{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T02:39:26Z","timestamp":1747190366296,"version":"3.40.5"},"reference-count":82,"publisher":"Wiley","license":[{"start":{"date-parts":[[2020,12,23]],"date-time":"2020-12-23T00:00:00Z","timestamp":1608681600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2020,12,23]]},"abstract":"<jats:p>With the development of deep learning, trackers based on convolutional neural networks (CNNs) have made significant achievements in visual tracking over the years. The fully connected Siamese network (SiamFC) is a typical representation of those trackers. SiamFC designs a two-branch architecture of a CNN and models\u2019 visual tracking as a general similarity-learning problem. However, the feature maps it uses for visual tracking are only from the last layer of the CNN. Those features contain high-level semantic information but lack sufficiently detailed texture information. This means that the SiamFC tracker tends to drift when there are other same-category objects or when the contrast between the target and the background is very low. Focusing on addressing this problem, we design a novel tracking algorithm that combines a correlation filter tracker and the SiamFC tracker into one framework. In this framework, the correlation filter tracker can use the Histograms of Oriented Gradients (HOG) and color name (CN) features to guide the SiamFC tracker. This framework also contains an evaluation criterion which we design to evaluate the tracking result of the two trackers. If this criterion finds the SiamFC tracker fails in some cases, our framework will use the tracking result from the correlation filter tracker to correct the SiamFC. In this way, the defects of SiamFC\u2019s high-level semantic features are remedied by the HOG and CN features. So, our algorithm provides a framework which combines two trackers together and makes them complement each other in visual tracking. And to the best of our knowledge, our algorithm is also the first one which designs an evaluation criterion using correlation filter and zero padding to evaluate the tracking result. Comprehensive experiments are conducted on the Online Tracking Benchmark (OTB), Temple Color (TC128), Benchmark for UAV Tracking (UAV-123), and Visual Object Tracking (VOT) Benchmark. The results show that our algorithm achieves quite a competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.<\/jats:p>","DOI":"10.1155\/2020\/6681391","type":"journal-article","created":{"date-parts":[[2020,12,25]],"date-time":"2020-12-25T02:21:05Z","timestamp":1608862865000},"page":"1-19","source":"Crossref","is-referenced-by-count":2,"title":["MFCFSiam: A Correlation-Filter-Guided Siamese Network with Multifeature for Visual Tracking"],"prefix":"10.1155","volume":"2020","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9094-5918","authenticated-orcid":true,"given":"Chenpu","family":"Li","sequence":"first","affiliation":[{"name":"College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5671-6118","authenticated-orcid":true,"given":"Qianjian","family":"Xing","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7283-2637","authenticated-orcid":true,"given":"Zhenguo","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Zang","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.07.005"},{"issue":"1","key":"2","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/MRA.2005.1411416","article-title":"Tracking all traffic: computer vision algorithms for monitoring vehicles, individuals, and crowds","volume":"12","author":"B. Maurin","year":"2005","journal-title":"IEEE robotics & automation magazine"},{"volume-title":"RF-Based Micro-Motion Tracking for Gesture Tracking and Recognition","year":"2019","author":"J. Lien","key":"3"},{"first-page":"3101","article-title":"Understanding and diagnosing visual tracking systems","author":"N. Wang","key":"4"},{"issue":"4","key":"5","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1109\/TMM.2016.2631884","article-title":"Occlusion-aware real-time object tracking","volume":"19","author":"X. Dong","year":"2016","journal-title":"IEEE Transactions on Multimedia"},{"issue":"1","key":"6","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s11390-017-1764-5","article-title":"Robust visual tracking based on convolutional features with illumination and occlusion handing","volume":"33","author":"K. Li","year":"2018","journal-title":"Journal of Computer Science and Technology"},{"first-page":"389","article-title":"Robust tracking in low light and sudden illumination changes","author":"H. Alismail","key":"7"},{"first-page":"4429","article-title":"Illumination insensitive efficient second-order minimization for planar object