Moving Object Tracking via 3-D Total Variation in Remote-Sensing Videos

被引：4

作者：

Wei, Jie ^{[1
]}

Sun, Jin ^{[1
]}

Wu, Zebin ^{[1
]}

Yang, Jiandong ^{[2
]}

Wei, Zhihui ^{[1
]}

机构：

[1] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China

[2] China Satellite Maritime Tracking & Control Dept, Jiangyin 214431, Peoples R China

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2022年 / 19卷

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Videos; TV; Object tracking; Hyperspectral imaging; Sun; Analytical models; Cameras; remote-sensing videos; robust principal component;

D O I：

10.1109/LGRS.2021.3077257

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Tracking moving objects in remote-sensing videos is becoming increasingly important in remote-sensing analysis. This letter presents a novel object tracking method for remote-sensing videos. We start with using the traditional robust principal component analysis (RPCA) model to extract the moving object from the background. To describe the continuity of moving objects in spatial and temporal directions, we incorporate a 3-D total variation (3DTV) regularization into the RPCA model. Considering that the background is not static and the captured videos will contain noise because of the instability of the sensing camera, our proposed method introduces a certain part of the function to model the noise and capture the changes in background. Experimental results on real videos provided by 2016 IEEE GRSS Data Fusion Contest and 2020 Hyperspectral Object Tracking Challenge demonstrate the advantages of the moving object-tracking method via 3-D TV.

引用

页数：5

共 50 条

[1] THE RADIOSITY METHOD IN OPTICAL REMOTE-SENSING OF STRUCTURED 3-D SURFACES
BOREL, CC
GERSTL, SAW
POWERS, BJ
[J]. REMOTE SENSING OF ENVIRONMENT, 1991, 36 (01) : 13 - 44
[2] Tensor Total Variation Regularized Moving Object Detection for Surveillance Videos
Tom, Anju Jose
George, Sudhish N.
[J]. 2018 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS (SPCOM 2018), 2018, : 327 - 331
[3] Remote-Sensing Image Segmentation Based on Implicit 3-D Scene Representation
Qi, Zipeng
Zou, Zhengxia
Chen, Hao
Shi, Zhenwei
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[4] Tracking moving object in 3-D space based on optical flow and edges
Mae, Y
Shirai, Y
[J]. FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 1439 - 1441
[5] Object Tracking and Target Reacquisition Based on 3-D Range Data for Moving Vehicles
Lee, Jehoon
Lankton, Shawn
Tannenbaum, Allen
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (10) : 2912 - 2924
[6] Distributed Kalman Filter for 3-D Moving Object Tracking over Sensor Networks
Zhu, Pengxiang
Ren, Wei
[J]. 2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 2418 - 2423
[7] 3-D landscape modeling for remote sensing
Su, LH
Huang, YX
Li, XW
[J]. VISUALIZATION AND OPTIMIZATION TECHNIQUES, 2001, 4553 : 384 - 391
[8] 3-D Object Recognition via Aspect Graph Aware 3-D Object Representation
Hu, Mengjie
Wei, Zhenzhong
Shao, Mingwei
Zhang, Guangjun
[J]. IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (12) : 2359 - 2363
[9] Geometric invariants for verification in 3-D object tracking
Uenohara, U
Kanade, T
[J]. IROS 96 - PROCEEDINGS OF THE 1996 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS - ROBOTIC INTELLIGENCE INTERACTING WITH DYNAMIC WORLDS, VOLS 1-3, 1996, : 785 - 790
[10] Multi-Robot Joint Visual-Inertial Localization and 3-D Moving Object Tracking
Zhu, Pengxiang
Ren, Wei
[J]. 2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 11573 - 11580

← 1 2 3 4 5 →