基于多表观模型竞争的视觉跟踪算法
在视觉跟踪中，如何适时地更新目标模型是影响跟踪算法跟踪精度和鲁棒性的关键性因素，也是当前研究中面临的重点和难点问题。对此，提出了一种基于多表观模型竞争的模型更新策略。通过多表观模型中各子模型的贡献度大小确定竞争优势排序，当最优子模型的贡献度满足多表观模型更新阈值时，对各子模型及其对应的系数进行更新；否则，仅对部分子模型进行更新。在此基础上，以粒子滤波算法为跟踪框架，提出了基于多表现模型竞争的视觉跟踪算法。实验结果表明，所提算法能够较好地处理视觉跟踪中的模型更新问题，跟踪性能较无模型更新策略的粒子滤波算法有明显提高。...
Saved in:
| Published in | 计算机应用研究 Vol. 35; no. 2; pp. 604 - 607 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
空军工程大学信息与导航学院,西安,710077%中国人民解放军空军94402部队,济南,250002
2018
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-3695 |
| DOI | 10.3969/j.issn.1001-3695.2018.02.060 |
Cover
| Abstract | 在视觉跟踪中，如何适时地更新目标模型是影响跟踪算法跟踪精度和鲁棒性的关键性因素，也是当前研究中面临的重点和难点问题。对此，提出了一种基于多表观模型竞争的模型更新策略。通过多表观模型中各子模型的贡献度大小确定竞争优势排序，当最优子模型的贡献度满足多表观模型更新阈值时，对各子模型及其对应的系数进行更新；否则，仅对部分子模型进行更新。在此基础上，以粒子滤波算法为跟踪框架，提出了基于多表现模型竞争的视觉跟踪算法。实验结果表明，所提算法能够较好地处理视觉跟踪中的模型更新问题，跟踪性能较无模型更新策略的粒子滤波算法有明显提高。 |
|---|---|
| AbstractList | TP391.41; 在视觉跟踪中,如何适时地更新目标模型是影响跟踪算法跟踪精度和鲁棒性的关键性因素,也是当前研究中面临的重点和难点问题.对此,提出了一种基于多表观模型竞争的模型更新策略.通过多表观模型中各子模型的贡献度大小确定竞争优势排序,当最优子模型的贡献度满足多表观模型更新阈值时,对各子模型及其对应的系数进行更新;否则,仅对部分子模型进行更新.在此基础上,以粒子滤波算法为跟踪框架,提出了基于多表观模型竞争的视觉跟踪算法.实验结果表明,所提算法能够较好地处理视觉跟踪中的模型更新问题,跟踪性能较无模型更新策略的粒子滤波算法有明显提高. 在视觉跟踪中，如何适时地更新目标模型是影响跟踪算法跟踪精度和鲁棒性的关键性因素，也是当前研究中面临的重点和难点问题。对此，提出了一种基于多表观模型竞争的模型更新策略。通过多表观模型中各子模型的贡献度大小确定竞争优势排序，当最优子模型的贡献度满足多表观模型更新阈值时，对各子模型及其对应的系数进行更新；否则，仅对部分子模型进行更新。在此基础上，以粒子滤波算法为跟踪框架，提出了基于多表现模型竞争的视觉跟踪算法。实验结果表明，所提算法能够较好地处理视觉跟踪中的模型更新问题，跟踪性能较无模型更新策略的粒子滤波算法有明显提高。 |
| Abstract_FL | During the visual tracking,how to update the target model timely is the key factor that affects the tracking performance and robustness.This problem is also considered to be the important and hard issue of the visual tracking.To this point,this paper proposed a model update strategy based on the competition of multiple appearance models.It assigned the competition superiority order according to the contribution of each sub model.When the contribution of the best sub model subjects to model update threshold,it updated all the sub models and the corresponding weights.Otherwise,it partially updated the multiple appearance models.Based on this,it proposed a visual tracking algorithm based on multiple appearance models under the framework of particle filter.The experimental results indicate that the proposed algorithm can well cope with the model update problem,which obviously improves the tracking performance compared with the particle filter tracking without model update. |
| Author | 余旺盛;侯志强;李建朋 |
| AuthorAffiliation | 空军工程大学信息与导航学院,西安710077;中国人民解放军空军94402部队,济南250002 |
| AuthorAffiliation_xml | – name: 空军工程大学信息与导航学院,西安,710077%中国人民解放军空军94402部队,济南,250002 |
| Author_FL | Li Jianpeng Yu Wangsheng Hou Zhiqiang |
| Author_FL_xml | – sequence: 1 fullname: Yu Wangsheng – sequence: 2 fullname: Hou Zhiqiang – sequence: 3 fullname: Li Jianpeng |
