Approach of target tracking combining particle filter and metric learning
Focusing on the issue of the significant degradation of target tracking performance caused by adverse factors in complex environment, a target tracking method based on particle filtering and metric learning was proposed.First of all, a convolutional neural network (CNN) was offline-trained via the p...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2021-05-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021087/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539201331363840 |
|---|---|
| author | Hongyan WANG Libin ZHANG Guoqiang CHEN Zumin WANG Zhiyuan GUAN |
| author_facet | Hongyan WANG Libin ZHANG Guoqiang CHEN Zumin WANG Zhiyuan GUAN |
| author_sort | Hongyan WANG |
| collection | DOAJ |
| description | Focusing on the issue of the significant degradation of target tracking performance caused by adverse factors in complex environment, a target tracking method based on particle filtering and metric learning was proposed.First of all, a convolutional neural network (CNN) was offline-trained via the proposed method to effectively obtain the target characteristics.After that, the distance measurement matrix optimization model to minimize the prediction error could be constructed on the basis of the metric learning for kernel regression (MLKR) method, and the resultant model could be handled via using the gradient descent approach to obtain the optimal solution of the candidate target.Moreover, based on the predicted value of the optimal candidate target, the reconstruction error was calculated to construct the target observation model.Finally, a long-short-term update strategy was introduced to achieve the effective target tracking under the particle filter tracking framework.The experiment results show that the proposed method has higher tracking accuracy and better robustness in complex environments. |
| format | Article |
| id | doaj-art-6da3822d216c40779d92c094f2b573ed |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2021-05-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-6da3822d216c40779d92c094f2b573ed2025-01-14T07:24:04ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2021-05-01429811059835292Approach of target tracking combining particle filter and metric learningHongyan WANGLibin ZHANGGuoqiang CHENZumin WANGZhiyuan GUANFocusing on the issue of the significant degradation of target tracking performance caused by adverse factors in complex environment, a target tracking method based on particle filtering and metric learning was proposed.First of all, a convolutional neural network (CNN) was offline-trained via the proposed method to effectively obtain the target characteristics.After that, the distance measurement matrix optimization model to minimize the prediction error could be constructed on the basis of the metric learning for kernel regression (MLKR) method, and the resultant model could be handled via using the gradient descent approach to obtain the optimal solution of the candidate target.Moreover, based on the predicted value of the optimal candidate target, the reconstruction error was calculated to construct the target observation model.Finally, a long-short-term update strategy was introduced to achieve the effective target tracking under the particle filter tracking framework.The experiment results show that the proposed method has higher tracking accuracy and better robustness in complex environments.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021087/target trackingparticle filterconvolutional neural networkmetric learningsparse representation |
| spellingShingle | Hongyan WANG Libin ZHANG Guoqiang CHEN Zumin WANG Zhiyuan GUAN Approach of target tracking combining particle filter and metric learning Tongxin xuebao target tracking particle filter convolutional neural network metric learning sparse representation |
| title | Approach of target tracking combining particle filter and metric learning |
| title_full | Approach of target tracking combining particle filter and metric learning |
| title_fullStr | Approach of target tracking combining particle filter and metric learning |
| title_full_unstemmed | Approach of target tracking combining particle filter and metric learning |
| title_short | Approach of target tracking combining particle filter and metric learning |
| title_sort | approach of target tracking combining particle filter and metric learning |
| topic | target tracking particle filter convolutional neural network metric learning sparse representation |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021087/ |
| work_keys_str_mv | AT hongyanwang approachoftargettrackingcombiningparticlefilterandmetriclearning AT libinzhang approachoftargettrackingcombiningparticlefilterandmetriclearning AT guoqiangchen approachoftargettrackingcombiningparticlefilterandmetriclearning AT zuminwang approachoftargettrackingcombiningparticlefilterandmetriclearning AT zhiyuanguan approachoftargettrackingcombiningparticlefilterandmetriclearning |