{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T03:30:32Z","timestamp":1762918232474,"version":"3.41.2"},"reference-count":43,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T00:00:00Z","timestamp":1619395200000},"content-version":"vor","delay-in-days":115,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2020GXNSFBA238014","2019GXNSFAA245014"],"award-info":[{"award-number":["2020GXNSFBA238014","2019GXNSFAA245014"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906050","61866009","62002082"],"award-info":[{"award-number":["61906050","61866009","62002082"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Pedestrian detection based on visual sensors has made significant progress, in which region proposal is the key step. There are two mainstream methods to generate region proposals: anchor\u2010based and anchor\u2010free. However, anchor\u2010based methods need more hyperparameters related to anchors for training compared with anchor\u2010free methods. In this paper, we propose a novel multiscale anchor\u2010free (MSAF) region proposal network to obtain proposals, especially for small\u2010scale pedestrians. It usually has several branches to predict proposals and assigns ground truth according to the height of pedestrian. Each branch consists of two components: one is feature extraction, and the other is detection head. Adapted channel feature fusion (ACFF) is proposed to select features at different levels of the backbone to effectively extract features. The detection head is used to predict the pedestrian center location, center offsets, and height to get bounding boxes. With our classifier, the detection performance can be further improved, especially for small\u2010scale pedestrians. The experiments on the Caltech and CityPersons demonstrate that the MSAF can significantly boost the pedestrian detection performance and the log\u2010average miss rate (MR) on the reasonable setting is 3.97% and 9.5%, respectively. If proposals are reclassified with our classifier, MR is 3.38% and 8.4%. The detection performance can be further improved, especially for small\u2010scale pedestrians.<\/jats:p>","DOI":"10.1155\/2021\/5590895","type":"journal-article","created":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T19:16:58Z","timestamp":1619464618000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multiscale Anchor\u2010Free Region Proposal Network for Pedestrian Detection"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8409-8089","authenticated-orcid":false,"given":"Zhiwei","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6334-4044","authenticated-orcid":false,"given":"Huihua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8371-8330","authenticated-orcid":false,"given":"Weijin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5005-0036","authenticated-orcid":false,"given":"Juan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9402-0421","authenticated-orcid":false,"given":"Lingqiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2581-0520","authenticated-orcid":false,"given":"Xipeng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,4,26]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"crossref","unstructured":"CaiZ.andHeZ. Trading private range counting over big IoT data 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) 2019 Dallas TX USA 144\u2013153 https:\/\/doi.org\/10.1109\/ICDCS.2019.00023.","DOI":"10.1109\/ICDCS.2019.00023"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2911697"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.122"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107144"},{"key":"e_1_2_10_5_2","unstructured":"BrazilG.andLiuX. Pedestrian detection with autoregressive network phases 2018 https:\/\/arxiv.org\/abs\/1812.00440."},{"key":"e_1_2_10_6_2","unstructured":"CaoG. XieX. YangW. LiaoQ. ShiG. andWuJ. Feature-fused SSD: fast detection for small objects 2017 https:\/\/arxiv.org\/abs\/1709.05054."},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"GirshickR. B. Fast R-CNN 2015 IEEE International Conference on Computer Vision (ICCV) 2015 Santiago Chile 1440\u20131448 https:\/\/doi.org\/10.1109\/ICCV.2015.169 2-s2.0-84964588182.