Fast Visual Tracking with Squeeze and Excitation Region Proposal Network

Dun Cao; Renhua Dai; Jin Wang; Baofeng Ji; Osama Alfarraj; Amr Tolba; Pradip Kumar Sharma; Min Zhu

doi:10.22967/HCIS.2023.13.007

Fast Visual Tracking with Squeeze and Excitation Region Proposal Network

Dun Cao
, Renhua Dai
, Jin Wang
, Baofeng Ji
, Osama Alfarraj
, Amr Tolba
, Pradip Kumar Sharma
, Min Zhu^*

^*Corresponding author for this work

Changsha University of Science and Technology
Henan University of Science and Technology
King Saud University
Zhejiang Shuren University

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

7 Downloads (Pure)

Abstract

Siamese trackers have achieved significant progress over the past few years. However, the existing methods are either high speed or high performance, and it is difficult for previous Siamese trackers to balance both. In this work, we propose a high-performance yet effective tracker (SiamSERPN), which utilizes MobileNetV2 as the backbone and equips with the proposed squeeze and excitation region proposal network (SERPN). For the SERPN block, we introduce the distance-IoU (DIoU) into the classification and regression branches to remedy the weakness of traditional RPN. Benefiting from the structure of MobileNetV2, we propose a feature aggregation architecture of multi-SERPN blocks to improve performance further. Extensive experiments and comparisons on visual tracking benchmarks, including VOT2016, VOT2018, and GOT-10k, demonstrate that our SiamSERPN can balance speed and performance. Especially on GOT-10k benchmark, our tracker scores 0.604

Original language	English
Article number	7
Number of pages	20
Journal	Human-centric Computing and Information Sciences
Volume	13
DOIs	https://doi.org/10.22967/HCIS.2023.13.007
Publication status	Published - 15 Feb 2023

Bibliographical note

Funding Information:
This work was funded by the National Natural Science Foundation of China (Grant No. 62272063, 62072056, 61902041 and 61801170), Open research fund of Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications), Ministry of Education, project of Education Department Cooperation Cultivation (Grant No. 201602011005 and No. 201702135098), China Postdoctoral Science Foundation (Grant No.

Funding

This work was funded by the National Natural Science Foundation of China (Grant No. 62272063, 62072056, 61902041 and 61801170), Open research fund of Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications), Ministry of Education, project of Education Department Cooperation Cultivation (Grant No. 201602011005 and No. 201702135098), China Postdoctoral Science Foundation (Grant No. 2018M633351), the National 13th Five National Defense Fund (Grant No. 6140311030207). Researchers Supporting Project No. RSP2023R102 King Saud University, Riyadh, Saudi Arabia.

Keywords

Distance-IoU
MobileNet-V2
Object Tracking
SERPN
Siamese Network

Access to Document

10.22967/HCIS.2023.13.007Licence: CC BY-NC

Cao_etal_HCISJ_Fast_Visual_Tracking_VOR
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Final published version, 5.34 MBLicence: CC BY-NC

Cite this

@article{89d4710dc7444601b8f061674c60b3a9,

title = "Fast Visual Tracking with Squeeze and Excitation Region Proposal Network",

abstract = "Siamese trackers have achieved significant progress over the past few years. However, the existing methods are either high speed or high performance, and it is difficult for previous Siamese trackers to balance both. In this work, we propose a high-performance yet effective tracker (SiamSERPN), which utilizes MobileNetV2 as the backbone and equips with the proposed squeeze and excitation region proposal network (SERPN). For the SERPN block, we introduce the distance-IoU (DIoU) into the classification and regression branches to remedy the weakness of traditional RPN. Benefiting from the structure of MobileNetV2, we propose a feature aggregation architecture of multi-SERPN blocks to improve performance further. Extensive experiments and comparisons on visual tracking benchmarks, including VOT2016, VOT2018, and GOT-10k, demonstrate that our SiamSERPN can balance speed and performance. Especially on GOT-10k benchmark, our tracker scores 0.604",

