{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:03:16Z","timestamp":1785211396692,"version":"3.55.0"},"reference-count":56,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2018,11,19]],"date-time":"2018-11-19T00:00:00Z","timestamp":1542585600000},"content-version":"vor","delay-in-days":322,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20171267"],"award-info":[{"award-number":["BK20171267"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["2016XYDXXJS-012"],"award-info":[{"award-number":["2016XYDXXJS-012"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61332017"],"award-info":[{"award-number":["61332017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002949","name":"Government of Jiangsu Province","doi-asserted-by":"publisher","award":["BRA2018333"],"award-info":[{"award-number":["BRA2018333"]}],"id":[{"id":"10.13039\/501100002949","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010023","name":"Natural Science Research of Jiangsu Higher Education Institutions of China","doi-asserted-by":"publisher","award":["18KJA520002"],"award-info":[{"award-number":["18KJA520002"]}],"id":[{"id":"10.13039\/501100010023","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:p>Multiple\u2010object tracking is a challenging issue in the computer vision community. In this paper, we propose a multiobject tracking algorithm in videos based on long short\u2010term memory (LSTM) and deep reinforcement learning. Firstly, the multiple objects are detected by the object detector YOLO V2. Secondly, the problem of single\u2010object tracking is considered as a Markov decision process (MDP) since this setting provides a formal strategy to model an agent that makes sequence decisions. The single\u2010object tracker is composed of a network that includes a CNN followed by an LSTM unit. Each tracker, regarded as an agent, is trained by utilizing deep reinforcement learning. Finally, we conduct a data association using LSTM for each frame between the results of the object detector and the results of single\u2010object trackers. From the experimental results, we can see that our tracker achieves better performance than the other state\u2010of\u2010the\u2010art methods. Multiple targets can be steadily tracked even when frequent occlusions, similar appearances, and scale changes happened.<\/jats:p>","DOI":"10.1155\/2018\/4695890","type":"journal-article","created":{"date-parts":[[2018,11,19]],"date-time":"2018-11-19T23:31:50Z","timestamp":1542670310000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning"],"prefix":"10.1155","volume":"2018","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0766-5841","authenticated-orcid":false,"given":"Ming-xin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6504-0025","authenticated-orcid":false,"given":"Chao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0717-5850","authenticated-orcid":false,"given":"Zhi-geng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7387-0718","authenticated-orcid":false,"given":"Lan-fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2112-7428","authenticated-orcid":false,"given":"Xing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2018,11,19]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2533391"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/s17010121"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.07.003"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.210"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.103"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"BaeS. H.andYoonK. J. Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2014 Columbus OH USA 1218\u20131225 https:\/\/doi.org\/10.1109\/CVPR.2014.159 2-s2.0-84911445394.","DOI":"10.1109\/CVPR.2014.159"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"AndriyenkoA.andSchindlerK. Multi-target tracking by continuous energy minimization 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2011 Providence RI USA https:\/\/doi.org\/10.1109\/CVPR.2011.5995311 2-s2.0-80052910259.","DOI":"10.1109\/CVPR.2011.5995311"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"GirshickR. Fast R-CNN Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) December 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_9_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"RedmonJ. DivvalaS. GirshickR. andFarhadiA. You only look once: unified real-time object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2016 Las Vegas NV USA 779\u2013788 https:\/\/doi.org\/10.1109\/cvpr.2016.91.