Visual tracking in complex scenes: A location fusion mechanism based on the combination of multiple visual cognition flows

Simple item page
dc.contributor.authorLiu, Shuai
dc.contributor.authorHuang, Shichen
dc.contributor.authorWang, Shuai
dc.contributor.authorMuhammad, Khan
dc.contributor.authorBellavista, Paolo
dc.contributor.authorDel Ser, Javier
dc.contributor.institutionIA
dc.date.accessioned2024-09-10T11:45:01Z
dc.date.available2024-09-10T11:45:01Z
dc.date.issued2023-08
dc.descriptionPublisher Copyright: © 2023 Elsevier B.V.
dc.description.abstractIn recent years, deep learning has revolutionized computer vision and has been widely used for monitoring in diverse visual scenes. However, in terms of some aspects such as complexity and explainability, deep learning is not always preferable over traditional machine-learning methods. Traditional visual tracking approaches have shown certain advantages in terms of data collection efficiency, computing requirements, and power consumption and are generally easier to understand and explain than deep neural networks. At present, traditional feature-based techniques relying on correlation filtering (CF) have become common for understanding complex visual scenes. However, current CF algorithms use a single feature to describe the information of the target and locate it accordingly. They cannot fully express changeable target appearances in a complex scene, which can easily lead to inaccurate target locations in time-varying visual scenes. Moreover, owing to the complexity of surveillance scenes, monitoring algorithms can lose their target. The original template update strategy uses each frame with a fixed interval length as a new template, which may lead to unreliable feature extraction and low tracking accuracy. To overcome these issues, in this work, we introduce an original location fusion mechanism based on multiple visual cognition processing streams to achieve real-time and efficient visual monitoring in complex scenes. First, we propose a process for extracting multiple forms of visual cognitive information, and it is periodically used to extract multiple feature information flows of a target of interest. Subsequently, a cognitive information fusion process is employed to fuse the positioning results of different visual cognitive information flows to achieve high-quality visual monitoring and positioning. Finally, a novel feature template memory storage and retrieval strategy is adopted. When the location result is unreliable, the target is retrieved from memory to ensure robust and accurate tracking. In addition, we provide an extensive set of performance results showing that our proposed approach exhibits more robust performance at a lower computational cost compared with 36 state-of-the-art algorithms for visual tracking in complex scenes.en
dc.description.sponsorshipThis work was supported by the Natural Science Foundation of China with No. 62207012 ; Key Scientific Research Projects of the Department of Education of Hunan Province with No. 22A0049 the National Social Science Foundation of China with No. AEA200013 . J. Del Ser acknowledges funding support from the Basque Government through ELKARTEK and EMAITEK funds as well as the Consolidated Research Group MATHMODE ( IT1456–22 ).
dc.description.statusPeer reviewed
dc.format.extent16
dc.identifier.citationLiu , S , Huang , S , Wang , S , Muhammad , K , Bellavista , P & Del Ser , J 2023 , ' Visual tracking in complex scenes : A location fusion mechanism based on the combination of multiple visual cognition flows ' , Information Fusion , vol. 96 , pp. 281-296 . https://doi.org/10.1016/j.inffus.2023.02.005
dc.identifier.doi10.1016/j.inffus.2023.02.005
dc.identifier.issn1566-2535
dc.identifier.urihttps://hdl.handle.net/11556/5045
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85148445905&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofInformation Fusion
dc.relation.projectIDNational Natural Science Foundation of China, NSFC, 62207012
dc.relation.projectIDEusko Jaurlaritza, IT1456–22
dc.relation.projectIDEducation Department of Henan Province, 22A0049
dc.relation.projectIDNational Office for Philosophy and Social Sciences, NPOPSS, AEA200013
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsComplex scenes
dc.subject.keywordsFeature template memory
dc.subject.keywordsLocation fusion
dc.subject.keywordsMultiple visual cognition
dc.subject.keywordsVisual monitoring
dc.subject.keywordsSoftware
dc.subject.keywordsSignal Processing
dc.subject.keywordsInformation Systems
dc.subject.keywordsHardware and Architecture
dc.titleVisual tracking in complex scenes: A location fusion mechanism based on the combination of multiple visual cognition flowsen
dc.typejournal article
Files