Distractor-Aware Object Tracking Based on Multi-Feature Fusion and Scale-Adaption

被引：0

作者：

Li S. ^{[1
]}

Zhao G. ^{[1
]}

Wang J. ^{[1
]}

机构：

[1] School of Automation, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu

来源：

Zhao, Gaopeng (zhaogaopeng@njust.edu.cn) | 1600年 / Chinese Optical Society卷 / 37期

关键词：

Distractor awareness; Machine vision; Multi-feature fusion; Object tracking; Scale adaption;

D O I：

10.3788/AOS201737.0515005

中图分类号：

学科分类号：

摘要：

Aiming at the tracking drift problem caused by the RGB feature, similar appearance and scale change in complex scenes, an improved method of distractor-aware object tracking based on multi-feature fusion and scale-adaption is proposed. Firstly, the distractor-aware object models are established base on the RGB feature and the modified (histogram of oriented gradient) HOG feature, which are extracted from object, surrounding background, and distractors. Secondly, the candidates are extracted by dense sampling in likelihood maps, which are obtained by calculating every pixel in the search region. The locations of the target and the distractor are obtained by vote score and distance score, also the model updating method is given. The RGB feature is extracted to establish a model scale, and the multi-scale feature pyramid method is used to get templates at different scales. The optimal scale is obtained by comparison between the model scale and the template scales. The experimental results indicate that the proposed algorithm can well adapt to environmental variation including distractors, partially blocking and scale variation and outperforms the compared tracking methods in terms of the distance precision and overlap precision. © 2017, Chinese Lasers Press. All right reserved.

引用

共 21 条

[1]

Zhang H., Hu S., Yang G., Video object tracking based on appearance models learning, Journal of Computer Research and Development, 52, 1, pp. 177-190, (2015)

[2]

Yin H., Chen B., Chai Y., Et al., Vision-based object detection and tracking: A review, Acta Automatica Sinica, 42, 10, pp. 1466-1489, (2016)

[3]

Zhang L., Wang Y., Sun H., Et al., Adaptive scale object tracking with kernelized correlation filters, Optics and Precision Engineering, 24, 2, pp. 448-459, (2016)

[4]

Yang X., Fei S., Li G., Et al., Improved mean shift tracking algorithm based on complicated feature fusion, Control and Decision, 29, 7, pp. 1297-1300, (2014)

[5]

Sun R., Huang J., Ding W., A real-time object tracking algorithm based on subspace learning, Opto-Electronic Engineering, 42, 2, pp. 52-58, (2015)

[6]

Liu W., Yuan G., Xue M., Robust fast visual tracking based on two-stage representation, Acta Optica Sinica, 36, 12, (2016)

[7]

Zhang X., Chen Z., Hu L., Et al., Object tracking method based on sparse representation of joint template, Control and Decision, 30, 9, pp. 1696-1700, (2015)

[8]

Wang Y., Chen H., Li S., Et al., Online boosting tracking algorithm combined with occlusion sensing, Journal on Communications, 37, 9, (2016)

[9]

Hu Z., Xu Y., Zhao X., Et al., Multi-feature selection tracking based on support vector machine, Journal of Applied Sciences, 33, 5, pp. 502-517, (2015)

[10]

Liu K., Dai P., Jiang X., Et al., Object tracking algorithm based on ranking support vector machine fused with multiple features, Computer Engineering, 40, 11, pp. 42-45, (2014)

← 1 2 3 →