{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T01:00:46Z","timestamp":1764723646096,"version":"3.46.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Frontier Innovative Technology Project","award":["[2022]40"],"award-info":[{"award-number":["[2022]40"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11760-025-04939-2","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:45:14Z","timestamp":1762735514000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ER-YOLO: A method for armored vehicle pose detection based on multi-scale edge analysis"],"prefix":"10.1007","volume":"19","author":[{"given":"Ruixuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinghai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoquan","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"4939_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128994","volume":"296","author":"Z Chen","year":"2026","unstructured":"Chen, Z., Zhang, Z., Su, Q., et al.: Object detection for autonomous vehicles under adverse weather conditions. Expert Syst. Appl. 296, 128994 (2026). https:\/\/doi.org\/10.1016\/j.eswa.2025.128994","journal-title":"Expert Syst. Appl."},{"key":"4939_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103165","volume":"65","author":"J Zhang","year":"2025","unstructured":"Zhang, J., Peng, J., Kong, X., et al.: Vehicle spatiotemporal distribution identification in low-light environment based on image enhancement and object detection. Adv. Eng. Inform. 65, 103165 (2025). https:\/\/doi.org\/10.1016\/j.aei.2025.103165","journal-title":"Adv. Eng. Inform."},{"key":"4939_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2022.103356","volume":"175","author":"T Xu","year":"2023","unstructured":"Xu, T., Xu, P., Zhao, H., et al.: Vehicle running attitude prediction model based on artificial neural network-parallel connected (ANN-PL) in the single-vehicle collision. Adv. Eng. Softw. 175, 103356 (2023). https:\/\/doi.org\/10.1016\/j.advengsoft.2022.103356","journal-title":"Adv. Eng. Softw."},{"key":"4939_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110759","volume":"153","author":"X Qiu","year":"2025","unstructured":"Qiu, X., Liao, S., Yang, D., et al.: Visual geo-localization and attitude estimation using satellite imagery and topographical elevation for unmanned aerial vehicles. Eng. Appl. Artif. Intell. 153, 110759 (2025). https:\/\/doi.org\/10.1016\/j.engappai.2025.110759","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"9","key":"4939_CR5","doi-asserted-by":"publisher","first-page":"6585","DOI":"10.1016\/j.jfranklin.2023.04.025","volume":"360","author":"Z Li","year":"2023","unstructured":"Li, Z., Guo, Y., Wang, J.: Joint estimation of position and attitude for intelligent vehicles by fusing delayed visual measurements. J. Franklin Inst. 360(9), 6585\u20136608 (2023). https:\/\/doi.org\/10.1016\/j.jfranklin.2023.04.025","journal-title":"J. Franklin Inst."},{"issue":"4","key":"4939_CR6","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1016\/j.dt.2020.06.013","volume":"17","author":"F Meng","year":"2021","unstructured":"Meng, F., Wang, X., Shao, F., et al.: Visual-attention gabor filter based online multi-armored target tracking. Def. Technol. 17(4), 1249\u20131261 (2021). https:\/\/doi.org\/10.1016\/j.dt.2020.06.013","journal-title":"Def. Technol."},{"key":"4939_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2023.104725","volume":"132","author":"X Zhao","year":"2023","unstructured":"Zhao, X., Dai, J., Li, L., et al.: Deep learning-based laser and infrared composite imaging for armor target identification and segmentation in complex battlefield environments. Infrared Phys. Technol. 132, 104725 (2023). https:\/\/doi.org\/10.1016\/j.infrared.2023.104725","journal-title":"Infrared Phys. Technol."},{"issue":"12","key":"4939_CR8","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.3724\/SP.J.1089.2018.17256","volume":"30","author":"Q Wang","year":"2018","unstructured":"Wang, Q., Chang, T., Zhang, L., et al.: An improved faster R-CNN algorithm for detection of multi-scale tank armored vehicle targets. J. Computer-Aided Des. Computer Graph. 30(12), 2278\u20132291 (2018). https:\/\/doi.org\/10.3724\/SP.J.1089.2018.17256","journal-title":"J. Computer-Aided Des. Computer Graph."},{"key":"4939_CR9","unstructured":"Ultralytics, YOLOv11: Enhancing real-time object detection performance, Ultralytics Research Papers, 2024."},{"key":"4939_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130091","volume":"637","author":"J Wu","year":"2025","unstructured":"Wu, J., Chen, Z., Guo, Q., et al.: Dsinet: dual semantic interaction and edge refinement network for salient object detection. Neurocomputing 637, 130091 (2025). https:\/\/doi.org\/10.1016\/j.neucom.2025.130091","journal-title":"Neurocomputing"},{"key":"4939_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3091312","volume":"60","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Shen, K., Liu, Z., et al.: Edge-aware multiscale feature integration network for salient object detection in optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201315 (2022). https:\/\/doi.org\/10.1109\/TGRS.2021.3091312","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"4939_CR12","unstructured":"Jiang, W., Wang, L., Yao, Y., et al.: A small object detection algorithm based on multi-scale feature aggregation diffusion and edge information enhancement, Computer Engineering and Applications, 2024. http:\/\/kns.cnki.net\/kcms\/detail\/11.2127.tp.20241210.1654.011.html"},{"key":"4939_CR13","doi-asserted-by":"publisher","DOI":"10.3390\/rs15204909","author":"J Yao","year":"2023","unstructured":"Yao, J., Xiao, S., Deng, Q., et al.: An infrared maritime small target detection algorithm based on semantic, detail, and edge multidimensional information fusion. Remote Sens. (2023). https:\/\/doi.org\/10.3390\/rs15204909","journal-title":"Remote Sens."