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759508"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"LinT. Doll\u00e1rP. GirshickR. B. HeK. HariharanB. andBelongieS. J. Feature pyramid networks for object detection 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Honolulu HI USA 936\u2013944 https:\/\/doi.org\/10.1109\/CVPR.2017.106 2-s2.0-85041898381.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_10_10_2","doi-asserted-by":"crossref","unstructured":"DuanK. BaiS. XieL. QiH. HuangQ. andTianQ. Centernet: keypoint triplets for object detection 2019 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) 2019 Seoul Korea (South) 6568\u20136577 https:\/\/doi.org\/10.1109\/ICCV.2019.00667.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"LiuW. LiaoS. RenW. HuW. andYuY. High-level semantic feature detection: a new perspective for pedestrian detection 2019 https:\/\/arxiv.org\/abs\/1904.02948.","DOI":"10.1109\/CVPR.2019.00533"},{"key":"e_1_2_10_13_2","doi-asserted-by":"crossref","unstructured":"RedmonJ. DivvalaS. K. GirshickR. B. andFarhadiA. You only look once: unified real-time object detection 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 Las Vegas NV USA 779\u2013788 https:\/\/doi.org\/10.1109\/CVPR.2016.91 2-s2.0-84986308404.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"TianZ. ShenC. ChenH. andHeT. FCOS: fully convolutional one-stage object detection 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) 2019 Seoul Korea (south) 9626\u20139635 https:\/\/doi.org\/10.1109\/ICCV.2019.00972.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_2_10_15_2","unstructured":"WangW. Adapted center and scale prediction: more stable and more accurate 2020 https:\/\/arxiv.org\/abs\/2002.09053."},{"key":"e_1_2_10_16_2","unstructured":"ZhangJ. LinL. ChenY. HuY. HoiS. C. H. andZhuJ. Attribute-aware pedestrian detection in a crowd 2019 http:\/\/arxiv.org\/abs\/1910.09188."},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932749"},{"key":"e_1_2_10_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"e_1_2_10_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"e_1_2_10_21_2","unstructured":"BochkovskiyA. WangC. andLiaoH. M. Yolov 4: optimal speed and accuracy of object detection 2020 https:\/\/arxiv.org\/abs\/2004.10934."},{"key":"e_1_2_10_22_2","unstructured":"RedmonJ.andFarhadiA. Yolov 3: an incremental improvement 2018 https:\/\/arxiv.org\/abs\/1804.02767."},{"key":"e_1_2_10_23_2","unstructured":"OksuzK. CamB. C. KalkanS. andAkbasE. Imbalance problems in object detection: a review 2019 https:\/\/arxiv.org\/abs\/1909.00169."},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"LinT. GoyalP. GirshickR. B. HeK. andDoll\u00e1rP. Focal loss for dense object detection 2017 IEEE International Conference on Computer Vision (ICCV) 2017 Venice Italy 2999\u20133007 https:\/\/doi.org\/10.1109\/ICCV.2017.324 2-s2.0-85041916350.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"ZhuC. HeY. andSavvidesM. Feature selective anchor-free module for single-shot object detection 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019 Long Beach CA USA 840\u2013849 https:\/\/doi.org\/10.1109\/CVPR.2019.00093.","DOI":"10.1109\/CVPR.2019.00093"},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"e_1_2_10_27_2","doi-asserted-by":"crossref","unstructured":"ZhangS. BenensonR. andSchieleB. Citypersons: a diverse dataset for pedestrian detection 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Honolulu HI USA 4457\u20134465 https:\/\/doi.org\/10.1109\/CVPR.2017.474 2-s2.0-85044330244.","DOI":"10.1109\/CVPR.2017.474"},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"BrazilG. YinX. andLiuX. Illuminating pedestrians via simultaneous detection and segmentation 2017 IEEE International Conference on Computer Vision (ICCV) 2017 Venice Italy https:\/\/doi.org\/10.1109\/ICCV.2017.530 2-s2.0-85041911808.","DOI":"10.1109\/ICCV.2017.530"},{"key":"e_1_2_10_29_2","unstructured":"ZhouC. WuM. andLamS. K. Ssa-cnn: semantic self-attention cnn for pedestrian detection 2019 https:\/\/arxiv.org\/abs\/1902.09080."