YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving
The use of object detection algorithms has become extremely important in autonomous vehicles. Object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. Therefore, the balance between the effectiveness and efficiency of the object detector must be consider...
Saved in:
Published in | IEEE transactions on instrumentation and measurement Vol. 70; pp. 1 - 13 |
---|---|
Main Authors | , , , , , , , |
Format | Journal Article |
Language | English |
Published |
New York
IEEE
2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The use of object detection algorithms has become extremely important in autonomous vehicles. Object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. Therefore, the balance between the effectiveness and efficiency of the object detector must be considered. This article proposes a one-stage object detection framework for improving the detection accuracy while supporting a true real-time operation based on the YOLOv4. The backbone network in the proposed framework is the CSPDarknet53_dcn(P). The last output layer in the CSPDarknet53 is replaced with deformable convolution to improve the detection accuracy. In order to perform feature fusion, a new feature fusion module PAN++ is designed and five scales detection layers are used to improve the detection accuracy of small objects. In addition, this article proposes an optimized network pruning algorithm to solve the problem that the real-time performance of the algorithm cannot be satisfied due to the limited computing resources of the vehicle-mounted computing platform. The method of sparse scaling factor is used to improve the existing channel pruning algorithm. Compared to the YOLOv4, the YOLOV4-5D improves the mean average precision by 4.23% on the BDD data sets and 1.68% on the KITTI data sets. Finally, by pruning the model, the inference speed of YOLOV4-5D is increased 31.3% and the memory is only 98.1 MB when the detection accuracy is almost unchanged. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 66 frames/s (fps) and shows higher accuracy than the previous approaches with a similar fps. |
---|---|
AbstractList | The use of object detection algorithms has become extremely important in autonomous vehicles. Object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. Therefore, the balance between the effectiveness and efficiency of the object detector must be considered. This article proposes a one-stage object detection framework for improving the detection accuracy while supporting a true real-time operation based on the YOLOv4. The backbone network in the proposed framework is the CSPDarknet53_dcn(P). The last output layer in the CSPDarknet53 is replaced with deformable convolution to improve the detection accuracy. In order to perform feature fusion, a new feature fusion module PAN++ is designed and five scales detection layers are used to improve the detection accuracy of small objects. In addition, this article proposes an optimized network pruning algorithm to solve the problem that the real-time performance of the algorithm cannot be satisfied due to the limited computing resources of the vehicle-mounted computing platform. The method of sparse scaling factor is used to improve the existing channel pruning algorithm. Compared to the YOLOv4, the YOLOV4-5D improves the mean average precision by 4.23% on the BDD data sets and 1.68% on the KITTI data sets. Finally, by pruning the model, the inference speed of YOLOV4-5D is increased 31.3% and the memory is only 98.1 MB when the detection accuracy is almost unchanged. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 66 frames/s (fps) and shows higher accuracy than the previous approaches with a similar fps. |
