[1]刘 洋,杨小军.基于孪生网络特征融合与阈值更新的跟踪算法[J].计算机技术与发展,2022,32(03):65-70.[doi:10. 3969 / j. issn. 1673-629X. 2022. 03. 011]
　LIU Yang,YANG Xiao-jun.Tracking Algorithm Based on Twin Networks Feature Fusion and Threshold Update[J].,2022,32(03):65-70.[doi:10. 3969 / j. issn. 1673-629X. 2022. 03. 011]
点击复制

基于孪生网络特征融合与阈值更新的跟踪算法()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年03期
页码:
65-70
栏目:
图形与图像
出版日期:
2022-03-10

文章信息/Info

Title:
Tracking Algorithm Based on Twin Networks Feature Fusion and Threshold Update
文章编号:
1673-629X(2022)03-0065-06
作者:
刘 洋; 杨小军
长安大学 信息工程学院,陕西 西安 710064
Author(s):
LIU Yang; YANG Xiao-jun
School of Information Engineering,Chang’an University,Xi’an 710064,China
关键词:
MobileNetV2; 特征融合; 注意力; 加权平均; 阈值更新
Keywords:
MobileNetV2; feature fusion; attention; weighted average; threshold update
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 03. 011
摘要:
针对常见的视频目标跟踪过程中由于背景相似干扰、遮挡和形变等一系列问题导致跟踪精度下降的问题,该文提出一种基于孪生网络特征融合与阈值更新的跟踪算法,并引入加权平均模块。 该算法采用 MobileNetV2 作为特征提取网络,借助深度可分离卷积运算,减少模型的参数量,并由深至浅进行多层特征融合,使特征同时具备浅层与深层的信息;模板分支的特征送入注意力机制模块,提高对目标关键特征的关注度;将融合并通过注意力机制后的特征向量的互相关结果与原始提取的特征向量的互相关结果再进行加权平均获得响应图;响应最高位置的相似度与设定阈值比较,判断是否进行模板更新,进一步提高跟踪精度。 实验结果表明,该算法在 OTB100 数据集上能够获得较好的跟踪效果,与现有的一些算法相比展现了更强的鲁棒性。
Abstract:
Aiming at the problem that the tracking accuracy is reduced due to a series of problems such as background similar? interference,occlusion and deformation in common video target tracking process,we propose a tracking algorithm? ? ? based on twin network feature fusion and threshold update and introduce a weighted average module. In this algorithm, MobileNetV2 is used as the feature extraction network. With the help of deep separable convolution operation, the number of model parameters is reduced,and multi-layer feature fusion is performed from deep to shallow, so that? features have shallow and deep information at the same time. The features of the template branch are sent into the attention mechanism module to improve the attention to the key features of the target. The response graph is obtained? by weighted average of the cross-correlation results of the fused and extracted feature vectors and the original extracted feature vectors through the attention mechanism. The similarity of the highest response position is compared with the? ?set threshold value to determine whether to update the template and further improve the tracking accuracy. Experiment shows that the proposed algorithm can achieve better tracking performance on OTC100 data set,and shows stronger robustness compared with some existing algorithms.

相似文献/References:

[1]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15.
　ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(03):15.
[2]黎粤华,单磊,田仲富,等. 基于多特征融合的视频烟雾检测[J].计算机技术与发展,2016,26(01):129.
　LI Yue-hua,SHAN Lei,TIAN Zhong-fu,et al. Video Smoke Detection Based on Multi Feature Fusion Technology[J].,2016,26(03):129.
[3]刘加运,李玉惠,李勃,等. 一种多维特征融合的车辆对象同一性匹配方法[J].计算机技术与发展,2016,26(04):167.
　LIU Jia-yun,LI Yu-hui,LI Bo,et al. A Vehicle Object Identity Matching Method of Multidimensional Feature Combination[J].,2016,26(03):167.
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(03):19.
[5]张雅倩,曾卫明,石玉虎.基于特征融合与稀疏表示的人耳识别[J].计算机技术与发展,2017,27(12):7.
　ZHANG Ya-qian,ZENG Wei-min,SHI Yu-hu.Ear Recognition Based on Feature Fusion and Sparse Representation[J].,2017,27(03):7.
[6]谭程午,夏利民,王 嘉.基于融合特征的群体行为识别[J].计算机技术与发展,2018,28(01):17.[doi:10.3969/ j. issn.1673-629X.2018.01.004]
　TAN Cheng-wu,XIA Li-min,WANG Jia.Recognition of Human Group Action Based on Fusion Features[J].,2018,28(03):17.[doi:10.3969/ j. issn.1673-629X.2018.01.004]
[7]王 敏,陈立潮,曹建芳,等.Hadoop 下自适应随机权值多特征融合图像分类[J].计算机技术与发展,2018,28(11):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
　WANG Min,CHEN Li-chao,CAO Jian-fang,et al.Multi-feature Fusion Image Classification of Adaptive Random Weight Based on Hadoop[J].,2018,28(03):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
[8]韩欣欣,叶奇玲.基于 SIFT 和 HOG 特征融合的人体行为识别方法[J].计算机技术与发展,2019,29(06):71.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 015]
　HAN Xin-xin,YE Qi-ling.Human Action Recognition Based on Feature Fusion of SIFT and HOG[J].,2019,29(03):71.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 015]
[9]宋相法,吕 明.融合三维骨架和深度图像特征的人体行为识别[J].计算机技术与发展,2019,29(07):55.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 011]
　SONG Xiang-fa,LYU Ming.Human Activity Recognition Based on Fusing 3D Skeleton and Depth Image Feature[J].,2019,29(03):55.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 011]
[10]王泽泓,刘厚泉.基于迁移学习与自适应特征融合的建筑物识别[J].计算机技术与发展,2019,29(12):40.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 007]
　WANG Ze-hong,LIU Hou-quan.Building Recognition Based on Transfer Learning and Adaptive Feature Fusion[J].,2019,29(03):40.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 007]

更新日期/Last Update: 2022-03-10