},{"key":"e_1_2_10_30_2","unstructured":"WangX. XiaoT. JiangY. ShaoS. SunJ. andShenC. Repulsion loss: detecting pedestrians in a crowd 2017 https:\/\/arxiv.org\/abs\/1711.07752."},{"key":"e_1_2_10_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_39"},{"key":"e_1_2_10_32_2","doi-asserted-by":"crossref","unstructured":"YuJ. JiangY. WangZ. CaoZ. andHuangT. S. Unitbox: an advanced object detection network Proceedings of the 24th ACM international conference on Multimedia 2016 Amsterdam the Netherlands 516\u2013520 https:\/\/doi.org\/10.1145\/2964284.2967274 2-s2.0-84994560549.","DOI":"10.1145\/2964284.2967274"},{"key":"e_1_2_10_33_2","unstructured":"HuangL. YangY. DengY. andYuY. Densebox: unifying landmark localization with end to end object detection 2015 https:\/\/arxiv.org\/abs\/1509.04874."},{"key":"e_1_2_10_34_2","doi-asserted-by":"crossref","unstructured":"ZhouX. ZhuoJ. andKr\u00e4henb\u00fchlP. Bottom-up object detection by grouping extreme and center points 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019b Long Beach CA USA 850\u2013859 https:\/\/doi.org\/10.1109\/CVPR.2019.00094.","DOI":"10.1109\/CVPR.2019.00094"},{"key":"e_1_2_10_35_2","unstructured":"HowardA. G. ZhuM. ChenB. KalenichenkoD. WangW. WeyandT. AndreettoM. andAdamH. Mobilenets: efficient convolutional neural networks for mobile vision applications 2017 https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_10_36_2","unstructured":"SimonyanK.andZissermanA. Very deep convolutional networks for large-scale image recognition 3rd International Conference on Learning Representations ICLR 2015 2015 San Diego CA USA."},{"key":"e_1_2_10_37_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 Las Vegas NV USA 770\u2013778 https:\/\/doi.org\/10.1109\/CVPR.2016.90 2-s2.0-84986274465.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_38_2","doi-asserted-by":"crossref","unstructured":"HuangG. LiuZ. van der MaatenL. andWeinbergerK. Q. Densely connected convolutional networks 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Honolulu HI USA 2261\u20132269 https:\/\/doi.org\/10.1109\/CVPR.2017.243 2-s2.0-85035343801.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_10_39_2","doi-asserted-by":"crossref","unstructured":"HeK. GkioxariG. Doll\u00e1rP. andGirshickR. B. Mask R-CNN 2017 IEEE International Conference on Computer Vision (ICCV) 2017 Venice Italy 2980\u20132988 https:\/\/doi.org\/10.1109\/ICCV.2017.322 2-s2.0-85040313738.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_10_40_2","doi-asserted-by":"crossref","unstructured":"MaoJ. XiaoT. JiangY. andCaoZ. What can help pedestrian detection? 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Honolulu HI USA 6034\u20136043 https:\/\/doi.org\/10.1109\/CVPR.2017.639 2-s2.0-85044508040.","DOI":"10.1109\/CVPR.2017.639"},{"key":"e_1_2_10_41_2","unstructured":"CaiZ.andVasconcelosN. Cascade R-CNN: high quality object detection and instance segmentation 2019 https:\/\/arxiv.org\/abs\/1906.09756."},{"key":"e_1_2_10_42_2","doi-asserted-by":"crossref","unstructured":"ZhangS. BenensonR. OmranM. HosangJ. H. andSchieleB. How far are we from solving pedestrian detection? 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016b Las Vegas NV USA 1259\u20131267 https:\/\/doi.org\/10.1109\/CVPR.2016.141 2-s2.0-84986325243.","DOI":"10.1109\/CVPR.2016.141"},{"key":"e_1_2_10_43_2","unstructured":"ZouZ. ShiZ. GuoY. andYeJ. Object detection in 20 years: a survey 2019 https:\/\/arxiv.org\/abs\/1905.05055."}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/5590895.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/5590895.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5590895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T14:00:20Z","timestamp":1723039220000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5590895"}},"subtitle":[],"editor":[{"given":"Yingjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5590895"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5590895","archive":["Portico"],"relation":{},"ISSN":["1530-8669","1530-8677"],"issn-type":[{"type":"print","value":"1530-8669"},{"type":"electronic","value":"1530-8677"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-02-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5590895"}}