On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds
On-satellite information processing enables all-weather target tracking. The background of videos from satellite sensors exhibits an affine transformation due to their motion relative to the Earth. In complex moving backgrounds, moving vehicles have a small number of pixels and weak texture features...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/3/418 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849717635094151168 |
|---|---|
| author | Jingyi Yu Siyuan Wei Yuxiao Wen Danshu Zhou Runjiang Dou Xiuyu Wang Jiangtao Xu Jian Liu Nanjian Wu Liyuan Liu |
| author_facet | Jingyi Yu Siyuan Wei Yuxiao Wen Danshu Zhou Runjiang Dou Xiuyu Wang Jiangtao Xu Jian Liu Nanjian Wu Liyuan Liu |
| author_sort | Jingyi Yu |
| collection | DOAJ |
| description | On-satellite information processing enables all-weather target tracking. The background of videos from satellite sensors exhibits an affine transformation due to their motion relative to the Earth. In complex moving backgrounds, moving vehicles have a small number of pixels and weak texture features. At the same time, the resources and performance of on-satellite equipment are limited. To address these issues, we propose a multi-object tracking (MOT) algorithm with a detection–association framework for moving vehicles in complex moving backgrounds and implement the algorithm on a satellite to achieve real-time MOT. We use feature matching to effectively eliminate the effects of background motion and use the neighborhood pixel difference method to extract moving vehicle targets in the detection stage. The accurate extraction of motion targets ensures the effectiveness of target association to achieve MOT of moving vehicles in complex moving backgrounds. Additionally, we use a Field-Programmable Gate Array (FPGA) to implement the algorithm completely on a satellite. We propose a pixel-level stream processing mode and a cache access processing mode, given the characteristics of on-satellite equipment and sensors. According to the experimental results, the prototype on-satellite implementation method proposed in this paper can achieve real-time processing at 1024 × 1024 px@47 fps. |
| format | Article |
| id | doaj-art-a54c61f3085c4848b09be0a620f1331d |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-a54c61f3085c4848b09be0a620f1331d2025-08-20T03:12:35ZengMDPI AGRemote Sensing2072-42922025-01-0117341810.3390/rs17030418On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving BackgroundsJingyi Yu0Siyuan Wei1Yuxiao Wen2Danshu Zhou3Runjiang Dou4Xiuyu Wang5Jiangtao Xu6Jian Liu7Nanjian Wu8Liyuan Liu9Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, School of Microelectronics, Tianjin University, Tianjin 300072, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaTianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, School of Microelectronics, Tianjin University, Tianjin 300072, ChinaTianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, School of Microelectronics, Tianjin University, Tianjin 300072, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaState Key Laboratory of Semiconductor Physics and Chip Technologies, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, ChinaOn-satellite information processing enables all-weather target tracking. The background of videos from satellite sensors exhibits an affine transformation due to their motion relative to the Earth. In complex moving backgrounds, moving vehicles have a small number of pixels and weak texture features. At the same time, the resources and performance of on-satellite equipment are limited. To address these issues, we propose a multi-object tracking (MOT) algorithm with a detection–association framework for moving vehicles in complex moving backgrounds and implement the algorithm on a satellite to achieve real-time MOT. We use feature matching to effectively eliminate the effects of background motion and use the neighborhood pixel difference method to extract moving vehicle targets in the detection stage. The accurate extraction of motion targets ensures the effectiveness of target association to achieve MOT of moving vehicles in complex moving backgrounds. Additionally, we use a Field-Programmable Gate Array (FPGA) to implement the algorithm completely on a satellite. We propose a pixel-level stream processing mode and a cache access processing mode, given the characteristics of on-satellite equipment and sensors. According to the experimental results, the prototype on-satellite implementation method proposed in this paper can achieve real-time processing at 1024 × 1024 px@47 fps.https://www.mdpi.com/2072-4292/17/3/418multi-object tracking (MOT)detection–association frameworkmoving vehicle targetson-satellite implementationFPGA |
| spellingShingle | Jingyi Yu Siyuan Wei Yuxiao Wen Danshu Zhou Runjiang Dou Xiuyu Wang Jiangtao Xu Jian Liu Nanjian Wu Liyuan Liu On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds Remote Sensing multi-object tracking (MOT) detection–association framework moving vehicle targets on-satellite implementation FPGA |
| title | On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds |
| title_full | On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds |
| title_fullStr | On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds |
| title_full_unstemmed | On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds |
| title_short | On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds |
| title_sort | on satellite implementation of real time multi object moving vehicle tracking with complex moving backgrounds |
| topic | multi-object tracking (MOT) detection–association framework moving vehicle targets on-satellite implementation FPGA |
| url | https://www.mdpi.com/2072-4292/17/3/418 |
| work_keys_str_mv | AT jingyiyu onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT siyuanwei onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT yuxiaowen onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT danshuzhou onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT runjiangdou onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT xiuyuwang onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT jiangtaoxu onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT jianliu onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT nanjianwu onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds AT liyuanliu onsatelliteimplementationofrealtimemultiobjectmovingvehicletrackingwithcomplexmovingbackgrounds |