{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T10:13:43Z","timestamp":1782814423501,"version":"3.54.5"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62263023"],"award-info":[{"award-number":["62263023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00371-024-03342-1","type":"journal-article","created":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T22:01:41Z","timestamp":1711058501000},"page":"481-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Combining YOLO and background subtraction for small dynamic target detection"],"prefix":"10.1007","volume":"41","author":[{"given":"Jian","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengwen","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,21]]},"reference":[{"issue":"7","key":"3342_CR1","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1109\/TNNLS.2019.2933590","volume":"31","author":"MJ Zhang","year":"2019","unstructured":"Zhang, M.J., Wang, N.N., Li, Y.S., Gao, X.B.: Neural probabilistic graphical model for face sketch synthesis. IEEE Trans. Neural Netw. Learn. Syst. 31(7), 2623\u20132637 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"10","key":"3342_CR2","doi-asserted-by":"publisher","first-page":"3109","DOI":"10.1109\/TNNLS.2018.2890017","volume":"30","author":"MJ Zhang","year":"2019","unstructured":"Zhang, M.J., Wang, N.N., Li, Y.S., Gao, X.B.: Deep latent low-rank representation for face sketch synthesis. IEEE Trans. Neural Netw. Learn. Syst. 30(10), 3109\u20133123 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3342_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104229","volume":"112","author":"RF Mansour","year":"2021","unstructured":"Mansour, R.F., Escorcia-Gutierrez, J., Gamarra, M., Villanueva, J.A., Leal, N.: Intelligent video anomaly detection and classification using faster RCNN with deep reinforcement learning mode. Image Vis. Comput. 112, 104229 (2021)","journal-title":"Image Vis. Comput."},{"key":"3342_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3118092","volume":"70","author":"XC Lu","year":"2021","unstructured":"Lu, X.C., Ji, J., Xing, Z.Q., Miao, Q.G.: Attention and feature fusion SSD for remote sensing object detection. IEEE Trans. Instrum. Meas. 70, 1\u20139 (2021)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"2","key":"3342_CR5","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TSMC.2020.3005231","volume":"52","author":"G Chen","year":"2020","unstructured":"Chen, G., Wang, H.T., Chen, K., Li, Z.J., Song, Z.D., Liu, Y.L., Chen, W.K., Knoll, A.: A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal. IEEE Trans. Syst. Man Cybern. Syst. 52(2), 936\u2013953 (2020)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"9","key":"3342_CR6","doi-asserted-by":"publisher","first-page":"4930","DOI":"10.3390\/su14094930","volume":"14","author":"L Zhao","year":"2022","unstructured":"Zhao, L., Zhi, L.Q., Zhao, C., Zheng, W.: Fire-YOLO: a small target object detection method for fire inspection. Sustainability 14(9), 4930 (2022)","journal-title":"Sustainability"},{"issue":"4","key":"3342_CR7","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.3390\/s23041865","volume":"23","author":"A Betti","year":"2023","unstructured":"Betti, A., Tucci, M.: YOLO-S: a lightweight and accurate YOLO-like Network for small target detection in aerial imagery. Sensors 23(4), 1865 (2023)","journal-title":"Sensors"},{"issue":"1","key":"3342_CR8","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"JJ Li","year":"2022","unstructured":"Li, J.J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D.D., Qi, J.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Industr. Inf. 18(1), 163\u2013173 (2022)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"1","key":"3342_CR9","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/TCI.2016.2629284","volume":"3","author":"Y Romano","year":"2016","unstructured":"Romano, Y., Isidoro, J., Milanfar, P.: RAISR: rapid and accurate image super resolution. IEEE Trans. Comput. Imag. 3(1), 110\u2013125 (2016)","journal-title":"IEEE Trans. Comput. Imag."},{"key":"3342_CR10","doi-asserted-by":"publisher","first-page":"56416","DOI":"10.1109\/ACCESS.2021.3072211","volume":"9","author":"ZZ Wang","year":"2021","unstructured":"Wang, Z.Z., Xie, K., Zhang, X.Y., Chen, H.Q., Wen, C., He, J.B.: Small-object detection based on yolo and dense block via image super-resolution. IEEE Access 9, 56416\u201356429 (2021)","journal-title":"IEEE Access"},{"key":"3342_CR11","doi-asserted-by":"crossref","unstructured":"Bai, Y.C., Zhang, Y.Q., Ding, M.L., Ghanem, B.: Sod-mtgan: Small object detection via multi-task generative adversarial network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 11217 206\u2013221 (2018)","DOI":"10.1007\/978-3-030-01261-8_13"},{"issue":"1","key":"3342_CR12","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/TCYB.2022.3163294","volume":"53","author":"MJ Zhang","year":"2022","unstructured":"Zhang, M.J., Wu, Q.Q., Zhang, J., Gao, X.B., Guo, J., Tao, D.C.: Fluid micelle network for image super-resolution reconstruction. IEEE Trans. Cybern. 