{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:32:30Z","timestamp":1743150750524,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819720910"},{"type":"electronic","value":"9789819720927"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-2092-7_18","type":"book-chapter","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:02:18Z","timestamp":1711692138000},"page":"354-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improved YOLOv5 Algorithm for\u00a0Small Object Detection in\u00a0Drone Images"],"prefix":"10.1007","author":[{"given":"Yitong","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiguang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv arXiv:2004.10934 (2020). https:\/\/doi.org\/10.48550\/arxiv.2004.10934","DOI":"10.48550\/arxiv.2004.10934"},{"key":"18_CR2","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Chen, H., Wang, J., Li, J., Qiu, Y., Zhang, D.: Small object detection for drone image based on advanced YOLOv7. In: 2023 42nd Chinese Control Conference (CCC), pp. 7453\u20137458 (2023). https:\/\/doi.org\/10.23919\/CCC58697.2023.10239784","DOI":"10.23919\/CCC58697.2023.10239784"},{"key":"18_CR4","doi-asserted-by":"publisher","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M. : YOLOv: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv arXiv:2207.02696 (2022). https:\/\/doi.org\/10.48550\/arxiv.2207.02696","DOI":"10.48550\/arxiv.2207.02696"},{"key":"18_CR5","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv arXiv:2209.02976 (2022). https:\/\/doi.org\/10.48550\/arxiv.2209.02976","DOI":"10.48550\/arxiv.2209.02976"},{"issue":"7","key":"18_CR6","first-page":"327106","volume":"44","author":"Z Feng","year":"2023","unstructured":"Feng, Z., Xie, Z., Bao, Z., Chen, K.: Real-time dense small object detection algorithm for UAV based on improved YOLOv5. Acta Aeronauticaet Astronautica Sinica 44(7), 327106 (2023)","journal-title":"Acta Aeronauticaet Astronautica Sinica"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Gao, T., Wushouer, M., Tuerhong, G.: Small object detection method based on improved YOLOv5. In: 2022 International Conference on Virtual Reality, Human-Computer Interaction and Artificial Intelligence (VRHCIAI), pp. 144\u2013149 (2022). https:\/\/doi.org\/10.1109\/VRHCIAI57205.2022.00032","DOI":"10.1109\/VRHCIAI57205.2022.00032"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Computer Society (2014). https:\/\/doi.org\/10.48550\/arxiv.1311.2524","DOI":"10.48550\/arxiv.1311.2524"},{"key":"18_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322","author":"K He","year":"2017","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR11","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, 1904\u20131916 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2015.2389824","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3314586","volume":"61","author":"R Kou","year":"2023","unstructured":"Kou, R., et al.: LW-IRSTNet: lightweight infrared small target segmentation network and application deployment. IEEE Trans. Geosci. Remote Sens. 61, 1\u201313 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3314586","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"18_CR13","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/s11263-019-01204-1","volume":"128","author":"H Law","year":"2020","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. Int. J. Comput. Vis. 128(3), 642\u2013656 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01204-1","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Li, S., Yang, X., Lin, X., Zhang, Y., Wu, J.: Real-time vehicle detection from UAV aerial images based on improved YOLOv5. Sensors 23(12) (2023). https:\/\/doi.org\/10.3390\/s23125634. https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5634","DOI":"10.3390\/s23125634"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. arXiv e-prints (2016). