{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:09:13Z","timestamp":1760609353570,"version":"3.37.3"},"reference-count":28,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61603040","61973036"],"award-info":[{"award-number":["61603040","61973036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Yunnan Applied Basic Research Project of China","award":["201701CF00037"],"award-info":[{"award-number":["201701CF00037"]}]},{"DOI":"10.13039\/501100018568","name":"Guangdong Province Science and Technology Innovation Strategy Special Fund Project","doi-asserted-by":"crossref","award":["skjtdzxrwqd2018001"],"award-info":[{"award-number":["skjtdzxrwqd2018001"]}],"id":[{"id":"10.13039\/501100018568","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Yunnan Provincial Science and Technology Department Key Research Program, China","award":["2018BA070"],"award-info":[{"award-number":["2018BA070"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Un. Sys."],"published-print":{"date-parts":[[2022,1]]},"abstract":"<jats:p> Visual-based object detection has large applications in security and surveillance for unmanned aerial vehicles (UAVs). Meanwhile, the object detectors are required of low-latency and easy to be deployed on embedded onboard platforms. Aiming to address these problems, we present a PA-YOLOv3 aerial images object detector based on YOLOv3 and PANet algorithms, which can be deployed on embedded platforms. The PA-YOLOv3 model uses the dual-tower structure to improve the feature extraction and expression capabilities in feature fusion stage of the network. Besides, we propose a balanced pruning method to reduce the model size and the imbalance of different feature layers during pruning. After balanced pruning, the latency and size of the model are significantly decreased. Finally, we deploy and quantify the model on the embedded platform with TensorRT technology and apply the model on the UAV system for testing. The comprehensive experiments are executed on VisDrone2018 dataset and real-world scenarios. The experimental results show the inference speed of PA-YOLOv3 boost of about [Formula: see text] model pruning and quantization, while maintaining high detection accuracy. <\/jats:p>","DOI":"10.1142\/s2301385022500030","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T15:59:10Z","timestamp":1618847950000},"page":"57-67","source":"Crossref","is-referenced-by-count":10,"title":["Low-Latency Aerial Images Object Detection for UAV"],"prefix":"10.1142","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7275-1995","authenticated-orcid":false,"given":"Kai","family":"Feng","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3100-5926","authenticated-orcid":false,"given":"Weixing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Han","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, P. R. China"},{"name":"Kunming-BIT Industry Technology, Research Institute Co. Ltd, Kunming 650106, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2021,5,20]]},"reference":[{"key":"S2301385022500030BIB001","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385020500090"},{"issue":"2","key":"S2301385022500030BIB002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.14323\/ijuseng.2014.4","volume":"2","author":"Cai G. W.","year":"2014","journal-title":"Unmanned Syst."},{"key":"S2301385022500030BIB003","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"S2301385022500030BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"S2301385022500030BIB005","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"S2301385022500030BIB006","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"S2301385022500030BIB007","first-page":"91","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Ren S. Q.","year":"2015"},{"key":"S2301385022500030BIB008","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"S2301385022500030BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"S2301385022500030BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"S2301385022500030BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"S2301385022500030BIB013","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"S2301385022500030BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"S2301385022500030BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"S2301385022500030BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2808368"},{"key":"S2301385022500030BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"S2301385022500030BIB018","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385016400094"},{"key":"S2301385022500030BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2017.8107763"},{"key":"S2301385022500030BIB020","first-page":"1269","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Denton E. L.","year":"2014"},{"key":"S2301385022500030BIB021","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"S2301385022500030BIB022","first-page":"1135","volume-title":"Proc. of the Advances in Neural Information Processing Systems","author":"Han S.","year":"2015"},{"key":"S2301385022500030BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"S2301385022500030BIB024","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00103"},{"key":"S2301385022500030BIB025","doi-asserted-by":"publisher","DOI":"10.1145\/3229762.3229763"},{"volume-title":"Proc. 2017 GPU Technology Conf.","year":"2017","author":"Szymon M.","key":"S2301385022500030BIB026"},{"key":"S2301385022500030BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"volume-title":"Proc. Int. Conf. Learning Representations","year":"2018","author":"Zhang H. Y.","key":"S2301385022500030BIB029"},{"key":"S2301385022500030BIB031","first-page":"437","volume-title":"Proc. 15th European Conf. Computer Vision Workshops","author":"Zhu P. F.","year":"2018"}],"container-title":["Unmanned Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S2301385022500030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T11:24:39Z","timestamp":1642677879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S2301385022500030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,20]]},"references-count":28,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10.1142\/S2301385022500030"],"URL":"https:\/\/doi.org\/10.1142\/s2301385022500030","relation":{},"ISSN":["2301-3850","2301-3869"],"issn-type":[{"type":"print","value":"2301-3850"},{"type":"electronic","value":"2301-3869"}],"subject":[],"published":{"date-parts":[[2021,5,20]]}}}