A Fast Object Tracker Based on Integrated Multiple Features and Dynamic Learning Rate

المؤلفون المشاركون

Li, Feng
Zhang, Jianming
Wang, Jin
Wu, You
Jin, Xiaokang

المصدر

Mathematical Problems in Engineering

العدد

المجلد 2018، العدد 2018 (31 ديسمبر/كانون الأول 2018)، ص ص. 1-14، 14ص.

الناشر

Hindawi Publishing Corporation

تاريخ النشر

2018-12-24

دولة النشر

مصر

عدد الصفحات

14

التخصصات الرئيسية

هندسة مدنية

الملخص EN

Object tracking is a vital topic in computer vision.

Although tracking algorithms have gained great development in recent years, its robustness and accuracy still need to be improved.

In this paper, to overcome single feature with poor representation ability in a complex image sequence, we put forward a multifeature integration framework, including the gray features, Histogram of Gradient (HOG), color-naming (CN), and Illumination Invariant Features (IIF), which effectively improve the robustness of object tracking.

In addition, we propose a model updating strategy and introduce a skewness to measure the confidence degree of tracking result.

Unlike previous tracking algorithms, we judge the relationship of skewness values between two adjacent frames to decide the updating of target appearance model to use a dynamic learning rate.

This way makes our tracker further improve the robustness of tracking and effectively prevents the target drifting caused by occlusion and deformation.

Extensive experiments on large-scale benchmark containing 50 image sequences show that our tracker is better than most existing excellent trackers in tracking performance and can run at average speed over 43 fps.

نمط استشهاد جمعية علماء النفس الأمريكية (APA)

Zhang, Jianming& Wu, You& Jin, Xiaokang& Li, Feng& Wang, Jin. 2018. A Fast Object Tracker Based on Integrated Multiple Features and Dynamic Learning Rate. Mathematical Problems in Engineering،Vol. 2018, no. 2018, pp.1-14.
https://search.emarefa.net/detail/BIM-1208148

نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)

Zhang, Jianming…[et al.]. A Fast Object Tracker Based on Integrated Multiple Features and Dynamic Learning Rate. Mathematical Problems in Engineering No. 2018 (2018), pp.1-14.
https://search.emarefa.net/detail/BIM-1208148

نمط استشهاد الجمعية الطبية الأمريكية (AMA)

Zhang, Jianming& Wu, You& Jin, Xiaokang& Li, Feng& Wang, Jin. A Fast Object Tracker Based on Integrated Multiple Features and Dynamic Learning Rate. Mathematical Problems in Engineering. 2018. Vol. 2018, no. 2018, pp.1-14.
https://search.emarefa.net/detail/BIM-1208148

نوع البيانات

مقالات

لغة النص

الإنجليزية

الملاحظات

Includes bibliographical references

رقم السجل

BIM-1208148