An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects
Optical remote sensing videos, as a new source of remote sensing data that has emerged in recent years, have significant potential in remote sensing applications, especially national defense. In this paper, a tracking pipeline named TDNet (tracking while detecting based on a neural network) is propo...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/4/724 |
| _version_ | 1797297062284361728 |
|---|---|
| author | Zhijuan Su Gang Wan Wenhua Zhang Ningbo Guo Yitian Wu Jia Liu Dianwei Cong Yutong Jia Zhanji Wei |
| author_facet | Zhijuan Su Gang Wan Wenhua Zhang Ningbo Guo Yitian Wu Jia Liu Dianwei Cong Yutong Jia Zhanji Wei |
| author_sort | Zhijuan Su |
| collection | DOAJ |
| description | Optical remote sensing videos, as a new source of remote sensing data that has emerged in recent years, have significant potential in remote sensing applications, especially national defense. In this paper, a tracking pipeline named TDNet (tracking while detecting based on a neural network) is proposed for optical remote sensing videos based on a correlation filter and deep neural networks. The pipeline is used to simultaneously track ships and planes in videos. There are many target tracking methods for general video data, but they suffer some difficulties in remote sensing videos with low resolution and those influenced by weather conditions. The tracked targets are usually misty. Therefore, in TDNet, we propose a new multi-target tracking method called MT-KCF and a detecting-assisted tracking (i.e., DAT) module to improve tracking accuracy and precision. Meanwhile, we also design a new target recognition (i.e., NTR) module to recognise newly emerged targets. In order to verify the performance of TDNet, we compare our method with several state-of-the-art tracking methods on optical video remote sensing data sets acquired from the Jilin No. 1 satellite. The experimental results demonstrate the effectiveness and the state-of-the-art performance of the proposed method. The proposed method can achieve more than 90% performance in terms of precision for single-target tracking tasks and more than 85% performance in terms of MOTA for multi-object tracking tasks. |
| first_indexed | 2024-03-07T22:14:48Z |
| format | Article |
| id | doaj.art-41a3dd5244ad4a3da4ee6e9435db097a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-07T22:14:48Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-41a3dd5244ad4a3da4ee6e9435db097a2024-02-23T15:33:13ZengMDPI AGRemote Sensing2072-42922024-02-0116472410.3390/rs16040724An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial ObjectsZhijuan Su0Gang Wan1Wenhua Zhang2Ningbo Guo3Yitian Wu4Jia Liu5Dianwei Cong6Yutong Jia7Zhanji Wei8School of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaSchool of Space Information, Space Engineering University, Beijing 101407, ChinaOptical remote sensing videos, as a new source of remote sensing data that has emerged in recent years, have significant potential in remote sensing applications, especially national defense. In this paper, a tracking pipeline named TDNet (tracking while detecting based on a neural network) is proposed for optical remote sensing videos based on a correlation filter and deep neural networks. The pipeline is used to simultaneously track ships and planes in videos. There are many target tracking methods for general video data, but they suffer some difficulties in remote sensing videos with low resolution and those influenced by weather conditions. The tracked targets are usually misty. Therefore, in TDNet, we propose a new multi-target tracking method called MT-KCF and a detecting-assisted tracking (i.e., DAT) module to improve tracking accuracy and precision. Meanwhile, we also design a new target recognition (i.e., NTR) module to recognise newly emerged targets. In order to verify the performance of TDNet, we compare our method with several state-of-the-art tracking methods on optical video remote sensing data sets acquired from the Jilin No. 1 satellite. The experimental results demonstrate the effectiveness and the state-of-the-art performance of the proposed method. The proposed method can achieve more than 90% performance in terms of precision for single-target tracking tasks and more than 85% performance in terms of MOTA for multi-object tracking tasks.https://www.mdpi.com/2072-4292/16/4/724optical remote sensing videoscorrelation filterdeep neural networktarget tracking |
| spellingShingle | Zhijuan Su Gang Wan Wenhua Zhang Ningbo Guo Yitian Wu Jia Liu Dianwei Cong Yutong Jia Zhanji Wei An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects Remote Sensing optical remote sensing videos correlation filter deep neural network target tracking |
| title | An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects |
| title_full | An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects |
| title_fullStr | An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects |
| title_full_unstemmed | An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects |
| title_short | An Integrated Detection and Multi-Object Tracking Pipeline for Satellite Video Analysis of Maritime and Aerial Objects |
| title_sort | integrated detection and multi object tracking pipeline for satellite video analysis of maritime and aerial objects |
| topic | optical remote sensing videos correlation filter deep neural network target tracking |
| url | https://www.mdpi.com/2072-4292/16/4/724 |
| work_keys_str_mv | AT zhijuansu anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT gangwan anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT wenhuazhang anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT ningboguo anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT yitianwu anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT jialiu anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT dianweicong anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT yutongjia anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT zhanjiwei anintegrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT zhijuansu integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT gangwan integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT wenhuazhang integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT ningboguo integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT yitianwu integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT jialiu integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT dianweicong integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT yutongjia integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects AT zhanjiwei integrateddetectionandmultiobjecttrackingpipelineforsatellitevideoanalysisofmaritimeandaerialobjects |