{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:25:13Z","timestamp":1778081113630,"version":"3.51.4"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10489-021-02512-1","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T16:03:26Z","timestamp":1626797006000},"page":"4244-4257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Small object detection via dual inspection mechanism for UAV visual images"],"prefix":"10.1007","volume":"52","author":[{"given":"Gangyi","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianran","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8372-7314","authenticated-orcid":false,"given":"Wenyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,20]]},"reference":[{"key":"2512_CR1","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.neucom.2020.10.092","volume":"423","author":"G Sun","year":"2021","unstructured":"Sun G, Ding S, Sun T, Zhang C (2021) Sa-capsgan: Using capsule networks with embedded self-attention for generative adversarial network. Neurocomputing 423:399\u2013406","journal-title":"Neurocomputing"},{"key":"2512_CR2","doi-asserted-by":"crossref","unstructured":"Hsieh M-R, Lin Y-L, Hsu HW (2017) Drone-based object counting by spatially regularized regional proposal network. . In: IEEE International Conference on Computer Vision, pp 4165\u20134173","DOI":"10.1109\/ICCV.2017.446"},{"key":"2512_CR3","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2014.81"},{"key":"2512_CR4","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2015","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2015) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38:142\u2013158","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2512_CR5","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 379\u2013387"},{"key":"2512_CR6","unstructured":"Xiao T, Li S, Wang B, Lin L, Wang X (2016) End-to-end deep learning for person search. In: IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"2512_CR7","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S (2016) Ssd: Single shot multibox detector. In: European Conference on Computer Vision, pp 1\u201317","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2512_CR8","first-page":"1","volume":"13","author":"J Leng","year":"2018","unstructured":"Leng J, Liu Y (2018) An enhanced ssd with feature fusion and visual reasoning for object detection. Neural Comput Appl 13:1\u201310","journal-title":"Neural Comput Appl"},{"key":"2512_CR9","doi-asserted-by":"crossref","unstructured":"Jeong J, Park H, Kwak N (2017) Enhancement of ssd by concatenating feature maps for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u201312","DOI":"10.5244\/C.31.76"},{"key":"2512_CR10","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2015) You only look once: Unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2512_CR11","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: Better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 6517\u20136525","DOI":"10.1109\/CVPR.2017.690"},{"key":"2512_CR12","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv:1804.02767"},{"key":"2512_CR13","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-Y (2020) Yolov4: Optimal speed and accuracy of object detection. pp 1\u201317. arXiv:1911.09070v4"},{"key":"2512_CR14","unstructured":"Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, pp 1\u201310"},{"key":"2512_CR15","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le Q (2020) Efficientdet: Scalable and efficient object detection. In: Ieee conference on computer vision and pattern recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2512_CR16","doi-asserted-by":"crossref","unstructured":"Lei J, Chen Y, Bo P, Ling N, Hou C (2018) Multi-stream region proposal network for pedestrian detection. In: IEEE International Conference on Multimedia and Expo Workshops , pp 1\u20136","DOI":"10.1109\/ICMEW.2018.8551499"},{"key":"2512_CR17","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris R, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: European Conference on Computer Vision, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"2512_CR18","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Dollar P (2018) Focal loss for dense object detection. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 42, pp 318\u2013327","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"2512_CR19","doi-asserted-by":"publisher","first-page":"2691","DOI":"10.1109\/TIFS.2018.2825953","volume":"13","author":"B Bayar","year":"2018","unstructured":"Bayar B, Stamm M (2018) Constrained convolutional neural networks: A new approach towards general purpose image manipulation detection. IEEE Trans Inf Forensic Secur 13:2691\u20132706","journal-title":"IEEE Trans Inf Forensic Secur"},{"key":"2512_CR20","doi-asserted-by":"crossref","unstructured":"Li T, Ding F, Yang W (2020) Uav object tracking by background cues and aberrances response suppression mechanism. Neural Comput Appl:1\u201315","DOI":"10.1007\/s00521-020-05200-2"},{"issue":"9","key":"2512_CR21","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/j.measurement.2015.06.010","volume":"73","author":"M Uysal","year":"2015","unstructured":"Uysal M, Toprak AS, Polat N (2015) Dem generation with uav photogrammetry and accuracy analysis in sahitler hill. Measurement 