tracking","author":"L. Chen","key":"8"},{"issue":"1","key":"9","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s11036-018-1134-8","article-title":"A robust parallel object tracking method for illumination variations","volume":"24","author":"S. Liu","year":"2019","journal-title":"Mobile Networks and Applications"},{"first-page":"3074","article-title":"Hierarchical convolutional features for visual tracking","author":"C. Ma","key":"10"},{"issue":"1-3","key":"11","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s11263-007-0075-7","article-title":"Incremental learning for robust visual tracking","volume":"77","author":"D. A. Ross","year":"2008","journal-title":"International journal of computer vision"},{"first-page":"548","article-title":"End-to-end flow correlation tracking with spatial-temporal attention","author":"Z. Zhu","key":"12"},{"first-page":"2411","article-title":"Online object tracking: a benchmark","author":"Y. Wu","key":"13"},{"key":"14","first-page":"188","article-title":"MEEM: robust tracking via multiple experts using entropy minimization","volume-title":"European conference on computer vision","author":"J. Zhang","year":"2014"},{"issue":"3","key":"15","first-page":"265","article-title":"Object tracking with multi-view support vector machines","volume":"17","author":"S. Zhang","year":"2015","journal-title":"IEEE Transactions on Multimedia"},{"issue":"8","key":"16","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.1109\/TPAMI.2010.226","article-title":"Robust object tracking with online multiple instance learning","volume":"33","author":"B. Babenko","year":"2010","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"1","key":"17","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1049\/el.2016.3011","article-title":"Robust visual tracking via self-similarity learning","volume":"53","author":"H. Song","year":"2016","journal-title":"Electronics Letters"},{"issue":"10","key":"18","doi-asserted-by":"crossref","first-page":"1818","DOI":"10.1109\/TMM.2015.2463221","article-title":"Visual tracking using strong classifier and structural local sparse descriptors","volume":"17","author":"B. Ma","year":"2015","journal-title":"IEEE Transactions on Multimedia"},{"issue":"3","key":"19","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1016\/j.patcog.2013.07.010","article-title":"Discriminative subspace learning with sparse representation view-based model for robust visual tracking","volume":"47","author":"Y. Xie","year":"2014","journal-title":"Pattern Recognition"},{"issue":"12","key":"20","doi-asserted-by":"crossref","first-page":"4686","DOI":"10.1109\/TIP.2015.2462076","article-title":"Robust visual tracking via sparsity-induced subspace learning","volume":"24","author":"Y. Sui","year":"2015","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"21","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1109\/TCSVT.2013.2278199","article-title":"Visual tracking via online nonnegative matrix factorization","volume":"24","author":"Y. Wu","year":"2013","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"2","key":"22","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s11263-014-0738-0","article-title":"Robust visual tracking via consistent low-rank sparse learning","volume":"111","author":"T. Zhang","year":"2015","journal-title":"International Journal of Computer Vision"},{"issue":"11","key":"23","doi-asserted-by":"crossref","first-page":"14277","DOI":"10.1007\/s11042-018-6800-0","article-title":"Particle filter re-detection for visual tracking via correlation filters","volume":"78","author":"D. Yuan","year":"2019","journal-title":"Multimedia Tools and Applications"},{"issue":"9","key":"24","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1109\/LSP.2015.2404856","article-title":"Visual tracking via constrained incremental non-negative matrix factorization","volume":"22","author":"H. Zhang","year":"2015","journal-title":"IEEE signal processing letters"},{"first-page":"1090","article-title":"Adaptive color attributes for real-time visual tracking","author":"M. Danelljan","key":"25"},{"issue":"9","key":"26","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object detection with discriminatively trained part-based models","volume":"32","author":"P. F. Felzenszwalb","year":"2009","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"27","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in neural information processing systems","author":"A. Krizhevsky","year":"2012"},{"key":"28","first-page":"443","article-title":"Is faster R-CNN doing well for pedestrian detection?","volume-title":"European conference on computer vision","author":"L. Zhang","year":"2016"},{"first-page":"650","article-title":"Face detection with the faster R-CNN","author":"H. Jiang","key":"29"},{"issue":"4","key":"30","first-page":"985","article-title":"Scale-aware