53(1), 578\u2013591 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"3342_CR13","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1109\/JSTARS.2022.3140776","volume":"15","author":"Z Zakria","year":"2022","unstructured":"Zakria, Z., Deng, J., Kumar, R., Khokhar, M.S., Cai, J., Kumar, J.: Multiscale and direction target detecting in remote sensing images via modified YOLO-v4. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 15, 1039\u20131048 (2022)","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"3342_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021)","journal-title":"Expert Syst. Appl."},{"key":"3342_CR15","doi-asserted-by":"crossref","unstructured":"Lin, Y.T., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3342_CR16","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector. In: European conference on computer vision, Springer, Cham, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3342_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108490","volume":"105","author":"SJ Ji","year":"2023","unstructured":"Ji, S.J., Ling, Q.H., Han, F.: An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information. Comput. Electr. Eng. 105, 108490 (2023)","journal-title":"Comput. Electr. Eng."},{"key":"3342_CR18","doi-asserted-by":"crossref","unstructured":"Liang, Z.W., Shao, J., Zhang, D.Y., Gao, L.L.: Small object detection using deep feature pyramid networks. In: Advances in Multimedia Information Processing\u2013PCM 2018: 19th Pacific-Rim Conference on Multimedia, Hefei, China, September, 21\u201322, 2018, Proceedings, Part III 19 Springer International Publishing, pp. 554\u2013564 (2018)","DOI":"10.1007\/978-3-030-00764-5_51"},{"key":"3342_CR19","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S.Z., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"3342_CR20","doi-asserted-by":"publisher","first-page":"57951","DOI":"10.1109\/ACCESS.2023.3284062","volume":"11","author":"SH Wang","year":"2023","unstructured":"Wang, S.H., Wang, Y.D., Chang, Y.J., Zhao, R.K., She, Y.S.: EBSE-YOLO: high precision recognition algorithm for small target foreign object detection. IEEE Access 11, 57951\u201357964 (2023)","journal-title":"IEEE Access"},{"issue":"7","key":"3342_CR21","doi-asserted-by":"publisher","first-page":"2100631","DOI":"10.1002\/adts.202100631","volume":"5","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Wen, C.B.: SOD-YOLO: a small target defect detection algorithm for wind turbine blades based on improved YOLOv5. Adv. Theory Simul. 5(7), 2100631 (2022)","journal-title":"Adv. Theory Simul."},{"key":"3342_CR22","first-page":"1","volume":"61","author":"MJ Zhang","year":"2023","unstructured":"Zhang, M.J., Zhang, R., Zhang, J., Guo, J., Li, Y.S., Gao, X.B.: Dim2Clear network for infrared small target detection. IEEE Trans. Geosci. Remote Sens. 61, 1\u201314 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3342_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, M.J., Bai, H.C., Zhang, J., Zhang, R., Wang, C.Y., Guo, J., Gao, X.B.: Rkformer: Runge-kutta transformer with random-connection attention for infrared small target detection. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1730\u20131738 (2022)","DOI":"10.1145\/3503161.3547817"},{"key":"3342_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, M.J., Zhang, R., Yang, Y.X., Bai, H.C., Zhang, J., Guo, J.: ISNet: Shape matters for infrared small target detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 877\u2013886 (2022)","DOI":"10.1109\/CVPR52688.2022.00095"},{"key":"3342_CR25","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B.Y., Yue, Y.X., Li, Q.Q., Yan, J.J.: Grid r-cnn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7363\u20137372 (2019)","DOI":"10.1109\/CVPR.2019.00754"},{"key":"3342_CR26","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J., Johnson, J.: Mesh r-cnn. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9785\u20139795 (2019)","DOI":"10.1109\/ICCV.2019.00988"},{"key":"3342_CR27","doi-asserted-by":"publisher","first-page":"106135","DOI":"10.1016\/j.compag.2021.106135","volume":"185","author":"XL Hu","year":"2021","unstructured":"Hu, X.L., Liu, Y., Zhao, Z.X., Liu, J.T., Yang, X.T., Sun, C.H., Chen, S.H., Li, B., Zhou, C.: Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network. Comput. Electron. Agric. 185, 106135 (2021)","journal-title":"Comput. Electron. Agric."