Author | Li, Yicheng Gao, Hongbo Chen, Long Wang, Hai Sotelo, Miguel Angel Cai, Yingfeng Luan, Tianyu Li, Zhixiong |
Author_xml | – sequence: 1 givenname: Yingfeng orcidid: 0000-0002-0633-9887 surname: Cai fullname: Cai, Yingfeng email: caicaixiao0304@126.com organization: Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China – sequence: 2 givenname: Tianyu orcidid: 0000-0002-5365-656X surname: Luan fullname: Luan, Tianyu email: luan_tianyu@qq.com organization: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, China – sequence: 3 givenname: Hongbo orcidid: 0000-0002-5271-1280 surname: Gao fullname: Gao, Hongbo email: ghb48@ustc.edu.cn organization: Department of Automation, University of Science and Technology of China, Hefei, China – sequence: 4 givenname: Hai orcidid: 0000-0002-9136-8091 surname: Wang fullname: Wang, Hai email: wanghai1019@163.com organization: School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, China – sequence: 5 givenname: Long orcidid: 0000-0002-2079-3867 surname: Chen fullname: Chen, Long email: chenlong@ujs.edu.cn organization: Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China – sequence: 6 givenname: Yicheng orcidid: 0000-0003-2937-7162 surname: Li fullname: Li, Yicheng email: liyucheng070@163.com organization: Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China – sequence: 7 givenname: Miguel Angel orcidid: 0000-0001-8809-2103 surname: Sotelo fullname: Sotelo, Miguel Angel email: miguel.sotelo@uah.es organization: Department of Computer Engineering, University of Alcal, Madrid, Spain – sequence: 8 givenname: Zhixiong orcidid: 0000-0002-7265-0008 surname: Li fullname: Li, Zhixiong email: zhixiong_li@uow.edu.au organization: Yonsei Frontier Laboratory, Yonsei University, Seoul, South Korea |
BookMark | eNo9kM1LAzEQxYNUsK3eBS8LnrdOvhNvpa1aWNlLPXgKu2lWUmxSs7sF_3u3tHgYHjO8Nw9-EzQKMTiE7jHMMAb9tFm_zwgQPKMgOKPqCo0x5zLXQpARGgNglWvGxQ2atO0OAKRgcoyKz7Iojyzny-dsHrJV0zjb-aPLqrA9bd56F7qsrHfDPVu6bpCYsmaYed_FEPexb7Nl8kcfvm7RdVN9t-7uolP08bLaLN7yonxdL-ZFbilVXS4wA7BWYCUrVbMaU-xqyzWxYDXREoAwypTbNrhiWNaVEsJRQqVlDGu-pVP0eP57SPGnd21ndrFPYag0hAMXoDjRgwvOLpti2ybXmEPy-yr9GgzmxMwMzMyJmbkwGyIP54h3zv3bNZVMa6B_hjtmmw |
CODEN | IEIMAO |
CitedBy_id | crossref_primary_10_1088_1361_6501_ac8275 crossref_primary_10_1016_j_jag_2023_103489 crossref_primary_10_1109_JSEN_2024_3355388 crossref_primary_10_1155_2022_3843021 crossref_primary_10_1109_TIM_2023_3327472 crossref_primary_10_1155_2022_2253697 crossref_primary_10_1109_ACCESS_2024_3351771 crossref_primary_10_1109_TIM_2023_3269780 crossref_primary_10_1049_itr2_12214 crossref_primary_10_1049_itr2_12336 crossref_primary_10_1109_TIM_2022_3191724 crossref_primary_10_1109_ACCESS_2023_3302909 crossref_primary_10_1155_2023_5602595 crossref_primary_10_1109_TVT_2022_3195608 crossref_primary_10_1109_JSEN_2022_3208076 crossref_primary_10_3390_s22103742 crossref_primary_10_1109_TIM_2024_3412212 crossref_primary_10_1108_IJIUS_03_2024_0065 crossref_primary_10_1016_j_eswa_2021_115417 crossref_primary_10_1109_ACCESS_2022_3143365 crossref_primary_10_1109_TIM_2022_3150568 crossref_primary_10_1155_2022_7919875 crossref_primary_10_1109_TITS_2023_3253554 crossref_primary_10_1049_itr2_12320 