},{"key":"4939_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103697","volume":"68","author":"W Huang","year":"2025","unstructured":"Huang, W., Pang, R., Zhou, Y., et al.: Multi-condition dam crack segmentation based on a novel lightweight CEE-YOLO model. Adv. Eng. Inform. 68, 103697 (2025). https:\/\/doi.org\/10.1016\/j.aei.2025.103697","journal-title":"Adv. Eng. Inform."},{"key":"4939_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2025.105545","volume":"26","author":"S Xu","year":"2025","unstructured":"Xu, S., Cui, K.: YOLO-EFM: Efficient traffic flow monitoring algorithm with enhanced multi-level information fusion. Results Eng. 26, 105545 (2025). https:\/\/doi.org\/10.1016\/j.rineng.2025.105545","journal-title":"Results Eng."},{"key":"4939_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127056","volume":"275","author":"B Liang","year":"2025","unstructured":"Liang, B., Luo, H., Wang, J., et al.: Multi-scale attention-edge interactive refinement network for salient object detection. Expert Syst. Appl. 275, 127056 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.127056","journal-title":"Expert Syst. Appl."},{"key":"4939_CR17","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929, 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"4939_CR18","doi-asserted-by":"publisher","unstructured":"Touvron, H., Cord, M., Douze, M., et al.: Training data-efficient image transformers & distillation through attention, arXiv preprint arXiv:2012.12877, 2020. https:\/\/doi.org\/10.48550\/arXiv.2012.12877","DOI":"10.48550\/arXiv.2012.12877"},{"key":"4939_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin Transformer: Hierarchical vision transformer using shifted windows, In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10012\u201310022, 2021. https:\/\/doi.org\/10.48550\/arXiv.2103.14030","DOI":"10.48550\/arXiv.2103.14030"},{"key":"4939_CR20","doi-asserted-by":"publisher","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., et al.: A ConvNet for the 2020s, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11976\u201311986, 2022. https:\/\/doi.org\/10.48550\/arXiv.2201.03545","DOI":"10.48550\/arXiv.2201.03545"},{"key":"4939_CR21","doi-asserted-by":"publisher","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (GELUs), arXiv preprint arXiv:1606.08415, 2023. https:\/\/doi.org\/10.48550\/arXiv.1606.08415","DOI":"10.48550\/arXiv.1606.08415"},{"key":"4939_CR22","doi-asserted-by":"publisher","unstructured":"Ding, X., Zhang, X., Han, J., et al.: Scaling up your kernels to 31x31: Revisiting large kernel design in CNNs, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11963\u201311975, 2022. https:\/\/doi.org\/10.48550\/arXiv.2203.06717","DOI":"10.48550\/arXiv.2203.06717"},{"key":"4939_CR23","doi-asserted-by":"publisher","unstructured":"Guo, M.-H., Lu, C.-Z., Liu, Z.-N., et al.: Visual attention network, arXiv preprint arXiv:2202.09741, 2022. https:\/\/doi.org\/10.48550\/arXiv.2202.09741","DOI":"10.48550\/arXiv.2202.09741"},{"key":"4939_CR24","doi-asserted-by":"publisher","unstructured":"Liu, S., Chen, T., Chen, X., et al.: More ConvNets in the 2020s: Scaling up kernels beyond 51x51 using sparsity, arXiv preprint arXiv:2207.03620, 2022. https:\/\/doi.org\/10.48550\/arXiv.2207.03620","DOI":"10.48550\/arXiv.2207.03620"},{"key":"4939_CR25","doi-asserted-by":"publisher","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1251\u20131258, 2017. https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"4939_CR26","doi-asserted-by":"publisher","unstructured":"Child, R., Gray, S., Radford, A., et al.: Generating long sequences with sparse transformers, arXiv preprint arXiv:1904.10509, 2019. https:\/\/doi.org\/10.48550\/arXiv.1904.10509","DOI":"10.48550\/arXiv.1904.10509"},{"key":"4939_CR27","doi-asserted-by":"publisher","unstructured":"Tu, Z., Talebi, H., Zhang, H., et al.: MaxViT: Multi-axis vision transformer, in: Proceedings of the European Conference on Computer Vision, 2022. https:\/\/doi.org\/10.48550\/arXiv.2204.01697","DOI":"10.48550\/arXiv.2204.01697"},{"key":"4939_CR28","doi-asserted-by":"publisher","unstructured":"Wang, W., Yao, L., Chen, L., et al.: CrossFormer: A versatile vision transformer hinging on cross-scale attention, in: Proceedings of the International Conference on Learning Representations, 2022. https:\/\/doi.org\/10.48550\/arXiv.2108.00154","DOI":"10.48550\/arXiv.2108.00154"},{"key":"4939_CR29","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhu, Y., Zhao, C., et al.: DPT: Deformable patch-based transformer for visual recognition, in: Proceedings of the 29th ACM International Conference on Multimedia, 2899\u20132907, 2021. https:\/\/doi.org\/10.1145\/3474085.3475467","DOI":"10.1145\/3474085.3475467"},{"key":"4939_CR30","doi-asserted-by":"publisher","unstructured":"Xia, Z., Pan, X., Song, S., et al.: Vision Transformer with Deformable Attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4794\u20134803, 2022. https:\/\/doi.org\/10.48550\/arXiv.2201.00520","DOI":"10.48550\/arXiv.2201.00520"},{"key":"4939_CR31","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformers, in: European Conference on Computer Vision, 213\u2013229, 2020.