keywords = "Distance-IoU, MobileNet-V2, Object Tracking, SERPN, Siamese Network",

author = "Dun Cao and Renhua Dai and Jin Wang and Baofeng Ji and Osama Alfarraj and Amr Tolba and Sharma, \{Pradip Kumar\} and Min Zhu",

note = "Funding Information: This work was funded by the National Natural Science Foundation of China (Grant No. 62272063, 62072056, 61902041 and 61801170), Open research fund of Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications), Ministry of Education, project of Education Department Cooperation Cultivation (Grant No. 201602011005 and No. 201702135098), China Postdoctoral Science Foundation (Grant No. ",

year = "2023",

month = feb,

day = "15",

doi = "10.22967/HCIS.2023.13.007",

language = "English",

volume = "13",

journal = "Human-centric Computing and Information Sciences",

issn = "2192-1962",

publisher = "Korea Information Processing Society",

}

TY - JOUR

T1 - Fast Visual Tracking with Squeeze and Excitation Region Proposal Network

AU - Cao, Dun

AU - Dai, Renhua

AU - Wang, Jin

AU - Ji, Baofeng

AU - Alfarraj, Osama

AU - Tolba, Amr

AU - Sharma, Pradip Kumar

AU - Zhu, Min

N1 - Funding Information: This work was funded by the National Natural Science Foundation of China (Grant No. 62272063, 62072056, 61902041 and 61801170), Open research fund of Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications), Ministry of Education, project of Education Department Cooperation Cultivation (Grant No. 201602011005 and No. 201702135098), China Postdoctoral Science Foundation (Grant No.

PY - 2023/2/15

Y1 - 2023/2/15

N2 - Siamese trackers have achieved significant progress over the past few years. However, the existing methods are either high speed or high performance, and it is difficult for previous Siamese trackers to balance both. In this work, we propose a high-performance yet effective tracker (SiamSERPN), which utilizes MobileNetV2 as the backbone and equips with the proposed squeeze and excitation region proposal network (SERPN). For the SERPN block, we introduce the distance-IoU (DIoU) into the classification and regression branches to remedy the weakness of traditional RPN. Benefiting from the structure of MobileNetV2, we propose a feature aggregation architecture of multi-SERPN blocks to improve performance further. Extensive experiments and comparisons on visual tracking benchmarks, including VOT2016, VOT2018, and GOT-10k, demonstrate that our SiamSERPN can balance speed and performance. Especially on GOT-10k benchmark, our tracker scores 0.604

AB - Siamese trackers have achieved significant progress over the past few years. However, the existing methods are either high speed or high performance, and it is difficult for previous Siamese trackers to balance both. In this work, we propose a high-performance yet effective tracker (SiamSERPN), which utilizes MobileNetV2 as the backbone and equips with the proposed squeeze and excitation region proposal network (SERPN). For the SERPN block, we introduce the distance-IoU (DIoU) into the classification and regression branches to remedy the weakness of traditional RPN. Benefiting from the structure of MobileNetV2, we propose a feature aggregation architecture of multi-SERPN blocks to improve performance further. Extensive experiments and comparisons on visual tracking benchmarks, including VOT2016, VOT2018, and GOT-10k, demonstrate that our SiamSERPN can balance speed and performance. Especially on GOT-10k benchmark, our tracker scores 0.604

KW - Distance-IoU

KW - MobileNet-V2

KW - Object Tracking

KW - SERPN

KW - Siamese Network

UR - https://www.scopus.com/pages/publications/85151009887

U2 - 10.22967/HCIS.2023.13.007

DO - 10.22967/HCIS.2023.13.007

M3 - Article

AN - SCOPUS:85151009887

SN - 2192-1962

VL - 13

JO - Human-centric Computing and Information Sciences

JF - Human-centric Computing and Information Sciences

M1 - 7

ER -

Fast Visual Tracking with Squeeze and Excitation Region Proposal Network

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this