Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism
Marine object tracking is critical for search and rescue activities in the complex marine environment. However, the complex marine environment poses a huge challenge to the effect of tracking, such as the variability of light, the impact of sea waves, the occlusion of other ships, etc. Under these c...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/18/5210 |
| _version_ | 1797553859154935808 |
|---|---|
| author | Yihong Zhang Shuai Li Demin Li Wuneng Zhou Yijin Yang Xiaodong Lin Shigao Jiang |
| author_facet | Yihong Zhang Shuai Li Demin Li Wuneng Zhou Yijin Yang Xiaodong Lin Shigao Jiang |
| author_sort | Yihong Zhang |
| collection | DOAJ |
| description | Marine object tracking is critical for search and rescue activities in the complex marine environment. However, the complex marine environment poses a huge challenge to the effect of tracking, such as the variability of light, the impact of sea waves, the occlusion of other ships, etc. Under these complex marine environmental factors, how to design an efficient dynamic visual tracker to make the results accurate, real time and robust is particularly important. The parallel three-branch correlation filters for complex marine environmental object tracking based on a confidence mechanism is proposed by us. The proposed tracker first detects the appearance change and position change of the object by constructing parallel three-branch correlation filters, which enhances the robustness of the correlation filter model. Through the weighted fusion of response maps, the center position of the object is accurately located. Secondly, the Gaussian-triangle joint distribution is used to replace the original Gaussian distribution in the training phase. Finally, a verification mechanism of confidence metric is embedded in the filter update section to analyze the tracking effect of the current frame, and to update the filter sample from verification result. Thus, a more accurate correlation filter is trained to prevent model drift and achieve a good tracking effect. We found that the effect of various interferences on the filter is effectively reduced by comparing with other trackers. The experiments prove that the proposed tracker can play an outstanding role in the complex marine environment. |
| first_indexed | 2024-03-10T16:22:37Z |
| format | Article |
| id | doaj.art-8918826202f44c4e9595adf597cc7326 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:22:37Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8918826202f44c4e9595adf597cc73262023-11-20T13:32:49ZengMDPI AGSensors1424-82202020-09-012018521010.3390/s20185210Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence MechanismYihong Zhang0Shuai Li1Demin Li2Wuneng Zhou3Yijin Yang4Xiaodong Lin5Shigao Jiang6College of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, DongHua University, Shanghai 201620, ChinaMarine object tracking is critical for search and rescue activities in the complex marine environment. However, the complex marine environment poses a huge challenge to the effect of tracking, such as the variability of light, the impact of sea waves, the occlusion of other ships, etc. Under these complex marine environmental factors, how to design an efficient dynamic visual tracker to make the results accurate, real time and robust is particularly important. The parallel three-branch correlation filters for complex marine environmental object tracking based on a confidence mechanism is proposed by us. The proposed tracker first detects the appearance change and position change of the object by constructing parallel three-branch correlation filters, which enhances the robustness of the correlation filter model. Through the weighted fusion of response maps, the center position of the object is accurately located. Secondly, the Gaussian-triangle joint distribution is used to replace the original Gaussian distribution in the training phase. Finally, a verification mechanism of confidence metric is embedded in the filter update section to analyze the tracking effect of the current frame, and to update the filter sample from verification result. Thus, a more accurate correlation filter is trained to prevent model drift and achieve a good tracking effect. We found that the effect of various interferences on the filter is effectively reduced by comparing with other trackers. The experiments prove that the proposed tracker can play an outstanding role in the complex marine environment.https://www.mdpi.com/1424-8220/20/18/5210parallel three-branch correlation filtersconfidence mechanismcomplex marine environmentobject tracking |
| spellingShingle | Yihong Zhang Shuai Li Demin Li Wuneng Zhou Yijin Yang Xiaodong Lin Shigao Jiang Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism Sensors parallel three-branch correlation filters confidence mechanism complex marine environment object tracking |
| title | Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism |
| title_full | Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism |
| title_fullStr | Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism |
| title_full_unstemmed | Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism |
| title_short | Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism |
| title_sort | parallel three branch correlation filters for complex marine environmental object tracking based on a confidence mechanism |
| topic | parallel three-branch correlation filters confidence mechanism complex marine environment object tracking |
| url | https://www.mdpi.com/1424-8220/20/18/5210 |
| work_keys_str_mv | AT yihongzhang parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism AT shuaili parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism AT deminli parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism AT wunengzhou parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism AT yijinyang parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism AT xiaodonglin parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism AT shigaojiang parallelthreebranchcorrelationfiltersforcomplexmarineenvironmentalobjecttrackingbasedonaconfidencemechanism |