###
计算机系统应用:2020,29(1):184-189
本文二维码信息
码上扫一扫!
基于细节提取的运动目标追踪算法
(1.福建师范大学 光电与信息工程学院, 福州 350007;2.福建师范大学 医学光电科学与技术教育部重点实验室, 福州 350007;3.福建师范大学 福建省光子技术重点实验室, 福州 350007;4.福建师范大学 福建省光电传感应用工程技术研究中心, 福州 350007)
Moving Target Tracking Algorithm Based on Detail Extraction
(1.College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China;2.Key Laboratory of Optoelectronic Science and Technology for Medicine (Ministry of Education), Fujian Normal University, Fuzhou 350007, China;3.Fujian Provincial Key Laboratory of Photonics Technology, Fujian Normal University, Fuzhou 350007, China;4.Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application, Fujian Normal University, Fuzhou 350007, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 432次   下载 264
投稿时间:2019-06-19    修订日期:2019-07-16
中文摘要: 目前运动目标追踪任务中干扰具有很大的欺骗性,目标追踪算法容易被带有陷阱的数据集所欺骗.为了提升追踪算法在追踪数据集上的效果,本文提出基于SiamFC孪生网络上改进的DPP-SiamFC追踪算法,该算法在原网络基础上引入DPP (Detail-Perserving Pooling)池化层和残差网络,有效的保留目标的细节特征.本文并在VOT2017追踪数据集上验证网络性能,实验结果达到了网络性能提升的效果.
Abstract:At present, the interference in the moving target tracking task is very deceptive, and the target tracking algorithm is easily deceived by the data set with traps. In order to improve the tracking algorithm's effect on tracking dataset, this study proposes an improved DPP-SiamFC tracking algorithm based on SiamFC twinning network. This algorithm introduces DPP (Detail-Perserving Pooling) pooling layer and residual network based on the original network, effectively retaining the details of the target. This study also verifies network performance on the VOT2017 tracking dataset, the experimental results have achieved the goal of improving network performance.
文章编号:7242     中图分类号:    文献标志码:
基金项目:福建省自然科学基金(2017J01744)
引用文本:
李科,蔡坚勇,张明伟,卢依宏,曾远强.基于细节提取的运动目标追踪算法.计算机系统应用,2020,29(1):184-189
LI Ke,CAI Jian-Yong,ZHANG Ming-Wei,LU Yi-Hong,ZENG Yuan-Qiang.Moving Target Tracking Algorithm Based on Detail Extraction.COMPUTER SYSTEMS APPLICATIONS,2020,29(1):184-189

用微信扫一扫

用微信扫一扫