crossref_primary_10_1109_TCE_2023_3326183 crossref_primary_10_26599_JICV_2023_9210019 crossref_primary_10_1049_itr2_12174 crossref_primary_10_1109_TIM_2024_3385037 crossref_primary_10_1109_TIM_2023_3336760 crossref_primary_10_1049_itr2_12172 crossref_primary_10_1155_2022_3705256 crossref_primary_10_3390_app12188948 crossref_primary_10_1049_itr2_12291 crossref_primary_10_3390_machines10080668 crossref_primary_10_1049_ipr2_12595 crossref_primary_10_1007_s11042_022_14084_4 crossref_primary_10_1109_ACCESS_2021_3125703 crossref_primary_10_1109_TIM_2022_3196954 crossref_primary_10_1155_2022_5033601 crossref_primary_10_1109_TETCI_2024_3367821 crossref_primary_10_1109_TIM_2021_3094622 crossref_primary_10_1109_TITS_2022_3195633 crossref_primary_10_1049_itr2_12120 crossref_primary_10_3390_s23073385 crossref_primary_10_1109_TITS_2022_3164407 crossref_primary_10_1109_ACCESS_2023_3240439 crossref_primary_10_1109_TIM_2023_3341122 crossref_primary_10_1007_s12065_023_00849_9 crossref_primary_10_3390_math12091331 crossref_primary_10_1109_ACCESS_2023_3321290 crossref_primary_10_1109_TIM_2024_3394483 crossref_primary_10_1109_TVT_2023_3241203 crossref_primary_10_1109_TITS_2023_3296508 crossref_primary_10_1109_TIM_2022_3158998 crossref_primary_10_1109_TIM_2023_3341131 crossref_primary_10_1155_2022_2259113 crossref_primary_10_1109_TIP_2021_3122293 crossref_primary_10_1109_TNNLS_2021_3128968 crossref_primary_10_1109_ACCESS_2022_3221942 crossref_primary_10_1109_TIV_2024_3353254 crossref_primary_10_1109_TIM_2023_3284928 crossref_primary_10_1109_TIM_2022_3181903 crossref_primary_10_1109_TIM_2023_3295017 crossref_primary_10_1109_ACCESS_2023_3331426 crossref_primary_10_1109_TIM_2023_3251414 crossref_primary_10_1155_2022_9463559 crossref_primary_10_1109_TITS_2023_3273817 crossref_primary_10_1109_TIM_2024_3413179 crossref_primary_10_1109_TIM_2022_3204080 crossref_primary_10_1007_s00500_023_09278_3 crossref_primary_10_1109_LSP_2021_3134171 crossref_primary_10_32604_iasc_2023_037902 crossref_primary_10_11728_cjss2023_05_2022_0044 crossref_primary_10_1109_ACCESS_2023_3245146 crossref_primary_10_1109_TIM_2022_3219500 crossref_primary_10_1088_2631_8695_ac8de1 crossref_primary_10_1109_MITS_2022_3201400 crossref_primary_10_3390_electronics12204281 crossref_primary_10_1109_ACCESS_2024_3394693 crossref_primary_10_1109_TIM_2024_3374313 crossref_primary_10_3390_jmse10121821 crossref_primary_10_1109_TIM_2024_3417547 crossref_primary_10_1109_TIM_2022_3201546 crossref_primary_10_1109_TITS_2022_3221067 crossref_primary_10_1109_TIM_2022_3176899 crossref_primary_10_1049_itr2_12367 crossref_primary_10_1155_2022_9328398 crossref_primary_10_3390_s22218097 crossref_primary_10_1155_2023_9215528 crossref_primary_10_1049_itr2_12253 crossref_primary_10_1109_JSEN_2023_3262134 crossref_primary_10_1103_PhysRevA_106_023516 crossref_primary_10_1109_ACCESS_2023_3327735 crossref_primary_10_1109_TIM_2022_3192056 crossref_primary_10_3390_machines10080626 crossref_primary_10_1109_TETCI_2023_3235381 crossref_primary_10_1109_TITS_2022_3202834 crossref_primary_10_3390_s22166316 crossref_primary_10_1155_2022_9056415 crossref_primary_10_1049_cvi2_12236 crossref_primary_10_3390_math10132199 crossref_primary_10_1109_TIM_2023_3241078 crossref_primary_10_3390_en15217956 crossref_primary_10_1109_TIM_2022_3165251 crossref_primary_10_3390_electronics13010010 crossref_primary_10_3390_su141811292 crossref_primary_10_1155_2021_9218137 crossref_primary_10_1109_TIM_2022_3177720 crossref_primary_10_1109_TTE_2023_3263592 