fast R-CNN for pedestrian detection","volume":"20","author":"J. Li","year":"2017","journal-title":"IEEE transactions on Multimedia"},{"key":"31","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.cviu.2017.04.002","article-title":"Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound","volume":"164","author":"F. Milletari","year":"2017","journal-title":"Computer Vision and Image Understanding"},{"first-page":"6154","article-title":"Cascade r-cnn: delving into high quality object detection","author":"Z. Cai","key":"32"},{"key":"33","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1016\/j.neucom.2017.08.062","article-title":"A hybrid deep learning CNN\u2013ELM for age and gender classification","volume":"275","author":"M. Duan","year":"2018","journal-title":"Neurocomputing"},{"issue":"4","key":"34","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1109\/TIP.2015.2510583","article-title":"Deeptrack: learning discriminative feature representations online for robust visual tracking","volume":"25","author":"H. Li","year":"2015","journal-title":"IEEE Transactions on Image Processing"},{"first-page":"4293","article-title":"Learning multi-domain convolutional neural networks for visual tracking","author":"H. Nam","key":"35"},{"article-title":"Modeling and propagating cnns in a tree structure for visual tracking","year":"2016","author":"H. Nam","key":"36"},{"key":"37","first-page":"597","article-title":"Online tracking by learning discriminative saliency map with convolutional neural network","volume-title":"International conference on machine learning","author":"S. Hong","year":"2015"},{"key":"38","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","volume-title":"European conference on computer vision","author":"L. Bertinetto","year":"2016"},{"issue":"4","key":"39","doi-asserted-by":"crossref","first-page":"2005","DOI":"10.1109\/TIP.2017.2669880","article-title":"Dual deep network for visual tracking","volume":"26","author":"Z. Chi","year":"2017","journal-title":"IEEE Transactions on Image Processing"},{"first-page":"2544","article-title":"Visual object tracking using adaptive correlation filters","author":"D. S. Bolme","key":"40"},{"key":"41","first-page":"702","article-title":"Exploiting the circulant structure of tracking-by-detection with kernels","volume-title":"European conference on computer vision","author":"J. F. Henriques","year":"2012"},{"issue":"3","key":"42","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","article-title":"High-speed tracking with kernelized correlation filters","volume":"37","author":"J. F. Henriques","year":"2014","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"first-page":"5388","article-title":"Long-term correlation tracking","author":"C. Ma","key":"43"},{"article-title":"Accurate scale estimation for robust visual tracking","author":"M. Danelljan","key":"44","doi-asserted-by":"crossref","DOI":"10.5244\/C.28.65"},{"key":"45","article-title":"Robust visual tracking with correlation filters and metric learning","volume-title":"Knowledge-Based Systems","author":"D. Yuan","year":"2020"},{"first-page":"7950","article-title":"Joint group feature selection and discriminative filter learning for robust visual object tracking","author":"T. Xu","key":"46"},{"key":"47","article-title":"TRBACF: learning temporal regularized correlation filters for high performance online visual object tracking","volume":"72, article 102882","author":"D. Yuan","year":"2020","journal-title":"Journal of Visual Communication and Image Representation"},{"first-page":"2891","article-title":"Learning aberrance repressed correlation filters for real-time uav tracking","author":"Z. Huang","key":"48"},{"key":"49","article-title":"Learning target-focusing convolutional regression model for visual object tracking","volume-title":"Knowledge-Based Systems","author":"D. Yuan","year":"2020"},{"first-page":"4303","article-title":"Hedged deep tracking","author":"Y. Qi","key":"50"},{"first-page":"4310","article-title":"Learning spatially regularized correlation filters for visual tracking","author":"M. Danelljan","key":"51"},{"first-page":"2805","article-title":"End-to-end representation learning for correlation filter based tracking","author":"J. Valmadre","key":"52"},{"first-page":"1763","article-title":"Learning dynamic siamese network for visual object tracking","author":"Q. Guo","key":"53"},{"first-page":"8971","article-title":"High performance visual tracking with siamese region proposal network","author":"B. Li","key":"54"},{"first-page":"7133","article-title":"D3S-A discriminative single shot segmentation tracker","author":"A. Lukezic","key":"55"},{"first-page":"6728","article-title":"Deformable Siamese attention networks for visual object