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999\u20133007 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Liu, S., Liang, P., Duan, Y., Zhang, Y., Feng, J.: Small target detection for unmanned aerial vehicle images based on YOLOv5l. In: 2022 10th International Conference on Information Systems and Computing Technology (ISCTech), pp. 210\u2013214 (2022). https:\/\/doi.org\/10.1109\/ISCTech58360.2022.00042","DOI":"10.1109\/ISCTech58360.2022.00042"},{"key":"18_CR18","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Computer Vision & Pattern Recognition (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/cvpr.2016.91"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517\u20136525 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv e-prints (2018). https:\/\/doi.org\/10.48550\/arxiv.1804.02767","DOI":"10.48550\/arxiv.1804.02767"},{"issue":"6","key":"18_CR21","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","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 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Tang, Z., Liu, Y., Shang, Y.: A new GNN-based object detection method for multiple small objects in aerial images. In: 2023 IEEE\/ACIS 23rd International Conference on Computer and Information Science (ICIS), pp. 14\u201319 (2023). https:\/\/doi.org\/10.1109\/ICIS57766.2023.10210246","DOI":"10.1109\/ICIS57766.2023.10210246"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Wang, L., Fang, S., Zhang, C., Li, R., Duan, C.: Efficient hybrid transformer: learning global-local context for urban scence segmentation. arXiv arXiv:2109.08937 (2021). https:\/\/doi.org\/10.48550\/arXiv.2109.08937","DOI":"10.48550\/arXiv.2109.08937"},{"key":"18_CR24","doi-asserted-by":"publisher","unstructured":"Wang, Q., Zhang, H., Hong, X., Zhou, Q.: Small object detection based on modified FSSD and model compression. In: 2021 IEEE 6th International Conference on Signal and Image Processing (ICSIP), pp. 88\u201392 (2021). https:\/\/doi.org\/10.1109\/ICSIP52628.2021.9688896","DOI":"10.1109\/ICSIP52628.2021.9688896"},{"key":"18_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"18_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., Sun, X.: DAMO-YOLO: a report on real-time object detection design. arXiv arXiv:2211.15444 (2023). https:\/\/doi.org\/10.48550\/arxiv.2211.15444","DOI":"10.48550\/arxiv.2211.15444"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Yan, X., Shen, B., Li, H.: Small objects detection method for UAVs aerial image based on YOLOv5s. In: 2023 IEEE 6th International Conference on Electronic Information and Communication Technology (ICEICT), pp. 61\u201366 (2023). https:\/\/doi.org\/10.1109\/ICEICT57916.2023.10245156","DOI":"10.1109\/ICEICT57916.2023.10245156"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Yang, C., Huang, Z., Wang, N.: QueryDet: cascaded sparse query for accelerating high-resolution small object detection. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13658\u201313667 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01330","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"18_CR30","doi-asserted-by":"publisher","unstructured":"Yu, M., Leung, H.: Small-object detection for UAV-based images. In: 2023 IEEE International Systems Conference (SysCon), pp.\u00a01\u20136 (2023). https:\/\/doi.org\/10.1109\/SysCon53073.2023.10131084","DOI":"10.1109\/SysCon53073.2023.10131084"},{"key":"18_CR31","doi-asserted-by":"publisher","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: Light-head R-CNN: in defense of two-stage object detector. arXiv arXiv:1711.07264 (2017). https:\/\/doi.org\/10.48550\/arxiv.1711.07264","DOI":"10.48550\/arxiv.1711.07264"},{"key":"18_CR32","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00442","DOI":"10.1109\/CVPR.2018.00442"},{"key":"18_CR33","doi-asserted-by":"publisher","first-page":"4371","DOI":"10.1109\/JSTARS.2022.3175498","volume":"15","author":"X Zhang","year":"2022","unstructured":"Zhang, X., Feng, Y., Zhang, S., Wang, N., Mei, S.: Finding nonrigid tiny person with densely cropped and local attention object detector networks in low-altitude aerial images. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 15, 4371\u20134385 (2022). https:\/\/doi.org\/10.1109\/JSTARS.2022.3175498","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"18_CR34","doi-asserted-by":"publisher","unstructured":"Zhu, X., Lyu, S., Wang, X., Zhao, Q.: TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2778\u20132788 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00312","DOI":"10.1109\/ICCVW54120.2021.00312"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2092-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T06:07:31Z","timestamp":1711692451000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2092-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819720910","9789819720927"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2092-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CVM submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"212","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}