crossref_primary_10_1109_TITS_2022_3215172 crossref_primary_10_1109_ACCESS_2021_3126796 crossref_primary_10_3390_s24123829 crossref_primary_10_46387_bjesr_1106501 crossref_primary_10_7717_peerj_cs_2021 crossref_primary_10_1155_2022_5818180 crossref_primary_10_3389_fcell_2022_941542 crossref_primary_10_1007_s11042_023_16736_5 crossref_primary_10_1109_TIM_2022_3229717 crossref_primary_10_1109_TIM_2022_3169564 crossref_primary_10_1109_TITS_2022_3177615 crossref_primary_10_1109_OJITS_2022_3160888 crossref_primary_10_1016_j_eswa_2022_117586 crossref_primary_10_1007_s12083_022_01390_9 crossref_primary_10_1049_itr2_12386 crossref_primary_10_11728_cjss2023_04_2022_0044 crossref_primary_10_1109_JSEN_2024_3401187 crossref_primary_10_1007_s11042_023_14439_5 crossref_primary_10_1109_ACCESS_2022_3147069 crossref_primary_10_1109_ACCESS_2023_3341928 crossref_primary_10_1109_TIM_2022_3216880 |
Cites_doi | 10.1109/CVPR.2018.00644 10.1007/978-3-030-58452-8_45 10.1109/CVPR.2016.90 10.1109/ITSC.2014.6957844 10.14358/PERS.81.2.103 10.1109/CVPR.2018.00913 10.1109/TPAMI.2015.2389824 10.1109/TIM.2015.2440556 10.1109/TITS.2021.3052908 10.1109/TIM.2018.2877285 10.1007/s11760-020-01760-x 10.1109/TELFOR.2018.8611986 10.1109/MIM.2014.6825388 10.1016/j.image.2018.09.002 10.1109/TIM.2018.2840598 10.1109/CVPR.2017.690 10.1109/CVPR.2012.6248074 10.1109/CVPR.2016.91 10.1016/j.aci.2017.05.002 10.1109/CVPRW.2017.60 10.1016/j.neunet.2018.02.005 10.1109/TIP.2020.2972692 10.1109/TIM.2014.2307992 10.1007/978-3-319-46493-0_22 10.1109/WACV.2018.00083 10.1109/ICCV.2017.89 10.1109/TITS.2021.3059674 10.1109/MITS.2019.2903518 10.1007/978-3-030-01252-6_24 10.1109/TITS.2018.2838132 10.1109/CVPRW50498.2020.00203 10.1016/j.patrec.2009.09.011 10.1109/TIP.2018.2888701 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
DBID | 97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M |
DOI | 10.1109/TIM.2021.3065438 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
DatabaseTitle | CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
DatabaseTitleList | Solid State and Superconductivity Abstracts |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Physics |
EISSN | 1557-9662 |
EndPage | 13 |
ExternalDocumentID | 10_1109_TIM_2021_3065438 9374990 |
Genre | orig-research |
GrantInformation_xml | – fundername: National Key Research and Development Program of China grantid: 2018YFB0105000 funderid: 10.13039/501100012166 – fundername: Key Research and Development Program of Jiangsu Province grantid: BE2019010-2; BE2020083-3 funderid: 10.13039/501100013058 – fundername: Natural Science Foundation of Jiangsu Province grantid: BK20180100 funderid: 10.13039/501100004608 – fundername: National Natural Science Foundation of China grantid: U20A20333; 52072160; 51875255; U1764264 funderid: 10.13039/501100001809 – fundername: Jiangsu Province’s six talent peaks grantid: TD-GDZB-022 funderid: 10.13039/501100010014 |
GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 85S 8WZ 97E A6W AAJGR AASAJ AAYOK ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETIX AI. AIBXA AKJIK ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RIG RNS TN5 TWZ VH1 VJK XFK AAYXX CITATION 7SP 7U5 8FD L7M |
ID | FETCH-LOGICAL-c338t-61400cc6187a8b4b131ebc592c0c92970024348edf1a417ba866e3237c44195d3 |
IEDL.DBID | RIE |
ISSN | 0018-9456 |
IngestDate | Fri Sep 13 05:25:54 EDT 2024 Fri Aug 23 02:16:44 EDT 2024 Wed Jun 26 19:25:35 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c338t-61400cc6187a8b4b131ebc592c0c92970024348edf1a417ba866e3237c44195d3 |
