A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR
Video synthetic aperture radar (Video-SAR) allows continuous and intuitive observation and is widely used for radar moving target tracking. The shadow of a moving target has the characteristics of stable scattering and no location shift, making moving target tracking using shadows a hot topic. Howev...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/22/4504 |
_version_ | 1797508596214267904 |
---|---|
author | Jinyu Bao Xiaoling Zhang Tianwen Zhang Jun Shi Shunjun Wei |
author_facet | Jinyu Bao Xiaoling Zhang Tianwen Zhang Jun Shi Shunjun Wei |
author_sort | Jinyu Bao |
collection | DOAJ |
description | Video synthetic aperture radar (Video-SAR) allows continuous and intuitive observation and is widely used for radar moving target tracking. The shadow of a moving target has the characteristics of stable scattering and no location shift, making moving target tracking using shadows a hot topic. However, the existing techniques mainly rely on the appearance of targets, which is impractical and costly, especially for tracking targets of interest (TOIs) with high diversity and arbitrariness. Therefore, to solve this problem, we propose a novel guided anchor Siamese network (GASN) dedicated to arbitrary TOI tracking in Video-SAR. First, GASN searches for matching areas in the subsequent frames with the initial area of the TOI in the first frame are conducted, returning the most similar area using a matching function, which is learned from general training without TOI-related data. With the learned matching function, GASN can be used to track arbitrary TOIs. Moreover, we also constructed a guided anchor subnetwork, referred to as GA-SubNet, which employs the prior information of the first frame and generates sparse anchors of the same shape as the TOIs. The number of unnecessary anchors is therefore reduced to suppress false alarms. Our method was evaluated on simulated and real Video-SAR data. The experimental results demonstrated that GASN outperforms state-of-the-art methods, including two types of traditional tracking methods (MOSSE and KCF) and two types of modern deep learning techniques (Siamese-FC and Siamese-RPN). We also conducted an ablation experiment to demonstrate the effectiveness of GA-SubNet. |
first_indexed | 2024-03-10T05:06:11Z |
format | Article |
id | doaj.art-8b1b095d3d6b49d096add92502eca669 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T05:06:11Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-8b1b095d3d6b49d096add92502eca6692023-11-23T01:18:27ZengMDPI AGRemote Sensing2072-42922021-11-011322450410.3390/rs13224504A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SARJinyu Bao0Xiaoling Zhang1Tianwen Zhang2Jun Shi3Shunjun Wei4School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaVideo synthetic aperture radar (Video-SAR) allows continuous and intuitive observation and is widely used for radar moving target tracking. The shadow of a moving target has the characteristics of stable scattering and no location shift, making moving target tracking using shadows a hot topic. However, the existing techniques mainly rely on the appearance of targets, which is impractical and costly, especially for tracking targets of interest (TOIs) with high diversity and arbitrariness. Therefore, to solve this problem, we propose a novel guided anchor Siamese network (GASN) dedicated to arbitrary TOI tracking in Video-SAR. First, GASN searches for matching areas in the subsequent frames with the initial area of the TOI in the first frame are conducted, returning the most similar area using a matching function, which is learned from general training without TOI-related data. With the learned matching function, GASN can be used to track arbitrary TOIs. Moreover, we also constructed a guided anchor subnetwork, referred to as GA-SubNet, which employs the prior information of the first frame and generates sparse anchors of the same shape as the TOIs. The number of unnecessary anchors is therefore reduced to suppress false alarms. Our method was evaluated on simulated and real Video-SAR data. The experimental results demonstrated that GASN outperforms state-of-the-art methods, including two types of traditional tracking methods (MOSSE and KCF) and two types of modern deep learning techniques (Siamese-FC and Siamese-RPN). We also conducted an ablation experiment to demonstrate the effectiveness of GA-SubNet.https://www.mdpi.com/2072-4292/13/22/4504video synthetic aperture radar (Video-SAR)moving target trackingguided anchor Siamese network (GASN) |
spellingShingle | Jinyu Bao Xiaoling Zhang Tianwen Zhang Jun Shi Shunjun Wei A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR Remote Sensing video synthetic aperture radar (Video-SAR) moving target tracking guided anchor Siamese network (GASN) |
title | A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR |
title_full | A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR |
title_fullStr | A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR |
title_full_unstemmed | A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR |
title_short | A Novel Guided Anchor Siamese Network for Arbitrary Target-of-Interest Tracking in Video-SAR |
title_sort | novel guided anchor siamese network for arbitrary target of interest tracking in video sar |
topic | video synthetic aperture radar (Video-SAR) moving target tracking guided anchor Siamese network (GASN) |
url | https://www.mdpi.com/2072-4292/13/22/4504 |
work_keys_str_mv | AT jinyubao anovelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT xiaolingzhang anovelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT tianwenzhang anovelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT junshi anovelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT shunjunwei anovelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT jinyubao novelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT xiaolingzhang novelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT tianwenzhang novelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT junshi novelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar AT shunjunwei novelguidedanchorsiamesenetworkforarbitrarytargetofinteresttrackinginvideosar |