{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:41:27Z","timestamp":1779237687159,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T00:00:00Z","timestamp":1751673600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T00:00:00Z","timestamp":1751673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11554-025-01718-7","type":"journal-article","created":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:15:37Z","timestamp":1751688937000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["RV-YOLO: real-time object detection algorithm for rail transit platform scenarios"],"prefix":"10.1007","volume":"22","author":[{"given":"Ke","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijia","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,5]]},"reference":[{"key":"1718_CR1","first-page":"257","volume":"36","author":"W Xiukun","year":"2021","unstructured":"Xiukun, W., Da, S., Dehua, W., Xiaomeng, W., Siyang, J., Ziming, Y.: A survey of the application of machine vision in rail transit system inspection. Control. Decis 36, 257\u2013282 (2021)","journal-title":"Control. Decis"},{"key":"1718_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y.: Computer vision-based detection model for passenger flows inside urban rail transit stations. In: Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022), vol. 12591, pp. 837\u2013842. SPIE (2023)","DOI":"10.1117\/12.2668571"},{"issue":"11","key":"1718_CR3","doi-asserted-by":"publisher","first-page":"1468","DOI":"10.1587\/transinf.2024EDL8011","volume":"E107D","author":"S Liu","year":"2024","unstructured":"Liu, S., Li, C., Liu, Y., Wang, Y.: SH-YOLO: small target high performance YOLO for abnormal behavior detection in escalator scene. IEICE Trans. Inf. Syst. E107D(11), 1468\u20131471 (2024)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"1718_CR4","doi-asserted-by":"crossref","unstructured":"Pravallika, A., Kumar, C.A., Praneeth, E.S., Abhilash, D., Priya, G.S.: Efficient vehicle detection system using YOLOV8 on jetson nano board. In: 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ICITEICS61368.2024.10625296"},{"key":"1718_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1718_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448. IEEE (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"1718_CR7","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1718_CR8","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., NanoCode012, Kwon, Y., TaoXie, Fang, J., Imyhxy, Michael, K., Lorna, Abhiram, V., Montes, D., Nadar, J., Laughing, Tkianai, yxNONG, Skalski, P., Wang, Z., Hogan, A., Fati, C., Mammana, L., AlexWang1900, Patel, D., Yiwei, D., You, F., Hajek, J., Diaconu, L., Minh, M.T.: ultralytics\/yolov5: v6.1 - TensorRT, TensorFlow Edge TPU and OpenVINO Export and Inference (2022)"},{"key":"1718_CR9","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: YOLOV7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"issue":"9","key":"1718_CR10","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1718_CR11","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, 29 (2016)"},{"key":"1718_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1718_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, D., Dai, L., Du, P.: CCE-YOLOV5S: an improved YOLOV5 model for UAV small target detection. In: 2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), pp. 824\u2013829. IEEE (2023)","DOI":"10.1109\/ICCASIT58768.2023.10351744"},{"key":"1718_CR14","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1718_CR15","doi-asserted-by":"crossref","unstructured":"Yang, J., Tong, Q., Zhong, Y., Li, Q.: Improved YOLOV5 for stroller and luggage detection. In: 2023 4th International Conference on Computer Engineering and Application (ICCEA), pp. 252\u2013257. IEEE (2023)","DOI":"10.1109\/ICCEA58433.2023.10135282"},{"key":"1718_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xiong, A., Lai, L., Chen, C., Liang, J.: AMME-YOLOV7: improved YOLOV7 based on attention mechanism and multiscale expansion for electric vehicle driver and passenger helmet wearing detection. In: 2023 IEEE International Conference on Smart Internet of Things (SmartIoT), pp. 223\u2013227. IEEE (2023)","DOI":"10.1109\/SmartIoT58732.2023.00039"},{"key":"1718_CR17","doi-asserted-by":"crossref","unstructured":"Saenprasert, W., Tun, E.E., Hajian, A., Ruangsang, W., Aramvith, S.: YOLO for small objects in aerial imagery: a performance evaluation. In: 2024 21st International Joint Conference on Computer Science and Software Engineering (JCSSE), pp. 720\u2013727. IEEE (2024)","DOI":"10.1109\/JCSSE61278.2024.10613680"},{"key":"1718_CR18","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOV10: real-time end-to-end object detection. arXiv preprint arXiv:2405.14458 (2024)"},{"key":"1718_CR19","unstructured":"Jocher, G., Qiu, J., Chaurasia, A.: Ultralytics YOLO (2023)"},{"key":"1718_CR20","doi-asserted-by":"crossref","unstructured":"Hou, X., Liu, M., Zhang, S., Wei, P., Chen, B.: Salience DETR: enhancing detection transformer with hierarchical salience filtering refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17574\u201317583 (2024)","DOI":"10.1109\/CVPR52733.2024.01664"},{"key":"1718_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, C., Sun, Y., Wang, W., Chen, Q., Ding, E., Yang, Y., Wang, J.: MS-DETR: efficient DETR training with mixed supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17027\u201317036 (2024)","DOI":"10.1109\/CVPR52733.2024.01611"},{"key":"1718_CR22","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: UnitBox: an advanced object detection network. In: Proceedings of the 24th ACM international conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"1718_CR23","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J.Y., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1718_CR24","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: Faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1718_CR25","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","volume":"506","author":"Y-F Zhang","year":"2022","unstructured":"Zhang, Y.