| Author_xml | – sequence: 1 fullname: 余旺盛;侯志强;李建朋 |
| BookMark | eNo9j0tLw0AUhWdRwbb6J8SFm8Q7j0wySym-oOCm-zB5TG3QqTaIZCsiFMGdCF20FIQUBTculPyepsnPcKTi3Ry45-McTgs19FDHCO1isKngYj-xB2mqbQyALcqFYxPAng3EBg4N1Pz_b6JWmiYAjGABTQTlrFgWT-XrpJ4v6vxutZiX08fqfbosxtXkvs4f6nxcf83q77fq42X1-byFNpS8SOPtP22j3tFhr3Nidc-OTzsHXSvkAJakPMJBQCMvYDKMzTGmQldGjBAXew5mUipMnUBSqYTi1DiRy0kUC2VE0TbaW8feSq2k7vvJ8GakTaGfpEmWZcnvPCBmnEF31mh4PtT964GBr0aDSznKfO4yRrjjCfoDO_hnGQ |
| ClassificationCodes | TP391.41 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3969/j.issn.1001-3695.2018.02.060 |
| DatabaseName | 中文科技期刊数据库 中文科技期刊数据库-CALIS站点 中文科技期刊数据库-7.0平台 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| DocumentTitleAlternate | Visual tracking algorithm based on competition of multiple appearance models |
| DocumentTitle_FL | Visual tracking algorithm based on competition of multiple appearance models |
| EndPage | 607 |
| ExternalDocumentID | jsjyyyj201802060 674426589 |
| GrantInformation_xml | – fundername: 国家自然科学基金资助项目; 陕西省自然科学基础研究计划项目 funderid: (61703423,61473309); (2016JM6050) |
| GroupedDBID | -0Y 2B. 2C0 2RA 5XA 5XJ 92H 92I 92L ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CQIGP CUBFJ CW9 TCJ TGT U1G U5S W92 ~WA 4A8 93N ABJNI PSX |
| ID | FETCH-LOGICAL-c600-a36d1bb3d8b4aceeee44fc7ad422718514aaf135ba3af9f63ad4d762de9f762f3 |
| ISSN | 1001-3695 |
| IngestDate | Thu May 29 03:54:52 EDT 2025 Wed Feb 14 10:09:56 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 2 |
| Keywords | 多表观模型 model update multiple appearance models 模型更新 visual tracking 视觉跟踪 粒子滤波 particle filter |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c600-a36d1bb3d8b4aceeee44fc7ad422718514aaf135ba3af9f63ad4d762de9f762f3 |
| Notes | 51-1196/TP During the visual tracking, how to update the target model timely is the key factor that affects the tracking perfor- mance and robustness. This problem is also considered to be the important and hard issue of the visual tracking. To this point, this paper proposed a model update strategy based on the competition of multiple appearance models. It assigned the competition superiority order according to the contribution of each sub model. When the contribution of the best sub model subjects to model update threshold, it updated all the sub models and the corresponding weights. Otherwise, it partially updated the multiple appearance models. Based on this, it proposed a visual tracking algorithm based on multiple appearance models under the framework of particle filter. The experimental results indicate that the proposed algorithm can well cope with the model update problem, which obviously improves the tracking performance compared with the particle filter tracking without model update. Yu Wangsheng1, H |