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4939_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129772","volume":"298","author":"L Cai","year":"2025","unstructured":"Cai, L., Zheng, Q., Wang, Y., et al.: CrossFPN: Efficient cross-scale feature pyramid network for real-time low-altitude aerial target detection. Expert Syst. Appl. 298, 129772 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.129772","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"4939_CR33","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2021","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2021). https:\/\/doi.org\/10.1109\/TITS.2020.2972974","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"4939_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104873","volume":"156","author":"X Zeng","year":"2025","unstructured":"Zeng, X., Liu, G., Chen, J., et al.: Efficient multimodal object detection via coordinate attention fusion for adverse environmental conditions. Digit. Signal Process. 156, 104873 (2025). https:\/\/doi.org\/10.1016\/j.dsp.2024.104873","journal-title":"Digit. Signal Process."},{"issue":"19","key":"4939_CR35","doi-asserted-by":"publisher","first-page":"31466","DOI":"10.1109\/JSEN.2024.3442951","volume":"24","author":"C Xu","year":"2024","unstructured":"Xu, C., Zhao, H., Xie, H., et al.: Multisensor decision-level fusion network based on attention mechanism for object detection. IEEE Sens. J. 24(19), 31466\u201331480 (2024). https:\/\/doi.org\/10.1109\/JSEN.2024.3442951","journal-title":"IEEE Sens. J."},{"key":"4939_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103565","volume":"126","author":"J Mi","year":"2026","unstructured":"Mi, J., Zhang, X.: DDAformer: a hybrid architecture with dynamic large kernel convolution and distance-aware transformer for brain tumor segmentation. Inf. Fusion 126, 103565 (2026). https:\/\/doi.org\/10.1016\/j.inffus.2025.103565","journal-title":"Inf. Fusion"},{"key":"4939_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106731","volume":"97","author":"B Wang","year":"2024","unstructured":"Wang, B., Qin, J., Lv, L., et al.: DSML-unet: depthwise separable convolution network with multiscale large kernel for medical image segmentation. Biomed. Signal Process. Control 97, 106731 (2024). https:\/\/doi.org\/10.1016\/j.bspc.2024.106731","journal-title":"Biomed. Signal Process. Control"},{"key":"4939_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112163","volume":"161","author":"B Dikici","year":"2025","unstructured":"Dikici, B., Bekciogullari, M., Acikgoz, H., et al.: A lightweight and improved you only look once model using GhostWise convolution and attention mechanism for accurate plant disease detection. Eng. Appl. Artif. Intell. 161, 112163 (2025). https:\/\/doi.org\/10.1016\/j.engappai.2025.112163","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4939_CR39","doi-asserted-by":"publisher","unstructured":"Zeng, W., Jin, S., Liu, W., et al.: Not all tokens are equal: Human-centric visual analysis via token clustering transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11101\u201311111, 2022. https:\/\/doi.org\/10.48550\/arXiv.2204.08680","DOI":"10.48550\/arXiv.2204.08680"},{"key":"4939_CR40","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., et al.: CSwin Transformer: A general vision transformer backbone with cross-shaped windows, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12124\u201312134, 2022.","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"4939_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112324","volume":"171","author":"L Lian","year":"2026","unstructured":"Lian, L., Qin, Y., Cao, Z., et al.: Rvsa-3d: voxel-based fully sparse attention 3d object detection for rail transit obstacle perception. Pattern Recognit. 171, 112324 (2026). https:\/\/doi.org\/10.1016\/j.patcog.2025.112324","journal-title":"Pattern Recognit."},{"key":"4939_CR42","doi-asserted-by":"publisher","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., et al.: Accurate, large minibatch SGD: Training ImageNet in 1 hour, arXiv preprint arXiv:1706.02677, 2017. https:\/\/doi.org\/10.48550\/arXiv.1706.02677","DOI":"10.48550\/arXiv.1706.02677"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04939-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04939-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04939-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:55:52Z","timestamp":1764723352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04939-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":42,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4939"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04939-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"24 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 November 2025","order":4,"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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1353"}}