ORCID | 0000-0002-5365-656X 0000-0002-0633-9887 0000-0002-5271-1280 0000-0003-2937-7162 0000-0002-9136-8091 0000-0002-2079-3867 0000-0001-8809-2103 0000-0002-7265-0008 |
PQID | 2505608529 |
PQPubID | 85462 |
PageCount | 13 |
ParticipantIDs | crossref_primary_10_1109_TIM_2021_3065438 ieee_primary_9374990 proquest_journals_2505608529 |
PublicationCentury | 2000 |
PublicationDate | 20210000 2021-00-00 20210101 |
PublicationDateYYYYMMDD | 2021-01-01 |
PublicationDate_xml | – year: 2021 text: 20210000 |
PublicationDecade | 2020 |
PublicationPlace | New York |
PublicationPlace_xml | – name: New York |
PublicationTitle | IEEE transactions on instrumentation and measurement |
PublicationTitleAbbrev | TIM |
PublicationYear | 2021 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref35 redmon (ref8) 2018 ref34 ref12 ref15 ref36 ref14 ref31 ref30 ref33 ref11 ref32 ref10 liu (ref16) 2016 ref1 ref39 ref17 ref38 ref19 ref18 zou (ref37) 2019 marshall (ref28) 2018 jocher (ref43) 2021 yu (ref13) 2018 zhao (ref25) 2018 ref24 ref23 ref26 ref20 ref42 ref41 ref22 park (ref40) 2016 ref21 ref27 ref29 ref7 ref4 ref3 ref6 ref5 ren (ref2) 2015 bochkovskiy (ref9) 2020 |
References_xml | – ident: ref5 doi: 10.1109/CVPR.2018.00644 – ident: ref36 doi: 10.1007/978-3-030-58452-8_45 – ident: ref17 doi: 10.1109/CVPR.2016.90 – ident: ref20 doi: 10.1109/ITSC.2014.6957844 – start-page: 21 year: 2016 ident: ref16 article-title: SSD: Single shot multibox detector publication-title: Proc Eur Conf Comput Vis contributor: fullname: liu – start-page: 91 year: 2015 ident: ref2 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: Proc Adv Neural Inf Process Syst (NIPS) contributor: fullname: ren – year: 2016 ident: ref40 article-title: Faster CNNs with direct sparse convolutions and guided pruning publication-title: arXiv 1608 01409 contributor: fullname: park – ident: ref38 doi: 10.14358/PERS.81.2.103 – ident: ref4 doi: 10.1109/CVPR.2018.00913 – year: 2018 ident: ref28 article-title: False positive: Self-driving cars and the agony of knowing what matters contributor: fullname: marshall – year: 2018 ident: ref13 article-title: BDD100K: A diverse driving dataset for heterogeneous multitask learning publication-title: arXiv 1805 04687 contributor: fullname: yu – ident: ref12 doi: 10.1109/TPAMI.2015.2389824 – year: 2020 ident: ref9 article-title: YOLOv4: Optimal speed and accuracy of object detection publication-title: arXiv 2004 10934 contributor: fullname: bochkovskiy – ident: ref6 doi: 10.1109/TIM.2015.2440556 – ident: ref29 doi: 10.1109/TITS.2021.3052908 – ident: ref21 doi: 10.1109/TIM.2018.2877285 – ident: ref41 doi: 10.1007/s11760-020-01760-x – ident: ref30 doi: 10.1109/TELFOR.2018.8611986 – ident: ref1 doi: 10.1109/MIM.2014.6825388 – year: 2018 ident: ref8 article-title: YOLOv3: An incremental improvement publication-title: arXiv 1804 02767 contributor: fullname: redmon – ident: ref18 doi: 10.1016/j.image.2018.09.002 – ident: ref3 doi: 10.1109/TIM.2018.2840598 – ident: ref10 doi: 10.1109/CVPR.2017.690 – year: 2019 ident: ref37 article-title: Object detection in 20 years: A survey publication-title: arXiv 1905 05055 contributor: fullname: zou – ident: ref32 doi: 10.1109/CVPR.2012.6248074 – ident: ref7 doi: 10.1109/CVPR.2016.91 – ident: ref15 doi: 10.1016/j.aci.2017.05.002 – ident: ref19 doi: 10.1109/CVPRW.2017.60 – ident: ref33 doi: 10.1016/j.neunet.2018.02.005 – ident: ref34 doi: 10.1109/TIP.2020.2972692 – ident: ref35 doi: 