摘要
为提高全卷积孪生网络(SiamFC)跟踪器在复杂场景下的跟踪能力,缓解跟踪器在跟踪过程中出现的目标漂移问题,提出一种结合空间注意力机制的实时目标跟踪算法。在SiamFC框架基础上,将改进的视觉几何组(VGG)网络作为主干网络,增强跟踪器对于目标深度特征的建模能力。对自注意力机制进行优化,提出一种即插即用的轻量级单卷积注意力模块(SCAM),将空间注意力分解为2个并行的一维特征编码过程,减少空间注意力的计算复杂度。保留跟踪过程中的初始目标模板作为第1模板,通过分析连通域在跟踪结果响应图的变化动态选择第2模板,融合2个模板后对目标进行定位。实验结果表明:在OTB100、LaSOT和UAV123数据集上,所提算法相比于SiamFC跟踪成功率分别提高了0.082、0.045和0.045,跟踪精度分别提高了0.118、0.051和0.062;在VOT2018数据集上,所提算法相比于SiamFC在跟踪准确率、鲁棒性和期望平均重叠率上分别提高了0.029、0.276和0.134;跟踪速度达到了70帧/s,能够满足实时跟踪的需求。
A real-time object tracking method coupled with a spatial attention mechanism is suggested in order to enhance the fully convolutional Siamese network(SiamFC)tracker’s tracking capability in complex settings and alleviate the target drift problem in the tracking process.The improved visual geometry group(VGG)network is used as the backbone network to enhance the modeling ability of the tracker for the target deep feature.The self-attention mechanism is optimized,and a lightweight single convolution attention module(SCAM)is proposed.The spatial attention is decomposed into two parallel one-dimensional feature coding processes to reduce the computational complexity of spatial attention.The initial target template in the tracking process is retained as the first template,and the second template is dynamically selected by analyzing the variation of the connected domain in the tracking response map.The target is located after fusing the two templates.The experimental results show that,compared with SiamFC,the success rate of the proposed algorithm on OTB100,LaSOT,and UAV123 datasets is increased respectively by 0.082,0.045,and 0.045,and the tracking accuracy by 0.118,0.051,and 0.062.On the VOT2018 dataset,the proposed algorithm improves the tracking accuracy,robustness,and expected average overlap by 0.029,0.276,and 0.134,respectively,compared with SiamFC.Real-time tracking requirements can be satisfied by the tracking speed,which can approach 70 frames per second.
作者
马素刚
张子贤
蒲磊
侯志强
MA Sugang;ZHANG Zixian;PU Lei;HOU Zhiqiang(School of Computer Science and Technology,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;School of Information Engineering,Chang’an University,Xi’an 710064,China;School of Operational Support,Rocket Force Engineering University,Xi’an 710025,China;Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing,Xi’an University of Posts and Telecommunications,Xi’an 710121,China)
出处
《北京航空航天大学学报》
EI
CAS
CSCD
北大核心
2024年第2期419-432,共14页
Journal of Beijing University of Aeronautics and Astronautics
基金
国家自然科学基金(62072370)
陕西省重点研发计划(2018ZDCXL-GY-04-02)
西安邮电大学研究生创新基金(CXJJZL2021011)。
关键词
目标跟踪
孪生网络
注意力机制
模板更新
深度学习
object tracking
Siamese network
attention mechanism
model update
deep learning
