognition (2012), 3570\u20133577.","journal-title":"In IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"CastrejonL. KunduK. UrtasunR. and FidlerS. Annotating object instances with a polygon-rnn arXiv preprint arXiv:1704.05548 2017.","DOI":"10.1109\/CVPR.2017.477"},{"key":"e_1_3_2_21_2","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"Chen L.","year":"2015","unstructured":"ChenL., PapandreouG., KokkinosI., MurphyK. and YuilleA.L., Semantic image segmentation with deep convolutional nets and fully connected crfs, International Conference on Learning Tepresentations,2015.","journal-title":"International Conference on Learning Tepresentations"},{"key":"e_1_3_2_22_2","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen L.","year":"2017","unstructured":"ChenL., PapandreouG., KokkinosI., MurphyK. and YuilleA.L., Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE Transactions on Pattern Analysis and Machine Intelligence,2017.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_23_2","unstructured":"ChenL. PapandreouG. SchroffF. and AdamH. Rethinking atrous convolution for semantic image segmentation arXiv preprint arXiv:1706.05587 2017."},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"VincentL. and SoilleP. Watersheds in digital spaces: An efficient algorithm based on immersion simulations IEEE Transactions on Pattern Analysis and Machine Intelligence 13(6) (1991) pp. 583\u2013598.","DOI":"10.1109\/34.87344"},{"key":"e_1_3_2_25_2","article-title":"The cityscapes dataset","author":"Cordts M.","unstructured":"CordtsM., OmranM., RamosS., ScharwaT.,\u00cc\u0139chter, En-zweilerM., BenensonR., FrankeU., RothS., and SchieleB., The cityscapes dataset, In CVPR Workshop on the Future of Datasets in Vision 2015,.","journal-title":"CVPR Workshop on the Future of Datasets in Vision 2015"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133570"},{"key":"e_1_3_2_28_2","article-title":"Deepcut: Object segmentation from bounding box annotations using convolutional neural networks","author":"Rajchl M.","year":"2016","unstructured":"RajchlM., LeeM., OktayO., KamnitsasK., Passerat-PalmbachJ., BaiW., RutherfordM., HajnalJ., KainzB., and RueckertD., Deepcut: Object segmentation from bounding box annotations using convolutional neural networks, IEEE Transactions on Medical Imaging, 2016.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_3_2_29_2","unstructured":"CignoniP. CallieriM. CorsiniM. DellepianeM. GanovelliF. and RanzugliaG. MeshLab: An Open-Source Mesh Processing Tool In ScaranoV. ChiaraR.D. and ErraU. editors Eurographics Italian Chapter Conference The Eurographics Association 2008."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095851"},{"key":"e_1_3_2_31_2","unstructured":"KrhenbhlP. and KoltunV. Efficient inference in fully connected crfs with gaussian edge potentials (2011) pp. 109\u2013117."},{"key":"e_1_3_2_32_2","unstructured":"RajpuraP.S. HegdeR.S. and BojinovH. Object detection using deep cnns trained on synthetic images 2017."},{"key":"e_1_3_2_33_2","first-page":"1529","article-title":"Conditional random fields as recurrent neural networks","author":"Zheng S.","year":"2015","unstructured":"ZhengS., JayasumanaS., RomeraparedesB., VineetV., SuZ., DuD., HuangC. and TorrP.H.S., Conditional random fields as recurrent neural networks, In IEEE International Conference on Computer Vision (2015), pp. 1529\u20131537.","journal-title":"IEEE International Conference on Computer Vision"},{"key":"e_1_3_2_34_2","unstructured":"ZhouS. N.WuJ. WuY. and ZhouX. Exploiting local structures with the kronecker layer in convolutional networks arXiv preprint arXiv: Computer Vision and Pattern Recognition 2015."},{"key":"e_1_3_2_35_2","first-page":"259","article-title":"Blue screen matting","author":"Smith","year":"1996","unstructured":"Smith, RayA., Blinn, and JamesF., Blue screen matting, Acm Siggraph Computer Graphics (1996), 259\u2013268.","journal-title":"Acm Siggraph Computer Graphics"},{"key":"e_1_3_2_36_2","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin T.","year":"2014","unstructured":"LinT., MaireM., BelongieS.J., HaysJ., PeronaP., RamananD., DollarP. and ZitnickC.L., Microsoft coco: Common objects in context, European Conference on Computer Vision (2014), pp. 740\u2013755.","journal-title":"European Conference on Computer Vision"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"BadrinarayananV. KendallA. and CipollaR. Segnet: A deep convolutional encoder-decoder architecture for image segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence 2017.","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_3_2_39_2","first-page":"675","article-title":"Caffe: Convolutional architecture for fast feature embedding","author":"Jia Y.","year":"2014","unstructured":"JiaY., ShelhamerE., DonahueJ., KarayevS., LongJ., GirshickR.B., GuadarramaS. and DarrellT., Caffe: Convolutional architecture for fast feature embedding, Acm Multimedia (2014), 675\u2013678.","journal-title":"Acm Multimedia"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-171675","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-171675","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-171675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:40:48Z","timestamp":1777455648000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-171675"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,20]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["10.3233\/JIFS-171675"],"URL":"https:\/\/doi.org\/10.3233\/jifs-171675","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,20]]}}}