10.1109/TIM.2014.2307992 – ident: ref23 doi: 10.1007/978-3-319-46493-0_22 – start-page: 325 year: 2018 ident: ref25 article-title: Comprehensive feature enhancement module for single-shot object detector publication-title: Proc Asian Conf Comput Vis contributor: fullname: zhao – ident: ref42 doi: 10.1109/WACV.2018.00083 – ident: ref31 doi: 10.1109/ICCV.2017.89 – ident: ref39 doi: 10.1109/TITS.2021.3059674 – ident: ref22 doi: 10.1109/MITS.2019.2903518 – ident: ref27 doi: 10.1007/978-3-030-01252-6_24 – ident: ref24 doi: 10.1109/TITS.2018.2838132 – ident: ref11 doi: 10.1109/CVPRW50498.2020.00203 – ident: ref14 doi: 10.1016/j.patrec.2009.09.011 – ident: ref26 doi: 10.1109/TIP.2018.2888701 – year: 2021 ident: ref43 article-title: Ultralytics/yolov5: V4.0-nn.SiLU() activations, weights & biases logging, PyTorch hub integration (version v4.0) contributor: fullname: jocher |
SSID | ssj0007647 |
Score | 2.6790085 |
Snippet | The use of object detection algorithms has become extremely important in autonomous vehicles. Object detection at high accuracy and a fast inference speed is... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 1 |
SubjectTerms | Accuracy Algorithms Autonomous driving Autonomous vehicles Computation Computer networks Convolution CSPDarknet53 Datasets Detectors Feature extraction Formability Inference Inference algorithms Object detection Object recognition Pruning Real time operation Real-time systems Roads Scaling factors YOLOv4 |
Title | YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving |
URI | https://ieeexplore.ieee.org/document/9374990 https://www.proquest.com/docview/2505608529/abstract/ |
Volume | 70 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFH-oIOjBrynOL3LwItiuSdMvb8M5pjh3cTBPpUnfYAiduNaDf70vaTdEPXhroSkhL3nv93vJ-wXgMvA4GtLl-FokjiRS4WQ1kFMK80Tj1MouDp_CwVg-TILJGlyvamEQ0R4-Q9c82r38fK4rkyrrUCglgE4EfT32RF2rtfK6UShrfUxOC5hQwXJL0ks6z_dDIoKCu_aWdFOJ8i0E2TtVfjliG136uzBc9qs-VPLqVqVy9ecPycb_dnwPdhqYybr1vNiHNSwOYPub-OABbNrDn3rRgseX0ePoQzpB74Z1C1YLGpMXZFmRm7eZLZpkI2VyNqyHpc30M4K7rFuVpipiXi1Y731mkhOHMO7fPd8OnOaWBUcTPS2JO9Iy1jrkcZTFSiruc1Q6SIT2NGGnyGoWyhjzKc8kj1QWhyH6wo80IakkyP0j2CjmBR4Dy3w51SGhKIVCasximfhcZcE0kBgKEbfhajnw6VstppFaEuIlKRkpNUZKGyO1oWXGcfVdM4RtOFtaKm1W2yK1MI6wo0hO_m51Clvm33Xq5Aw2yvcKzwlMlOrCzqIvEyzCyQ |
link.rule.ids | 315,786,790,802,4043,27956,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED5VIAQMvBHl6YEFiZQ4cR5mqyhVgZYuRYIpip2rVCGliCYM_HrOTlohYGBLpFixfLbv-853nwHOA5ejIV2Orz3pCCIVTloBOaUwkxrHVnZx8Bj2nsT9c_DcgMtFLQwi2uQzbJlHe5afTXVpQmVX5EoJoBNBXyY_78qqWmux70ahqBQyOS1hwgXzQ0lXXo3uBkQFPd6y96SbWpRvTsjeqvJrK7b-pbsJg3nPqrSS11ZZqJb-_CHa-N-ub8FGDTRZu5oZ29DAfAfWv8kP7sCKTf_Us13ovwz7ww_hBJ1r1s5ZJWlM-yBL88y8TWzZJBsqE7VhHSxsrJ8R4GXtsjB1EdNyxjrvExOe2IOn7u3opufU9yw4mghqQeyRFrLWIY-jNFZCcZ-j0oH0tKsJPUVWtVDEmI15Knik0jgM0ff8SBOWkkHm78NSPs3xAFjqi7EOCUcp9ITGNBbS5yoNxoHA0PPiJlzMBz55q-Q0EktDXJmQkRJjpKQ2UhN2zTguvquHsAnHc0sl9XqbJRbIEXr05OHfrc5gtTca9JP-3ePDEayZ_1SBlGNYKt5LPCFoUahTO6O-AIy3xh8 |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=YOLOv4-5D%3A+An+Effective+and+Efficient+Object+Detector+for+Autonomous+Driving&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Cai%2C+Yingfeng&rft.au=Luan%2C+Tianyu&rft.au=Gao%2C+Hongbo&rft.au=Wang%2C+Hai&rft.date=2021&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=70&rft.spage=1&rft.epage=13&rft_id=info:doi/10.1109%2FTIM.2021.3065438&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIM_2021_3065438 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon |