摘要
当前的一阶段回归网络可以通过多分支响应图的融合获得多级信息。然而,现有算法的响应图融合方法主要是基于简单的逐元素相加或相乘运算。基于此,提出一种新的跟踪模型,该模型集成了基于双线性卷积神经网络的新型响应图融合方法,可以获得响应图的位置关联和信息交互,利于更准确地跟踪目标物体。基于OTB2013基准数据库对本文算法进行测试,结果表明,与一流的跟踪算法相比,本文算法已经取得了比较有竞争力的结果。
The existing one-stage regression networks can obtain the multi-level information through the fusion of multi-branch response maps.However,the algorithms for response map fusion are mostly based on a simple element-wise sum or a multiplication operation.In this paper,a novel tracking model that includes a novel response map fusion method based on bilinear convolutional neural network,is proposed.The proposed model can obtain position correlation and information interaction of response maps,which is useful for achieving more accurate target tracking.The proposed algorithm is tested on the OTB2013 benchmark.Results show that,a competitive performance can be achieved by using the proposed model,compared to the state-of-arts tracking models.
作者
张春婷
Zhang Chunting(School of Electronics and Information Engineering,Tianjin University,Tianjin 300072,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第4期231-237,共7页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61701341)。
关键词
机器视觉
目标跟踪
回归框架
响应图融合
双线性卷积神经网络
machine vision
object tracking
regression framework
response map fusion
bilinear convolutional neural network
