HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter
In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-le...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/2137 |
| _version_ | 1797570995445301248 |
|---|---|
| author | Chenpu Li Qianjian Xing Zhenguo Ma |
| author_facet | Chenpu Li Qianjian Xing Zhenguo Ma |
| author_sort | Chenpu Li |
| collection | DOAJ |
| description | In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers. |
| first_indexed | 2024-03-10T20:33:18Z |
| format | Article |
| id | doaj.art-c0715e55eed84c4b80de52f95475cba1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:33:18Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c0715e55eed84c4b80de52f95475cba12023-11-19T21:14:45ZengMDPI AGSensors1424-82202020-04-01207213710.3390/s20072137HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman FilterChenpu Li0Qianjian Xing1Zhenguo Ma2College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou 310027, ChinaCollege of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou 310027, ChinaCollege of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou 310027, ChinaIn the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.https://www.mdpi.com/1424-8220/20/7/2137visual trackingStapleSiamFCKalman filter |
| spellingShingle | Chenpu Li Qianjian Xing Zhenguo Ma HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter Sensors visual tracking Staple SiamFC Kalman filter |
| title | HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter |
| title_full | HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter |
| title_fullStr | HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter |
| title_full_unstemmed | HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter |
| title_short | HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter |
| title_sort | hksiamfc visual tracking framework using prior information provided by staple and kalman filter |
| topic | visual tracking Staple SiamFC Kalman filter |
| url | https://www.mdpi.com/1424-8220/20/7/2137 |
| work_keys_str_mv | AT chenpuli hksiamfcvisualtrackingframeworkusingpriorinformationprovidedbystapleandkalmanfilter AT qianjianxing hksiamfcvisualtrackingframeworkusingpriorinformationprovidedbystapleandkalmanfilter AT zhenguoma hksiamfcvisualtrackingframeworkusingpriorinformationprovidedbystapleandkalmanfilter |