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"BrendelW. AmerM. andTodorovicS. Multiobject tracking as maximum weight independent set Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2011 Providence RI USA 1273\u20131280 https:\/\/doi.org\/10.1109\/cvpr.2011.5995395 2-s2.0-80052897117.","DOI":"10.1109\/CVPR.2011.5995395"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"HenriquesJ. F. CaseiroR. andBatistaJ. Globally optimal solution to multi-object tracking with merged measurements Proceedings of the IEEE Conference on Computer Vision (ICCV) November 2011 Barcelona Spain 2470\u20132477 https:\/\/doi.org\/10.1109\/ICCV.2011.6126532 2-s2.0-84856685291.","DOI":"10.1109\/ICCV.2011.6126532"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"ButtA. A.andCollinsR. T. Multi-target tracking by Lagrangian relaxation to min-cost network flow Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2013 Portland OR USA 1846\u20131853 https:\/\/doi.org\/10.1109\/CVPR.2013.241 2-s2.0-84887397689.","DOI":"10.1109\/CVPR.2013.241"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"WuZ. ThangaliA. SclaroffS. andBetkeM. Coupling detection and data association for multiple object tracking Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2012 Providence RI USA 1948\u20131955 https:\/\/doi.org\/10.1109\/CVPR.2012.6247896 2-s2.0-84866692788.","DOI":"10.1109\/CVPR.2012.6247896"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691769"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.3390\/s17030617"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.232"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"DehghanA. TianY. TorrP. H. S. andShahM. Target identity-aware network flow for online multiple target tracking Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2015 Boston MA USA 1146\u20131154 https:\/\/doi.org\/10.1109\/cvpr.2015.7298718 2-s2.0-84956633470.","DOI":"10.1109\/CVPR.2015.7298718"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2509979"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2570553"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682196"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"DuY. WangW. andWangL. Hierarchical recurrent neural network for skeleton based action recognition 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2015 Boston MA USA 1110\u20131118 https:\/\/doi.org\/10.1109\/CVPR.2015.7298714 2-s2.0-84959217041.","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"CaoC. LiuX. YangY. YuY. WangJ. WangZ. HuangY. WangL. HuangC. XuW. RamananD. andHuangT. S. Look and think twice: capturing top-down visual attention with feedback convolutional neural networks 2015 IEEE International Conference on Computer Vision (ICCV) December 2016 Santiago Chile 2956\u20132964 https:\/\/doi.org\/10.1109\/ICCV.2015.338 2-s2.0-84973861662.","DOI":"10.1109\/ICCV.2015.338"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"AlahiA. GoelK. RamanathanV. RobicquetA. Fei-FeiL. andSavareseS. Social LSTM: human trajectory prediction in crowded spaces 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2016 Las Vegas NV USA 961\u2013971 https:\/\/doi.org\/10.1109\/CVPR.2016.110.","DOI":"10.1109\/CVPR.2016.110"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"NavneetD.andTriggsB. Histograms of oriented gradients for human detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2005 San Diego CA USA https:\/\/doi.org\/10.1109\/CVPR.2005.177 2-s2.0-33645146449.","DOI":"10.1109\/CVPR.2005.177"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"WangX. Y. HanT. X. andYanS. C. An HOG-LBP human detector with partial occlusion handling Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2009 Kyoto Japan https:\/\/doi.org\/10.1109\/ICCV.2009.5459207.","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"e_1_2_9_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"LuJ. W. WangG. DengW. H. MoulinP. andZhouJ. Multi-manifold deep metric learning for image set classification Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2015 Boston MA USA https:\/\/doi.org\/10.1109\/CVPR.2015.7298717 2-s2.0-84959212880.","DOI":"10.1109\/CVPR.2015.7298717"},{"key":"e_1_2_9_30_2","unstructured":"DonahueJ. JiaY. VinyalsO. HoffmanJ. ZhangN. TzengE. andDarrellT. DeCAF: a deep convolutional activation feature for generic visual recognition Proceedings of International Conference on Machine Learning June 2014 Bejing China 647\u2013655."},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2510583"},{"key":"e_1_2_9_32_2","unstructured":"WangN. Y.andYeungD. Y. Learning a deep compact image representation for visual tracking Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS) December 2013 South Lake Tahoe NV USA."},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2403231"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2066286"},{"key":"e_1_2_9_35_2","unstructured":"MnihV. KavukcuogluK. SilverD. GravesA. MilanMiloglouI. WierstraD. andRiedmillerM. Playing Atari with deep reinforcement learning 2013 http:\/\/arxiv.org\/abs\/1312.5602."},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_2_9_37_2","doi-asserted-by":"crossref","unstructured":"JayaramanD.andGraumanK. Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion 2016 http:\/\/arxiv.org\/abs\/1605.00164.","DOI":"10.1007\/978-3-319-46454-1_30"},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"CaicedoJ. C.andLazebnikS. Active object localization with deep reinforcement learning 2015 IEEE International Conference on Computer Vision (ICCV) December 2015 Santiago Chile 2488\u20132496 https:\/\/doi.org\/10.1109\/iccv.2015.286 2-s2.0-84973897631.","DOI":"10.1109\/ICCV.2015.286"},{"key":"e_1_2_9_39_2","unstructured":"ZhangD. MaeiH. WangX. andWangY.