73(9):539\u2013543","journal-title":"Measurement"},{"key":"2512_CR22","doi-asserted-by":"crossref","unstructured":"Ge W, Yang S, Yu Y (2018) Multi-evidence filtering and fusion for multi-label classification, object detection and semantic segmentation based on weakly supervised learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1277\u20131286","DOI":"10.1109\/CVPR.2018.00139"},{"key":"2512_CR23","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2017) Multi-view 3d object detection network for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 6526\u20136534","DOI":"10.1109\/CVPR.2017.691"},{"key":"2512_CR24","doi-asserted-by":"crossref","unstructured":"Conte G, Doherty P (2008) An integrated uav navigation system based on aerial image matching. In: IEEE Aerospace Conference Proceedings, pp 1\u201310","DOI":"10.1109\/AERO.2008.4526556"},{"key":"2512_CR25","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1109\/TGRS.2008.2009355","volume":"47","author":"A Laliberte","year":"2009","unstructured":"Laliberte A, Rango A (2009) Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle (uav) imagery. IEEE Trans Geosci Remote Sens 47:761\u2013770","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2512_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10095020.2017.1420510","volume":"21","author":"Y Lu","year":"2018","unstructured":"Lu Y, Xue Z, Xia G-S, Zhang L (2018) A survey on vision-based uav navigation. Geo-spatial Inf Sci 21:1\u201312","journal-title":"Geo-spatial Inf Sci"},{"key":"2512_CR27","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 936\u2013944","DOI":"10.1109\/CVPR.2017.106"},{"key":"2512_CR28","doi-asserted-by":"publisher","first-page":"1883","DOI":"10.4249\/scholarpedia.1883","volume":"4","author":"L Peterson","year":"2009","unstructured":"Peterson L (2009) K-nearest neighbor. Scholarpedia 4:1883","journal-title":"Scholarpedia"},{"key":"2512_CR29","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Huang W, Liu H (2018) Deep feature pyramid reconfiguration for object detection. In: European Conference on Computer Vision, pp 8\u201314","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"2512_CR30","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: Delving into high quality object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2512_CR31","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 (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904\u20131920","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2512_CR32","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2512_CR33","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 (2017) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2512_CR34","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1007\/s10489-020-01665-9","volume":"50","author":"X Ding","year":"2020","unstructured":"Ding X, Li Q, Cheng Y, Wang J, Bian W, Jie B (2020) Local keypoint-based faster r-cnn. Appl Intell 50:3007\u20133022","journal-title":"Appl Intell"},{"key":"2512_CR35","doi-asserted-by":"publisher","first-page":"3125","DOI":"10.1007\/s10489-020-01704-5","volume":"50","author":"Q-C Mao","year":"2020","unstructured":"Mao Q-C, Sun H-M, Zuo L-Q, Jia R-S (2020) Finding every car: A traffic surveillance multi-scale vehicle object detection method. Appl Intell 50:3125\u20133136","journal-title":"Appl Intell"},{"key":"2512_CR36","doi-asserted-by":"crossref","unstructured":"Dai X, Yuan X, Wei X (2020) Tirnet: Object detection in thermal infrared images for autonomous driving. Appl Intell:1\u201310","DOI":"10.1007\/s10489-020-01882-2"},{"key":"2512_CR37","first-page":"1","volume":"2","author":"Y Ren","year":"2018","unstructured":"Ren Y, Zhu C, Xiao S (2018) Small object detection in optical remote sensing images via modified faster r-cnn. Appl Sci 2:1\u201311","journal-title":"Appl Sci"},{"key":"2512_CR38","unstructured":"Yi K, Jian Z, Chen S, Chen Y, Zheng N (2018) Knowledge-based recurrent attentive neural network for traffic sign detection 4:15\u201318. arXiv:1803.05263"},{"key":"2512_CR39","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2512_CR40","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Y, Wang N, Zhang Z-X (2019) Scale-aware trident networks for object detection. In: IEEE International Conference on Computer Vision, pp 6053\u20136062","DOI":"10.1109\/ICCV.2019.00615"},{"key":"2512_CR41","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le Q (2020) Efficientdet: Scalable and efficient object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2512_CR42","doi-asserted-by":"crossref","unstructured":"Liu Z, Gao G, Sun L, Fang Z (2020) Hrdnet: High-resolution detection network for small objects, pp 1\u20138. arXiv:2006.07607","DOI":"10.1109\/ICME51207.2021.9428241"},{"key":"2512_CR43","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/s13042-015-0351-8","volume":"8","author":"S Ding","year":"2017","unstructured":"Ding S, Zhang N, Zhang J, Xu X, Shi Z (2017) Unsupervised extreme learning machine with representational features. Int J Mach Learn Cybern 8:587\u2013595","journal-title":"Int J Mach Learn Cybern"},{"key":"2512_CR44","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s13042-015-0419-5","volume":"7","author":"J Zhang","year":"2016","unstructured":"Zhang J, Ding S, Zhang N, Shi Z (2016) Incremental extreme learning