Learning Spatial–Temporal Background-Aware Based Tracking
Discriminative correlation filter (DCF) based tracking algorithms have obtained prominent speed and accuracy strengths, which have attracted extensive attention and research. However, some unavoidable deficiencies still exist. For example, the circulant shifted sampling process is likely to cause re...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/18/8427 |
| _version_ | 1797520429898792960 |
|---|---|
| author | Peiting Gu Peizhong Liu Jianhua Deng Zhi Chen |
| author_facet | Peiting Gu Peizhong Liu Jianhua Deng Zhi Chen |
| author_sort | Peiting Gu |
| collection | DOAJ |
| description | Discriminative correlation filter (DCF) based tracking algorithms have obtained prominent speed and accuracy strengths, which have attracted extensive attention and research. However, some unavoidable deficiencies still exist. For example, the circulant shifted sampling process is likely to cause repeated periodic assumptions and cause boundary effects, which degrades the tracker’s discriminative performance, and the target is not easy to locate in complex appearance changes. In this paper, a spatial–temporal regularization module based on BACF (background-aware correlation filter) framework is proposed, which is performed by introducing a temporal regularization to deal effectively with the boundary effects issue. At the same time, the accuracy of target recognition is improved. This model can be effectively optimized by employing the alternating direction multiplier (ADMM) method, and each sub-problem has a corresponding closed solution. In addition, in terms of feature representation, we combine traditional hand-crafted features with deep convolution features linearly enhance the discriminative performance of the filter. Considerable experiments on multiple well-known benchmarks show the proposed algorithm is performs favorably against many state-of-the-art trackers and achieves an AUC score of 64.4% on OTB-100. |
| first_indexed | 2024-03-10T07:56:39Z |
| format | Article |
| id | doaj.art-fc4a3cb870db487cbcd404a05de246df |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T07:56:39Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fc4a3cb870db487cbcd404a05de246df2023-11-22T11:52:31ZengMDPI AGApplied Sciences2076-34172021-09-011118842710.3390/app11188427Learning Spatial–Temporal Background-Aware Based TrackingPeiting Gu0Peizhong Liu1Jianhua Deng2Zhi Chen3Fujian Provincial Key Laboratory of Data-Intensive Computing, Key Laboratory of Intelligent Computing and Information Processing, School of Mathmatics and Computer Science, Quanzhou Normal University, No. 398, Donghai Street, Quanzhou 362000, ChinaCollege of Engineering, Huaqiao University, No. 269, Chenghuabei Road, Quanzhou 362021, ChinaChengdu Aeronautic Polytechnic, No. 699, East 7th Checheng Road, Chengdu 610100, ChinaCollege of Engineering, Huaqiao University, No. 269, Chenghuabei Road, Quanzhou 362021, ChinaDiscriminative correlation filter (DCF) based tracking algorithms have obtained prominent speed and accuracy strengths, which have attracted extensive attention and research. However, some unavoidable deficiencies still exist. For example, the circulant shifted sampling process is likely to cause repeated periodic assumptions and cause boundary effects, which degrades the tracker’s discriminative performance, and the target is not easy to locate in complex appearance changes. In this paper, a spatial–temporal regularization module based on BACF (background-aware correlation filter) framework is proposed, which is performed by introducing a temporal regularization to deal effectively with the boundary effects issue. At the same time, the accuracy of target recognition is improved. This model can be effectively optimized by employing the alternating direction multiplier (ADMM) method, and each sub-problem has a corresponding closed solution. In addition, in terms of feature representation, we combine traditional hand-crafted features with deep convolution features linearly enhance the discriminative performance of the filter. Considerable experiments on multiple well-known benchmarks show the proposed algorithm is performs favorably against many state-of-the-art trackers and achieves an AUC score of 64.4% on OTB-100.https://www.mdpi.com/2076-3417/11/18/8427boundary effectsspatial–temporal regularizationdiscriminative correlation filter |
| spellingShingle | Peiting Gu Peizhong Liu Jianhua Deng Zhi Chen Learning Spatial–Temporal Background-Aware Based Tracking Applied Sciences boundary effects spatial–temporal regularization discriminative correlation filter |
| title | Learning Spatial–Temporal Background-Aware Based Tracking |
| title_full | Learning Spatial–Temporal Background-Aware Based Tracking |
| title_fullStr | Learning Spatial–Temporal Background-Aware Based Tracking |
| title_full_unstemmed | Learning Spatial–Temporal Background-Aware Based Tracking |
| title_short | Learning Spatial–Temporal Background-Aware Based Tracking |
| title_sort | learning spatial temporal background aware based tracking |
| topic | boundary effects spatial–temporal regularization discriminative correlation filter |
| url | https://www.mdpi.com/2076-3417/11/18/8427 |
| work_keys_str_mv | AT peitinggu learningspatialtemporalbackgroundawarebasedtracking AT peizhongliu learningspatialtemporalbackgroundawarebasedtracking AT jianhuadeng learningspatialtemporalbackgroundawarebasedtracking AT zhichen learningspatialtemporalbackgroundawarebasedtracking |