View in EDS

A dense connection based network for real-time object tracking.

Saved in:
Bibliographic Details
Title: A dense connection based network for real-time object tracking.
Authors: Lu, Yuwei1 (AUTHOR), Yuan, Yuan1 (AUTHOR) y.yuan1.ieee@gmail.com, Wang, Qi1 (AUTHOR)
Source: Neurocomputing. Oct2020, Vol. 410, p229-236. 8p.
Subjects: Object tracking (Computer vision), Computer vision, Deep learning, Feature extraction, Computer performance, Tracking algorithms
Abstract: With the development of deep learning, the performance of many computer vision tasks has been greatly improved. For visual tracking, deep learning methods mainly focus on extracting better features or designing end-to-end trackers. However, during tracking specific targets most of the existing trackers based on deep learning are less discriminative and time-consuming. In this paper, a cascade based tracking algorithm is proposed to promote the robustness of the tracker and reduce time consumption. First, we propose a novel deep network for feature extraction. Since some pruning strategies are applied, the speed of the feature extraction stage can be more than 50 frames per second. Then, a cascade tracker named DCCT is presented to improve the performance and enhance the robustness by utilizing both texture and semantic features. Similar to the cascade classifier, the proposed DCCT tracker consists of several weaker trackers. Each weak tracker rejects some false candidates of the tracked object, and the final tracking results are obtained by synthesizing these weak trackers. Intensive experiments are conducted in some public datasets and the results have demonstrated the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]
Copyright of Neurocomputing is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 146535300
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A dense connection based network for real-time object tracking.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lu%2C+Yuwei%22">Lu, Yuwei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yuan%2C+Yuan%22">Yuan, Yuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> y.yuan1.ieee@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Qi%22">Wang, Qi</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neurocomputing%22">Neurocomputing</searchLink>. Oct2020, Vol. 410, p229-236. 8p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Object+tracking+%28Computer+vision%29%22">Object tracking (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+performance%22">Computer performance</searchLink><br /><searchLink fieldCode="DE" term="%22Tracking+algorithms%22">Tracking algorithms</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: With the development of deep learning, the performance of many computer vision tasks has been greatly improved. For visual tracking, deep learning methods mainly focus on extracting better features or designing end-to-end trackers. However, during tracking specific targets most of the existing trackers based on deep learning are less discriminative and time-consuming. In this paper, a cascade based tracking algorithm is proposed to promote the robustness of the tracker and reduce time consumption. First, we propose a novel deep network for feature extraction. Since some pruning strategies are applied, the speed of the feature extraction stage can be more than 50 frames per second. Then, a cascade tracker named DCCT is presented to improve the performance and enhance the robustness by utilizing both texture and semantic features. Similar to the cascade classifier, the proposed DCCT tracker consists of several weaker trackers. Each weak tracker rejects some false candidates of the tracked object, and the final tracking results are obtained by synthesizing these weak trackers. Intensive experiments are conducted in some public datasets and the results have demonstrated the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neurocomputing is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=146535300
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.neucom.2020.06.019
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 229
    Subjects:
      – SubjectFull: Object tracking (Computer vision)
        Type: general
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Feature extraction
        Type: general
      – SubjectFull: Computer performance
        Type: general
      – SubjectFull: Tracking algorithms
        Type: general
    Titles:
      – TitleFull: A dense connection based network for real-time object tracking.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lu, Yuwei
      – PersonEntity:
          Name:
            NameFull: Yuan, Yuan
      – PersonEntity:
          Name:
            NameFull: Wang, Qi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 14
              M: 10
              Text: Oct2020
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 09252312
          Numbering:
            – Type: volume
              Value: 410
          Titles:
            – TitleFull: Neurocomputing
              Type: main
ResultId 1