A Robust and Accurate Object Tracking Algorithm Based on Convolutional Neural Network

LI Kang; LI Ya-min; HU Xue-min; SHAO Fang

doi:10.3969/j.issn.0372-2112.2018.09.007

您当前的位置：

首页 >

文章列表页 >

A Robust and Accurate Object Tracking Algorithm Based on Convolutional Neural Network

更新时间：2025-07-16

- A Robust and Accurate Object Tracking Algorithm Based on Convolutional Neural Network
- Acta Electronica Sinica Vol. 46, Issue 9, Pages: 2087-2093(2018)
- 作者机构：
  
  湖北大学计算机与信息工程学院,湖北,武汉,430062
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2018.09.007
  CLC： TP391.41
- Published Online：25 September 2018，
  
  Published：2018
- 稿件说明：
移动端阅览
LI Kang, LI Ya-min, HU Xue-min, et al. A Robust and Accurate Object Tracking Algorithm Based on Convolutional Neural Network[J]. Acta Electronica Sinica, 2018, 46(9): 2087-2093.
DOI：

LI Kang, LI Ya-min, HU Xue-min, et al. A Robust and Accurate Object Tracking Algorithm Based on Convolutional Neural Network[J]. Acta Electronica Sinica, 2018, 46(9): 2087-2093. DOI： 10.3969/j.issn.0372-2112.2018.09.007.

摘要

目标跟踪是计算机视觉中重要的研究领域之一.为了跟踪复杂场景中外观变化剧烈的目标，本文提出了一种基于卷积神经网络的目标跟踪算法.算法中的网络模型结构包括预训练的特征提取层和自适应更新的分类器层.在开始跟踪前，首先训练全连接层和分类器层的参数，以及目标的特征与位置之间的线性关系.其次，定义了评估跟踪结果可信度的标准.如果得到的跟踪结果的可信度较高，则根据跟踪结果的特征调整位置，提高跟踪结果的精确度.最后，在训练网络时，每次迭代都选择分类器得分的最高的负样本参与训练.该策略可以提高模型的分辨能力.在OTB50测试集中的实验结果表明，我们的算法取得了良好的跟踪结果.

Abstract

Object tracking is one of the most important area of computer vision. In order to track the object whose appearance changes dramatically in complex scene

we propose a tracking algorithm based on the convolutional neural network. The network of our tracker has two parts: the feature extraction layer and the adaptive classifier layer. At the beginning

we train a fully-connected layer

a softmax layer and the linear relationship between feature and position of these samples. Next

we define a reliability of the tracking result. If the result is reliable

we will adjust the result location according to its features. Finally

in the network training process

we select the negative samples with max classifying scores in each iteration. The strategy could improve distinguishability of our tracker. Experiments on OTB50 show that our tracker could achieve state-of-the-art performance.

关键词

Keywords

references

Views

871

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Visual Object Tracking Algorithm Based on Adaptive Feature Selection

Neural Network Based Image Style Transfer: A Survey

DRHA-UIE: An Underwater Image Enhancement Method Based on Dual Residual Hybrid Attention Block

Evaluation of the Effect of Neural Network Training Tricks on the Performance of High-Resolution Remote Sensing Image Scene Classification

Related Author

WANG Cai-xia

AN Qi

ZHOU Hong-ce

LI Yi-peng

WANG Wei

ZHANG Jing-yi

WEN Yu-hui

WEI Yun-chao

Related Institution

School of Electronic Information and Engineering, Changchun University of Science and Technology

Jilin Province Technology Research Center of Photoelectric Detection and Intelligent Information Processing

School of Computer Science and Technology, Beijing Jiaotong University

College of Computer Science and Technology， Jilin University

School of Information Engineering, North China University of Water Resources and Electric Power

⁰