},{"issue":"7","key":"3342_CR28","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1007\/s00371-021-02116-3","volume":"38","author":"MH Junos","year":"2022","unstructured":"Junos, M.H., Mohd Khairuddin, A.S.M., Thannirmalai, S., Dahari, M.: Automatic detection of oil palm fruits from UAV images using an improved YOLO model. Vis. Comput. 38(7), 2341\u20132355 (2022)","journal-title":"Vis. Comput."},{"issue":"10","key":"3342_CR29","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.3390\/rs13101909","volume":"13","author":"JH Jiang","year":"2021","unstructured":"Jiang, J.H., Fu, X.J., Qin, R., Wang, X.Y., Ma, Z.F.: High-speed lightweight ship detection algorithm based on YOLO-v4 for three-channels RGB SAR image. Remote Sens. 13(10), 1909 (2021)","journal-title":"Remote Sens."},{"key":"3342_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, F., Wang, L.: Fruit classification model based on improved Darknet53 convolutional neural network. In: 2020 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), IEEE, pp. 881\u2013884 (2020)","DOI":"10.1109\/ICITBS49701.2020.00194"},{"key":"3342_CR31","doi-asserted-by":"crossref","unstructured":"Shan, M.M., Zhang, J., Zhu, H.L., Li, C.H., Tian, F.L.: Grasp Detection Algorithm Based on CSP-ResNet. In: 2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), IEEE, pp. 501\u2013506 (2022)","DOI":"10.1109\/ICICML57342.2022.10009877"},{"key":"3342_CR32","doi-asserted-by":"publisher","first-page":"110227","DOI":"10.1109\/ACCESS.2020.3001279","volume":"8","author":"XL Wang","year":"2020","unstructured":"Wang, X.L., Wang, S., Cao, J.Q., Wang, Y.S.: Data-driven based tiny-YOLOv3 method for front vehicle detection inducing SPP-net. IEEE Access. 8, 110227\u2013110236 (2020)","journal-title":"IEEE Access."},{"issue":"2","key":"3342_CR33","doi-asserted-by":"publisher","first-page":"2434","DOI":"10.1007\/s10489-022-03622-0","volume":"53","author":"HF Yu","year":"2023","unstructured":"Yu, H.F., Li, X.B., Feng, Y.K., Han, S.: Multiple attentional path aggregation network for marine object detectio. Appl. Intell. 53(2), 2434\u20132451 (2023)","journal-title":"Appl. Intell."},{"key":"3342_CR34","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van, Gool. L.: Efficient non-maximum suppression. In: 18th international conference on pattern recognition (ICPR\u201906), IEEE, pp. 850\u2013855 (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"3342_CR35","doi-asserted-by":"publisher","first-page":"106694","DOI":"10.1016\/j.compag.2022.106694","volume":"193","author":"AM Roy","year":"2022","unstructured":"Roy, A.M., Bhaduri, J.: Real-time growth stage detection model for high degree of occultation using DenseNet-fused YOLOv4. Comput. Electron. Agric. 193, 106694 (2022)","journal-title":"Comput. Electron. Agric."},{"issue":"9","key":"3342_CR36","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.3390\/rs15092331","volume":"15","author":"HY Ma","year":"2023","unstructured":"Ma, H.Y., Liu, Z.W., Jiang, K., Jiang, B.B., Feng, H.H., Hu, S.F.: A novel ST-ViBe algorithm for satellite fog detection at dawn and dusk. Remote Sens. 15(9), 2331 (2023)","journal-title":"Remote Sens."},{"issue":"11","key":"3342_CR37","doi-asserted-by":"publisher","first-page":"5244","DOI":"10.1109\/TIP.2017.2728181","volume":"26","author":"PM Jodoin","year":"2017","unstructured":"Jodoin, P.M., Maddalena, L., Petrosino, A., Wang, Y.: Extensive benchmark and survey of modeling methods for scene background initialization. IEEE Trans. Image Process. 26(11), 5244\u20135256 (2017)","journal-title":"IEEE Trans. Image Process."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03342-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03342-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03342-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T12:58:48Z","timestamp":1737723528000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03342-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,21]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3342"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03342-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,21]]},"assertion":[{"value":"25 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest\/competing interests to declare that are relevant to the content of this article. All authors declare that they have no financial interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All authors affirm that human research participants provided informed consent for publication of the images in Fig.\u00a0. The rest of the images are from the SBMnet dataset.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"All authors have read and agreed to the published version of the manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"All authors\u2019 organizations receive the same financial benefits.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Employment"}}]}}