<abstract xmlns="http://www.w3.org/1999/xhtml"><p> In order to improve the performance of tracking, we propose a new online tracking method based on classification and adaptive fused feature. We first label a few positive and negative samples, train the classifier by the online SSSM (Semi-Supervised Support Vector Machine) learning and these labelled samples, and then locate the position of the object from the next frame according to the trained classifier. In order to adapt more of the new samples, we need to update the classifier by finding new samples with high confident value obtained by the trained classifier and add them into the online SSSM. Finally we also update the object model by the online incremental PCA (Principal Component Analysis) because of background clutter, heavy occlusion and complicated object appearance changes. Compared with the basic mean shift tracking and the ensemble tracking method, experimental results show that our tracking method is able to effectively handle heavy occlusion and background clutter in some challenge videos including some thermal videos.</p></abstract>

In order to improve the performance of tracking, we propose a new online tracking method based on classification and adaptive fused feature. We first label a few positive and negative samples, train the classifier by the online SSSM (Semi-Supervised Support Vector Machine) learning and these labelled samples, and then locate the position of the object from the next frame according to the trained classifier. In order to adapt more of the new samples, we need to update the classifier by finding new samples with high confident value obtained by the trained classifier and add them into the online SSSM. Finally we also update the object model by the online incremental PCA (Principal Component Analysis) because of background clutter, heavy occlusion and complicated object appearance changes. Compared with the basic mean shift tracking and the ensemble tracking method, experimental results show that our tracking method is able to effectively handle heavy occlusion and background clutter in some challenge videos including some thermal videos.

Object Tracking Based on Online Semi-Supervised SVM and Adaptive-Fused Feature

College of Optoelectronic Engineering, Changzhou Institute of Technology, 213002 China

Changzhou Institute of Modern Optical Technology, 213002 China

Changzhou Key Laboratory of Optoelectronic Materials and Devices, 213002 China

Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education, Chongqing University, Chongqing, 400044 China

Cybernetics and Information Technologies

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Object Tracking Based on Online Semi-Supervised SVM and Adaptive-Fused Feature"}

In order to improve the performance of tracking, we propose a new online tracking method based on classification and adaptive fused feature. We first label a...

Object Tracking Based on Online Semi-Supervised SVM and Adaptive-Fused Feature

Data publikacji: 22 cze 2016

Zakres stron: 198 - 211

DOI: https://doi.org/10.1515/cait-2016-0030

Słowa kluczowe
Visual tracking, SSSM, feature fusion, incremental PCA，online

© by Xifang Zhu

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Object Tracking Based on Online Semi-Supervised SVM and Adaptive-Fused Feature

Data publikacji: 22 cze 2016

Zakres stron: 198 - 211

DOI: https://doi.org/10.1515/cait-2016-0030

Słowa kluczoweVisual tracking, SSSM, feature fusion, incremental PCA，online

© by Xifang Zhu

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Słowa kluczowe
Visual tracking, SSSM, feature fusion, incremental PCA，online