A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing
Autonomous underwater vehicles (AUV) recycling in an underwater environment is particularly challenging due to the continuous exploitation of marine resources. AUV recycling via visual technology is the primary method. However, the current visual technology is limited by harsh sea conditions and has...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/748 |
| _version_ | 1797623324400943104 |
|---|---|
| author | Tao Zou Weilun Situ Wenlin Yang Weixiang Zeng Yunting Wang |
| author_facet | Tao Zou Weilun Situ Wenlin Yang Weixiang Zeng Yunting Wang |
| author_sort | Tao Zou |
| collection | DOAJ |
| description | Autonomous underwater vehicles (AUV) recycling in an underwater environment is particularly challenging due to the continuous exploitation of marine resources. AUV recycling via visual technology is the primary method. However, the current visual technology is limited by harsh sea conditions and has problems, such as poor tracking and detection. To solve these problems, we propose a long-term target anti-interference tracking (LTAT) method, which integrates Siamese networks, You Only Look Once (YOLO) networks and online learning ideas. Meanwhile, we propose using the cubature Kalman filter (CKF) for optimization and prediction of the position. We constructed a launch and recovery system (LARS) tracking and capturing the AUV. The system consists of the following parts: First, images are acquired via binocular cameras. Next, the relative position between the AUV and the end of the LARS was estimated based on the pixel positions of the tracking AUV feature points and binocular camera data. Finally, using a discrete proportion integration differentiation (PID) method, the LARS is controlled to capture the moving AUV via a CKF-optimized position. To verify the feasibility of our proposed system, we used the robot operating system (ROS) platform and Gazebo software to simulate the system for experiments and visualization. The experiment demonstrates that in the tracking process when the AUV makes a sinusoidal motion with an amplitude of 0.2 m in the three-dimensional space and the relative distance between the AUV and LARS is no more than 1 m, the estimated position error of the AUV does not exceed 0.03 m. In the capturing process, the final capturing error is about 28 mm. Our results verify that our proposed system has high robustness and accuracy, providing the foundation for future AUV recycling research. |
| first_indexed | 2024-03-11T09:27:09Z |
| format | Article |
| id | doaj.art-5399b68ce86f4a23b3b9a9b5f4140549 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:09Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5399b68ce86f4a23b3b9a9b5f41405492023-11-16T17:53:41ZengMDPI AGRemote Sensing2072-42922023-01-0115374810.3390/rs15030748A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and CapturingTao Zou0Weilun Situ1Wenlin Yang2Weixiang Zeng3Yunting Wang4School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaGuangdong Institute of Intelligent Unmanned System, Guangzhou 511458, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaAutonomous underwater vehicles (AUV) recycling in an underwater environment is particularly challenging due to the continuous exploitation of marine resources. AUV recycling via visual technology is the primary method. However, the current visual technology is limited by harsh sea conditions and has problems, such as poor tracking and detection. To solve these problems, we propose a long-term target anti-interference tracking (LTAT) method, which integrates Siamese networks, You Only Look Once (YOLO) networks and online learning ideas. Meanwhile, we propose using the cubature Kalman filter (CKF) for optimization and prediction of the position. We constructed a launch and recovery system (LARS) tracking and capturing the AUV. The system consists of the following parts: First, images are acquired via binocular cameras. Next, the relative position between the AUV and the end of the LARS was estimated based on the pixel positions of the tracking AUV feature points and binocular camera data. Finally, using a discrete proportion integration differentiation (PID) method, the LARS is controlled to capture the moving AUV via a CKF-optimized position. To verify the feasibility of our proposed system, we used the robot operating system (ROS) platform and Gazebo software to simulate the system for experiments and visualization. The experiment demonstrates that in the tracking process when the AUV makes a sinusoidal motion with an amplitude of 0.2 m in the three-dimensional space and the relative distance between the AUV and LARS is no more than 1 m, the estimated position error of the AUV does not exceed 0.03 m. In the capturing process, the final capturing error is about 28 mm. Our results verify that our proposed system has high robustness and accuracy, providing the foundation for future AUV recycling research.https://www.mdpi.com/2072-4292/15/3/748autonomous underwater vehicles (AUV)long-term trackingdeep learningCKFLARS capturing |
| spellingShingle | Tao Zou Weilun Situ Wenlin Yang Weixiang Zeng Yunting Wang A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing Remote Sensing autonomous underwater vehicles (AUV) long-term tracking deep learning CKF LARS capturing |
| title | A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing |
| title_full | A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing |
| title_fullStr | A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing |
| title_full_unstemmed | A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing |
| title_short | A Method for Long-Term Target Anti-Interference Tracking Combining Deep Learning and CKF for LARS Tracking and Capturing |
| title_sort | method for long term target anti interference tracking combining deep learning and ckf for lars tracking and capturing |
| topic | autonomous underwater vehicles (AUV) long-term tracking deep learning CKF LARS capturing |
| url | https://www.mdpi.com/2072-4292/15/3/748 |
| work_keys_str_mv | AT taozou amethodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT weilunsitu amethodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT wenlinyang amethodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT weixiangzeng amethodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT yuntingwang amethodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT taozou methodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT weilunsitu methodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT wenlinyang methodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT weixiangzeng methodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing AT yuntingwang methodforlongtermtargetantiinterferencetrackingcombiningdeeplearningandckfforlarstrackingandcapturing |