tracking","author":"Y. Yu","key":"56"},{"first-page":"7952","article-title":"Siamese cascaded region proposal networks for real-time visual tracking","author":"H. Fan","key":"57"},{"first-page":"6578","article-title":"Siam r-cnn: visual tracking by re-detection","author":"P. Voigtlaender","key":"58"},{"key":"59","first-page":"91","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","volume-title":"Advances in Neural Information Processing Systems","author":"S. Ren","year":"2015"},{"issue":"2","key":"60","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/TCSVT.2019.2892759","article-title":"When correlation filters meet siamese networks for real-time complementary tracking","volume":"30","author":"D. Li","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"12","key":"61","doi-asserted-by":"crossref","first-page":"5630","DOI":"10.1109\/TIP.2015.2482905","article-title":"Encoding color information for visual tracking: algorithms and benchmark","volume":"24","author":"P. Liang","year":"2015","journal-title":"IEEE Transactions on Image Processing"},{"first-page":"459","article-title":"Triplet loss in siamese network for object tracking","author":"X. Dong","key":"62"},{"first-page":"479","article-title":"Context-aware deep feature compression for high-speed visual tracking","author":"J. Choi","key":"63"},{"first-page":"4591","article-title":"Deeper and wider siamese networks for real-time visual tracking","author":"Z. Zhang","key":"64"},{"first-page":"1401","article-title":"Staple: complementary learners for real-time tracking","author":"L. Bertinetto","key":"65"},{"first-page":"1135","article-title":"Learning background-aware correlation filters for visual tracking","author":"H. Kiani Galoogahi","key":"66"},{"article-title":"Dcfnet: discriminant correlation filters network for visual tracking","year":"2017","author":"Q. Wang","key":"67"},{"first-page":"4021","article-title":"Large margin object tracking with circulant feature maps","author":"M. Wang","key":"68"},{"key":"69","first-page":"254","article-title":"A scale adaptive kernel correlation filter tracker with feature integration","volume-title":"European conference on computer vision","author":"Y. Li","year":"2014"},{"issue":"4","key":"70","first-page":"1779","article-title":"Robust visual tracking via convolutional networks without training","volume":"25","author":"K. Zhang","year":"2016","journal-title":"IEEE Transactions on Image Processing"},{"first-page":"1430","article-title":"Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking","author":"M. Danelljan","key":"71"},{"first-page":"4335","article-title":"Multi-task correlation particle filter for robust object tracking","author":"T. Zhang","key":"72"},{"first-page":"58","article-title":"Convolutional features for correlation filter based visual tracking","author":"M. Danelljan","key":"73"},{"article-title":"A benchmark and simulator for UAV tracking","author":"M. Mueller","key":"74","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46448-0_27"},{"first-page":"6638","article-title":"Eco: efficient convolution operators for tracking","author":"M. Danelljan","key":"75"},{"first-page":"4282","article-title":"Siamrpn++: evolution of siamese visual tracking with very deep networks","author":"B. Li","key":"76"},{"first-page":"4904","article-title":"Learning spatial-temporal regularized correlation filters for visual tracking","author":"F. Li","key":"77"},{"article-title":"SiamVGG: visual tracking using deeper siamese networks","year":"2019","author":"Y. Li","key":"78"},{"first-page":"4834","article-title":"A twofold Siamese network for real-time object tracking","author":"A. He","key":"79"},{"first-page":"483","article-title":"Unveiling the power of deep tracking","author":"G. Bhat","key":"80"},{"first-page":"489","article-title":"Correlation tracking via joint discrimination and reliability learning","author":"C. Sun","key":"81"},{"author":"M. Che","key":"82","article-title":"Channel pruning for visual tracking"}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2020\/6681391.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2020\/6681391.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2020\/6681391.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,25]],"date-time":"2020-12-25T02:21:52Z","timestamp":1608862912000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/wcmc\/2020\/6681391\/"}},"subtitle":[],"editor":[{"given":"Amr","family":"Tolba","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,12,23]]},"references-count":82,"alternative-id":["6681391","6681391"],"URL":"https:\/\/doi.org\/10.1155\/2020\/6681391","relation":{},"ISSN":["1530-8677","1530-8669"],"issn-type":[{"type":"electronic","value":"1530-8677"},{"type":"print","value":"1530-8669"}],"subject":[],"published":{"date-parts":[[2020,12,23]]}}}