-F., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient IoU loss for accurate bounding box regression. Neurocomputing 506, 146\u2013157 (2022)","journal-title":"Neurocomputing"},{"key":"1718_CR26","unstructured":"Gevorgyan, Z.: SIoU loss: more powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740 (2022)"},{"key":"1718_CR27","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"1718_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1718_CR29","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"1718_CR30","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.-Y.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"1718_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"1718_CR32","doi-asserted-by":"crossref","unstructured":"Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., Hu, H.: DETRs with hybrid matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"1718_CR33","unstructured":"Song, H., Sun, D., Chun, S., Jampani, V., Han, D., Heo, B., Kim, W., Yang, M.-H.: VIDT: an efficient and effective fully transformer-based object detector. arXiv preprint arXiv:2110.03921 (2021)"},{"key":"1718_CR34","unstructured":"Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., Du, Y., et\u00a0al.: PP-YOLOE: an evolved version of YOLO. arXiv preprint arXiv:2203.16250 (2022)"},{"key":"1718_CR35","first-page":"26183","volume":"34","author":"Y Fang","year":"2021","unstructured":"Fang, Y., Liao, B., Wang, X., Fang, J., Qi, J., Wu, R., Niu, J., Liu, W.: You only look at one sequence: rethinking transformer in vision through object detection. Adv. Neural. Inf. Process. Syst. 34, 26183\u201326197 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1718_CR36","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: YOLO-world: real-time open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16901\u201316911 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"1718_CR37","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"1718_CR38","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, X.: LS DETR: lightweight DETR with selective transmission training strategy. In: 2024 2nd International Conference on Algorithm, Image Processing and Machine Vision (AIPMV), pp. 24\u201330. IEEE (2024)","DOI":"10.1109\/AIPMV62663.2024.10692215"},{"key":"1718_CR39","doi-asserted-by":"crossref","unstructured":"Ben\u00a0Saad, A., Facciolo, G., Davy, A.: On the importance of large objects in CNN based object detection algorithms. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 533\u2013542 (2024)","DOI":"10.1109\/WACV57701.2024.00059"},{"key":"1718_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105628","volume":"117","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Wang, W., Li, Z., Shu, S., Lang, X., Zhang, T., Dong, J.: Development of a cross-scale weighted feature fusion network for hot-rolled steel surface defect detection. Eng. Appl. Artif. Intell. 117, 105628 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1718_CR41","unstructured":"Khoramdel, J., Moori, A., Borhani, Y., Ghanbarzadeh, A., Najafi, E.: YOLO-former: YOLO shakes hand with VIT. arXiv preprint arXiv:2401.06244 (2024)"},{"issue":"3","key":"1718_CR42","doi-asserted-by":"publisher","first-page":"614","DOI":"10.3390\/rs15030614","volume":"15","author":"D Wan","year":"2023","unstructured":"Wan, D., Lu, R., Wang, S., Shen, S., Xu, T., Lang, X.: YOLO-HR: improved YOLOV5 for object detection in high-resolution optical remote sensing images. Remote Sens. 15(3), 614 (2023)","journal-title":"Remote Sens."},{"key":"1718_CR43","doi-asserted-by":"publisher","unstructured":"Ren, Z., Yao, K., Sheng, S., Wang, B., Lang, X., Wan, D., Fu, W.: YOLO-SDH: improved yolov5 using scaled decoupled head for object detection. Int. J. Mach. Learn. Cybern. 16, 1643\u20131660 (2025). https:\/\/doi.org\/10.1007\/s13042-024-02357-3","DOI":"10.1007\/s13042-024-02357-3"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01718-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01718-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01718-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T16:59:11Z","timestamp":1757350751000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01718-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,5]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1718"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01718-7","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,5]]},"assertion":[{"value":"19 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2025","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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"143"}}