{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:56:11Z","timestamp":1782392171390,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"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":["62272049"],"award-info":[{"award-number":["62272049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Technological Innovation 2030 \u2013 \"New Generation Artificial Intelligence\"","award":["2018AAA0100800"],"award-info":[{"award-number":["2018AAA0100800"]}]},{"name":"Science and Technology Project of Beijing Municipal Commission of Education","award":["KM202111417009"],"award-info":[{"award-number":["KM202111417009"]}]},{"name":"Academic Research Projects of Beijing Union University","award":["ZKZD202301"],"award-info":[{"award-number":["ZKZD202301"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s11760-024-03476-8","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T06:47:44Z","timestamp":1724309264000},"page":"8327-8335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["YOLOv7-P: a lighter and more effective UAV aerial photography object detection algorithm"],"prefix":"10.1007","volume":"18","author":[{"given":"Fengxi","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,20]]},"reference":[{"key":"3476_CR1","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3476_CR2","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"3476_CR3","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3476_CR4","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"3476_CR5","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Fang, J., Michael, K., Montes, D., Nadar, J., Skalski, P., et al.: ultralytics\/YOLOv5: v6.1\u2014TensorRT, TensorFlow edge TPU and OpenVINO export and inference. Zenodo (2022)"},{"key":"3476_CR6","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"3476_CR7","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"3476_CR8","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":"1","key":"3476_CR9","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1038\/s41377-022-00714-x","volume":"11","author":"C Zuo","year":"2022","unstructured":"Zuo, C., Qian, J., Feng, S., Yin, W., Li, Y., Fan, P., Han, J., Qian, K., Chen, Q.: Deep learning in optical metrology: a review. Light Sci. Appl. 11(1), 39 (2022)","journal-title":"Light Sci. Appl."},{"key":"3476_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"3476_CR11","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"3476_CR12","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"3476_CR13","unstructured":"Cao, J., Chen, Q., Guo, J., Shi, R.: Attention-guided context feature pyramid network for object detection. arXiv preprint arXiv:2005.11475 (2020)"},{"key":"3476_CR14","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., Liang, R.: AFPN: asymptotic feature pyramid network for object detection. arXiv preprint arXiv:2306.15988 (2023)","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"3476_CR15","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"3476_CR16","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: GhostNet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580\u20131589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"3476_CR17","unstructured":"Li, H., Li, J., Wei, H., Liu, Z., Zhan, Z., Ren, Q.: Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles. arXiv preprint arXiv:2206.02424 (2022)"},{"key":"3476_CR18","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.-H., He, H., Zhuo, W., Wen, S., Lee, C.-H., Chan, S.-H.G.: Run, don\u2019t walk: chasing higher flops for faster neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12021\u201312031 (2023)","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"3476_CR19","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"},{"issue":"8","key":"3476_CR20","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., Zuo, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574\u20138586 (2021)","journal-title":"IEEE Trans. Cybern."},{"key":"3476_CR21","unstructured":"Gevorgyan, Z.: SIoU Loss: more powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740 (2022)"},{"key":"3476_CR22","unstructured":"Wang, J., Xu, C., Yang, W., Yu, L.: A normalized Gaussian Wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389 (2021)"},{"key":"3476_CR23","unstructured":"Wang, C.-Y., Liao, H.-Y.M., Yeh, I.-H.: Designing network design strategies through gradient path analysis. arXiv preprint arXiv:2211.04800 (2022)"},{"key":"3476_CR24","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., Wang, X., Zhang, Y.: VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)"},{"key":"3476_CR25","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.-S.: Tiny object detection in aerial images. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3791\u20133798. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"3476_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3476_CR27","unstructured":"GitHub\u2014Ultralytics\/Ultralytics:YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"3476_CR28","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":"3476_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H., Liao, H.-Y.M.: YOLOv9: learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616 (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"3476_CR30","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)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03476-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03476-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03476-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T02:07:11Z","timestamp":1732673231000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03476-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,20]]},"references-count":30,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["3476"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03476-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,20]]},"assertion":[{"value":"28 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2024","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}