Object tracking using a convolutional network and a structured output SVM
Abstract Object tracking has been a challenge in computer vision. In this paper, we present a novel method to model target appearance and combine it with structured output learning for robust online tracking within a tracking-by-detection framework. We take both convolutional features and handcrafte...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-06-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41095-017-0087-3 |
| _version_ | 1819139095811588096 |
|---|---|
| author | Junwei Li Xiaolong Zhou Sixian Chan Shengyong Chen |
| author_facet | Junwei Li Xiaolong Zhou Sixian Chan Shengyong Chen |
| author_sort | Junwei Li |
| collection | DOAJ |
| description | Abstract Object tracking has been a challenge in computer vision. In this paper, we present a novel method to model target appearance and combine it with structured output learning for robust online tracking within a tracking-by-detection framework. We take both convolutional features and handcrafted features into account to robustly encode the target appearance. First, we extract convolutional features of the target by kernels generated from the initial annotated frame. To capture appearance variation during tracking, we propose a new strategy to update the target and background kernel pool. Secondly, we employ a structured output SVM for refining the target’s location to mitigate uncertainty in labeling samples as positive or negative. Compared with existing state-of-the-art trackers, our tracking method not only enhances the robustness of the feature representation, but also uses structured output prediction to avoid relying on heuristic intermediate steps to produce labelled binary samples. Extensive experimental evaluation on the challenging OTB-50 video sequences shows competitive results in terms of both success and precision rate, demonstrating the merits of the proposed tracking method. |
| first_indexed | 2024-12-22T11:17:13Z |
| format | Article |
| id | doaj.art-f1b2cceee62d44e1a2d2b6089ee39f53 |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-12-22T11:17:13Z |
| publishDate | 2017-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-f1b2cceee62d44e1a2d2b6089ee39f532022-12-21T18:27:59ZengSpringerOpenComputational Visual Media2096-04332096-06622017-06-013432533510.1007/s41095-017-0087-3Object tracking using a convolutional network and a structured output SVMJunwei Li0Xiaolong Zhou1Sixian Chan2Shengyong Chen3Zhejiang University of TechnologyZhejiang University of TechnologyZhejiang University of TechnologyTianjin University of TechnologyAbstract Object tracking has been a challenge in computer vision. In this paper, we present a novel method to model target appearance and combine it with structured output learning for robust online tracking within a tracking-by-detection framework. We take both convolutional features and handcrafted features into account to robustly encode the target appearance. First, we extract convolutional features of the target by kernels generated from the initial annotated frame. To capture appearance variation during tracking, we propose a new strategy to update the target and background kernel pool. Secondly, we employ a structured output SVM for refining the target’s location to mitigate uncertainty in labeling samples as positive or negative. Compared with existing state-of-the-art trackers, our tracking method not only enhances the robustness of the feature representation, but also uses structured output prediction to avoid relying on heuristic intermediate steps to produce labelled binary samples. Extensive experimental evaluation on the challenging OTB-50 video sequences shows competitive results in terms of both success and precision rate, demonstrating the merits of the proposed tracking method.http://link.springer.com/article/10.1007/s41095-017-0087-3object trackingconvolutional networkstructured learningfeature extraction |
| spellingShingle | Junwei Li Xiaolong Zhou Sixian Chan Shengyong Chen Object tracking using a convolutional network and a structured output SVM Computational Visual Media object tracking convolutional network structured learning feature extraction |
| title | Object tracking using a convolutional network and a structured output SVM |
| title_full | Object tracking using a convolutional network and a structured output SVM |
| title_fullStr | Object tracking using a convolutional network and a structured output SVM |
| title_full_unstemmed | Object tracking using a convolutional network and a structured output SVM |
| title_short | Object tracking using a convolutional network and a structured output SVM |
| title_sort | object tracking using a convolutional network and a structured output svm |
| topic | object tracking convolutional network structured learning feature extraction |
| url | http://link.springer.com/article/10.1007/s41095-017-0087-3 |
| work_keys_str_mv | AT junweili objecttrackingusingaconvolutionalnetworkandastructuredoutputsvm AT xiaolongzhou objecttrackingusingaconvolutionalnetworkandastructuredoutputsvm AT sixianchan objecttrackingusingaconvolutionalnetworkandastructuredoutputsvm AT shengyongchen objecttrackingusingaconvolutionalnetworkandastructuredoutputsvm |