Xiaofeng Lu, Xuan Wang, Zhengyang Wang, Xinhong Hei
{"title":"Multi-layer features template update object tracking algorithm based on SiamFC++","authors":"Xiaofeng Lu, Xuan Wang, Zhengyang Wang, Xinhong Hei","doi":"10.1186/s13640-023-00616-x","DOIUrl":null,"url":null,"abstract":"<p>SiamFC++ only extracts the object feature of the first frame as a tracking template, and only uses the highest level feature maps in both the classification branch and the regression branch, so that the respective characteristics of the two branches are not fully utilized. In view of this, the present paper proposes an object tracking algorithm based on SiamFC++. The algorithm uses the multi-layer features of the Siamese network to update template. First, FPN is used to extract feature maps from different layers of Backbone for classification branch and regression branch. Second, 3D convolution is used to update the tracking template of the object tracking algorithm. Next, a template update judgment condition is proposed based on mutual information. Finally, AlexNet is used as the backbone and GOT-10K as training set. Compared with SiamFC++, our algorithm obtains improved results on OTB100, VOT2016, VOT2018 and GOT-10k data sets, and the tracking process is real time.</p>","PeriodicalId":49322,"journal":{"name":"Eurasip Journal on Image and Video Processing","volume":"9 1","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Eurasip Journal on Image and Video Processing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1186/s13640-023-00616-x","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
SiamFC++ only extracts the object feature of the first frame as a tracking template, and only uses the highest level feature maps in both the classification branch and the regression branch, so that the respective characteristics of the two branches are not fully utilized. In view of this, the present paper proposes an object tracking algorithm based on SiamFC++. The algorithm uses the multi-layer features of the Siamese network to update template. First, FPN is used to extract feature maps from different layers of Backbone for classification branch and regression branch. Second, 3D convolution is used to update the tracking template of the object tracking algorithm. Next, a template update judgment condition is proposed based on mutual information. Finally, AlexNet is used as the backbone and GOT-10K as training set. Compared with SiamFC++, our algorithm obtains improved results on OTB100, VOT2016, VOT2018 and GOT-10k data sets, and the tracking process is real time.
期刊介绍:
EURASIP Journal on Image and Video Processing is intended for researchers from both academia and industry, who are active in the multidisciplinary field of image and video processing. The scope of the journal covers all theoretical and practical aspects of the domain, from basic research to development of application.