| PageCount | 4 |
| ParticipantIDs | wanfang_journals_jsjyyyj201802060 chongqing_primary_674426589 |
| PublicationCentury | 2000 |
| PublicationDate | 2018 |
| PublicationDateYYYYMMDD | 2018-01-01 |
| PublicationDate_xml | – year: 2018 text: 2018 |
| PublicationDecade | 2010 |
| PublicationTitle | 计算机应用研究 |
| PublicationTitleAlternate | Application Research of Computers |
| PublicationTitle_FL | Application Research of Computers |
| PublicationYear | 2018 |
| Publisher | 空军工程大学信息与导航学院,西安,710077%中国人民解放军空军94402部队,济南,250002 |
| Publisher_xml | – name: 空军工程大学信息与导航学院,西安,710077%中国人民解放军空军94402部队,济南,250002 |
| SSID | ssj0042190 ssib001102940 ssib002263599 ssib023646305 ssib051375744 ssib025702191 |
| Score | 2.130262 |
| Snippet | ... TP391.41;... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 604 |
| SubjectTerms | 多表观模型 模型更新 粒子滤波 视觉跟踪 |
| Title | 基于多表观模型竞争的视觉跟踪算法 |
| URI | http://lib.cqvip.com/qk/93231X/201802/674426589.html https://d.wanfangdata.com.cn/periodical/jsjyyyj201802060 |
| Volume | 35 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NaxNBFB9iCuLFb7FWJULnuDXZmZ2dOe40G4qgpwi9hdmvlhxStekhPYoIRfAmQg8tBSFFwUsPSv6eptk_wzezk-1apKgQJi9v9s17u28y7zfL7nsILUdxTOOmxx3YKqcOJdBEXqycJItoK6Isapo8Bc9fsLWX9Nm6t16rnVSeWtoZRivx7h_fK_kfrwIP_Krfkv0Hz5aDAgNo8C-04GFo_8rHOPSw6GAZ4JDqloeaE1AsgMNx0MIBN4SPuYtDpn8CU0uFmEsc-jiQmrbiQnNAltO5FJsTQhPS1-o0AczAiIdY-HpkSXBRxnKOdI1gaNRVDhOrxlpPt4IaddQYCcc0LScQWJb3C41pbSyEkfaNNAhJ_SHS9IKSjhmyY5QAYZToXhBp26sipZE1JnBZvdnx28qsn_0izJ6KXbqLTCd2irqVdZgVNY1tSGdFYd2L0YIIJky00ApWSgX6eT9uErkWlQ4u5ONmPgVU43FxBS24PsCbOloIZFt2zlEogLZqVkJXJ_w53_XplP2ssszqOoIQN8pl1msR3zNFCQpAQaGzSKphDbyKlq31Ty-zXWcL2dwabLwGDGReSRtkarBRQU_dm-i63fY0gmIO30K13c3b6Ma8pEjDRpg7qDk9nJxOPk6_7OdHx_n47dnx0fTgw-zbwelkb7b_Lh-_z8d7-Y_D_OfX2ffPZyef7qJuJ-yurjm2qIcTA7Z2FGFJK4pIwiOqAKClKaVZ7KuEui7AJIDvSmUt4kWKqExkjEBPAgE7SUUGXxm5h-qDrUF6HzUSlpAmV77wU4hElIosTmPl-glVVMSKLaKl8vx7r4rcLb3Se4voib0iPfuP3u71t_uj0aivryHsoljzwaUjLKFr-sjiftxDVB--2UkfAUIdRo_tjPgF-c5vkA |
| linkProvider | EBSCOhost |
| 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=%E5%9F%BA%E4%BA%8E%E5%A4%9A%E8%A1%A8%E8%A7%82%E6%A8%A1%E5%9E%8B%E7%AB%9E%E4%BA%89%E7%9A%84%E8%A7%86%E8%A7%89%E8%B7%9F%E8%B8%AA%E7%AE%97%E6%B3%95&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%BA%94%E7%94%A8%E7%A0%94%E7%A9%B6&rft.au=%E4%BD%99%E6%97%BA%E7%9B%9B%3B%E4%BE%AF%E5%BF%97%E5%BC%BA%3B%E6%9D%8E%E5%BB%BA%E6%9C%8B&rft.date=2018&rft.issn=1001-3695&rft.volume=35&rft.issue=2&rft.spage=604&rft.epage=607&rft_id=info:doi/10.3969%2Fj.issn.1001-3695.2018.02.060&rft.externalDocID=674426589 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F93231X%2F93231X.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjyyyj%2Fjsjyyyj.jpg |