machine based on deep feature embedded. Int J Mach Learn Cybern 7:111\u2013120","journal-title":"Int J Mach Learn Cybern"},{"key":"2512_CR45","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1007\/s13042-016-0550-y","volume":"8","author":"L Meng","year":"2016","unstructured":"Meng L, Ding S, Xue Y (2016) Research on denoising sparse autoencoder. Int J Mach Learn Cybern 8:1719\u20131729","journal-title":"Int J Mach Learn Cybern"},{"key":"2512_CR46","unstructured":"Zhu P, Wen L, Du D, Bian X, Hu Q, Ling H (2020) Vision meets drones: Past, present and future, pp 1\u201311. arXiv:2001.06303"},{"key":"2512_CR47","doi-asserted-by":"crossref","unstructured":"Du D, Qi Y, Yu H, Yang Y, Duan K, Li G, Zhang W, Tian Q (2018) The unmanned aerial vehicle benchmark: Object detection and tracking, pp 1\u201317","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"2512_CR48","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollr P, Zitnick C (2014) Microsoft coco: Common objects in context. In: IEEE International Conference on Computer Vision, vol 8693, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2512_CR49","unstructured":"Fu C-Y, Liu W, Ranga A, Tyagi A, Berg A C (2017) Dssd: Deconvolutional single shot detector. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u201311"},{"key":"2512_CR50","doi-asserted-by":"crossref","unstructured":"Yang F, Fan H, Chu P, Blasch E, Ling H (2019) Clustered object detection in aerial images. In: IEEE International Conference on Computer Vision, pp 1\u201310","DOI":"10.1109\/ICCV.2019.00840"},{"key":"2512_CR51","unstructured":"Singh B, Najibi M, Davis L (2018) Sniper: Efficient multi-scale training. In: Conference on Neural Information Processing Systems, pp 1\u201311"},{"key":"2512_CR52","doi-asserted-by":"crossref","unstructured":"Singh B, Davis L (2018) An analysis of scale invariance in object detection-snip. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u201310","DOI":"10.1109\/CVPR.2018.00377"},{"key":"2512_CR53","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li S (2020) Refinedet++: Single-shot refinement neural network for object detection. IEEE Trans Circ Sys Video Technol:1\u201310"},{"key":"2512_CR54","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, Wang Y (2018) Receptive field block net for accurate and fast object detection. In: European Conference on Computer Vision, pp 404\u2013419","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"2512_CR55","doi-asserted-by":"crossref","unstructured":"Kim S-W, Kook H-K, Sun J-Y, Kang M-C, Ko S-J (2018) Parallel feature pyramid network for object detection. In: European Conference on Computer Vision, pp 234\u2013250","DOI":"10.1007\/978-3-030-01228-1_15"},{"key":"2512_CR56","doi-asserted-by":"crossref","unstructured":"Wang T, Anwer R M, Cholakkal H, Khan F S, Pang Y, Shao L (2019) Learning rich features at high-speed for single-shot object detection. In: IEEE International Conference on Computer Vision, pp 1971\u20131980","DOI":"10.1109\/ICCV.2019.00206"},{"key":"2512_CR57","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: European Conference on Computer Vision, pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2512_CR58","first-page":"9259","volume":"33","author":"Q Zhao","year":"2019","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2019) M2det: A single-shot object detector based on multi-level feature pyramid network. Proc AAAI Conf Artif Intell 33:9259\u20139266","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"2512_CR59","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detectionv","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2512_CR60","doi-asserted-by":"crossref","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 840\u2013849","DOI":"10.1109\/CVPR.2019.00093"},{"key":"2512_CR61","unstructured":"Liu S, Huang D, Wang Y (2019) Learning spatial fusion for single-shot object detection, pp 1\u20138. arXiv:1911.09516"},{"key":"2512_CR62","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Tian Q (2019) Centernet: Object detection with keypoint triplets for object detection. In: IEEE International Conference on Computer Vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2512_CR63","unstructured":"Zhu C, Chen F, Shen Z, Savvides M (2019) Soft anchor-point object detection, pp 1\u20139. arXiv:1911.12448"},{"key":"2512_CR64","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y, Lei Z, Li S (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u201310","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"2512_CR65","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: IEEE International Conference on Computer Vision, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02512-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02512-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02512-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T06:49:34Z","timestamp":1645512574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02512-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,20]]},"references-count":65,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["2512"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02512-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,20]]},"assertion":[{"value":"5 May 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}