The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam beberapa tahun kebelakangan ini, pembangunan penjejakan visual semakin baik dan lebih baik, tetapi beberapa kaedah tidak dapat mengatasi masalah ketepatan rendah dan kadar kejayaan penjejakan. Walaupun terdapat beberapa penjejak akan lebih tepat, ia memerlukan lebih banyak masa. Untuk menyelesaikan masalah, kami mencadangkan penjejak yang diperkukuh berdasarkan Ciri Konvolusi Hierarki (pendek kata HCF). Ciri HOG, penamaan warna dan skala kelabu digunakan dengan pemberat berbeza untuk menambah ciri lilitan, yang boleh meningkatkan keteguhan penjejakan. Pada masa yang sama, kami menambah baik strategi kemas kini model untuk menjimatkan kos masa. Penjejak ini dipanggil RHCF dan kod itu diterbitkan di https://github.com/z15846/RHCF. Percubaan pada set data OTB2013 menunjukkan bahawa penjejak kami boleh mencapai promosi ketepatan dan kadar kejayaan dengan sah.
Xin ZENG
Sichuan University of Science and Engineering
Lin ZHANG
Sichuan University of Science and Engineering
Zhongqiang LUO
Sichuan University of Science and Engineering
Xingzhong XIONG
Sichuan University of Science and Engineering
Chengjie LI
Southwest Minzu University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Xin ZENG, Lin ZHANG, Zhongqiang LUO, Xingzhong XIONG, Chengjie LI, "Reinforced Tracker Based on Hierarchical Convolutional Features" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 6, pp. 1225-1233, June 2022, doi: 10.1587/transinf.2021EDP7140.
Abstract: In recent years, the development of visual tracking is getting better and better, but some methods cannot overcome the problem of low accuracy and success rate of tracking. Although there are some trackers will be more accurate, they will cost more time. In order to solve the problem, we propose a reinforced tracker based on Hierarchical Convolutional Features (HCF for short). HOG, color-naming and grayscale features are used with different weights to supplement the convolution features, which can enhance the tracking robustness. At the same time, we improved the model update strategy to save the time costs. This tracker is called RHCF and the code is published on https://github.com/z15846/RHCF. Experiments on the OTB2013 dataset show that our tracker can validly achieve the promotion of the accuracy and success rate.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7140/_p
Salinan
@ARTICLE{e105-d_6_1225,
author={Xin ZENG, Lin ZHANG, Zhongqiang LUO, Xingzhong XIONG, Chengjie LI, },
journal={IEICE TRANSACTIONS on Information},
title={Reinforced Tracker Based on Hierarchical Convolutional Features},
year={2022},
volume={E105-D},
number={6},
pages={1225-1233},
abstract={In recent years, the development of visual tracking is getting better and better, but some methods cannot overcome the problem of low accuracy and success rate of tracking. Although there are some trackers will be more accurate, they will cost more time. In order to solve the problem, we propose a reinforced tracker based on Hierarchical Convolutional Features (HCF for short). HOG, color-naming and grayscale features are used with different weights to supplement the convolution features, which can enhance the tracking robustness. At the same time, we improved the model update strategy to save the time costs. This tracker is called RHCF and the code is published on https://github.com/z15846/RHCF. Experiments on the OTB2013 dataset show that our tracker can validly achieve the promotion of the accuracy and success rate.},
keywords={},
doi={10.1587/transinf.2021EDP7140},
ISSN={1745-1361},
month={June},}
Salinan
TY - JOUR
TI - Reinforced Tracker Based on Hierarchical Convolutional Features
T2 - IEICE TRANSACTIONS on Information
SP - 1225
EP - 1233
AU - Xin ZENG
AU - Lin ZHANG
AU - Zhongqiang LUO
AU - Xingzhong XIONG
AU - Chengjie LI
PY - 2022
DO - 10.1587/transinf.2021EDP7140
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2022
AB - In recent years, the development of visual tracking is getting better and better, but some methods cannot overcome the problem of low accuracy and success rate of tracking. Although there are some trackers will be more accurate, they will cost more time. In order to solve the problem, we propose a reinforced tracker based on Hierarchical Convolutional Features (HCF for short). HOG, color-naming and grayscale features are used with different weights to supplement the convolution features, which can enhance the tracking robustness. At the same time, we improved the model update strategy to save the time costs. This tracker is called RHCF and the code is published on https://github.com/z15846/RHCF. Experiments on the OTB2013 dataset show that our tracker can validly achieve the promotion of the accuracy and success rate.
ER -