-F. Deep reinforcement learning for visual object tracking in videos 2017 http:\/\/arxiv.org\/abs\/1701.08936."},{"key":"e_1_2_9_40_2","unstructured":"JieZ. LiangX. FengJ. JinX. LuW. F. andYanS. Tree-structured reinforcement learning for sequential object localization Conference on Neural Information Processing Systems 2016 Barcelona Spain 127\u2013135."},{"key":"e_1_2_9_41_2","unstructured":"LuoW. SunP. MuY. andLiuW. End-to-end active object tracking via reinforcement learning 2017 http:\/\/arxiv.org\/abs\/1705.10561."},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"YunS. ChoiJ. YooY. YunK. andChoiJ. Y. Action-decision networks for visual tracking with deep reinforcement learning 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 2017 Honolulu HI USA https:\/\/doi.org\/10.1109\/CVPR.2017.148 2-s2.0-85040308344.","DOI":"10.1109\/CVPR.2017.148"},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_9_44_2","unstructured":"GravesA. Generating sequences with recurrent neural networks http:\/\/arxiv.org\/abs\/1308.0850."},{"key":"e_1_2_9_45_2","unstructured":"WangZ. FreitasN. andLanctotM. Dueling network architectures for deep reinforcement learning 2015 http:\/\/arxiv.org\/abs\/1511.06581."},{"key":"e_1_2_9_46_2","unstructured":"Van HasseltH. GuezA. andSilverD. Deep reinforcement learning with double Q-learning http:\/\/arxiv.org\/abs\/1509.06461."},{"key":"e_1_2_9_47_2","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.3698"},{"key":"e_1_2_9_48_2","doi-asserted-by":"crossref","unstructured":"RedmonJ.andFarhadiA. YOLO9000: better faster stronger 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 2016 Honolulu HI USA https:\/\/doi.org\/10.1109\/cvpr.2017.690 2-s2.0-85041900441.","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_9_49_2","unstructured":"MilanA. RezatofighiS. H. DickA. ReidI. D. andSchindlerK. Online multi-target tracking using recurrent neural networks http:\/\/arxiv.org\/abs\/1604.03635."},{"key":"e_1_2_9_50_2","unstructured":"Leal-Taix\u00e9L. MilanA. ReidI. RothS. andSchindlerK. MOTChallenge 2015: towards a benchmark for multi-target tracking http:\/\/arxiv.org\/abs\/1504.01942."},{"key":"e_1_2_9_51_2","doi-asserted-by":"crossref","unstructured":"TaylorG. R. ChosakA. J. andBrewerP. C. OVVV: using virtual worlds to design and evaluate surveillance systems IEEE Conference on Computer Vision and Pattern Recognition June 2007 Minneapolis MN USA 1\u20138 https:\/\/doi.org\/10.1109\/CVPR.2007.383518 2-s2.0-34948814551.","DOI":"10.1109\/CVPR.2007.383518"},{"key":"e_1_2_9_52_2","doi-asserted-by":"crossref","unstructured":"GaidonA. WangQ. CabonY. andVigE. VirtualWorlds as proxy for multi-object tracking analysis 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2016 Las Vegas NV USA 4340\u20134349 https:\/\/doi.org\/10.1109\/CVPR.2016.470.","DOI":"10.1109\/CVPR.2016.470"},{"key":"e_1_2_9_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0960-z"},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"XiangY. AlahiA. andSavareseS. Learning to track: online multi-object tracking by decision making 2015 IEEE International Conference on Computer Vision (ICCV) December 2015 Santiago Chile 4705\u20134713 https:\/\/doi.org\/10.1109\/ICCV.2015.534 2-s2.0-84973864179.","DOI":"10.1109\/ICCV.2015.534"},{"key":"e_1_2_9_55_2","doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9L. Canton-FerrerC. andSchindlerK. Learning by tracking: Siamese CNN for robust target association 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2016 Las Vegas NV USA https:\/\/doi.org\/10.1109\/cvprw.2016.59 2-s2.0-85010189124.","DOI":"10.1109\/CVPRW.2016.59"},{"key":"e_1_2_9_56_2","doi-asserted-by":"crossref","unstructured":"RezatofighiS. H. MilanA. ZhangZ. ShiQ. DickA. andReidI. Joint probabilistic data association revisited IEEE International Conference on Computer Vision December 2015 Santiago Chile 3047\u20133055 https:\/\/doi.org\/10.1109\/ICCV.2015.349 2-s2.0-84973879702.","DOI":"10.1109\/ICCV.2015.349"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2018\/4695890.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2018\/4695890.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2018\/4695890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T22:32:11Z","timestamp":1723156331000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2018\/4695890"}},"subtitle":[],"editor":[{"given":"Michele","family":"Scarpiniti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["10.1155\/2018\/4695890"],"URL":"https:\/\/doi.org\/10.1155\/2018\/4695890","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"value":"1076-2787","type":"print"},{"value":"1099-0526","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]},"assertion":[{"value":"2017-09-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-03-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-11-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4695890"}}