Attention-mechanism-based tracking method for intelligent Internet of vehicles
Attention-mechanism-based tracking method for intelligent Internet of vehicles
复制标题
基于注意力机制的智能车联网跟踪方法
DOI：
10.1177/1550147718805946
复制
发表时间：
2018-10
影响因子：
2.3
通讯作者：
Guizani Mohsen
中科院分区：
文献类型：
--
作者：
Kang Xu;Song Bin;Guo Jie;Du Xiaojiang;Guizani Mohsen
车辆跟踪任务在车联网和智能交通系统中起着重要的作用。除了传统的全球定位系统传感器之外，图像传感器还可以捕获不同类型的车辆，分析其驾驶情况，并与它们进行交互。针对传统卷积神经网络易受背景干扰的问题，提出了一种基于人的注意力机制的车辆跟踪方法，该方法采用通道间全连接层自选择深度特征。主要包括以下内容：（1）一种全卷积神经网络融合注意力机制，选择深度特征进行卷积;（2）一种模板和语义背景区域分离方法，在初始帧中自适应地将目标车辆从背景中分离出来;（3）一种基于我们的交通数据集的两阶段模型训练方法。实验结果表明，该方法在不增加跟踪时间的情况下，提高了跟踪精度。同时，增强了算法在复杂背景区域条件下的鲁棒性.该方法在总体流量数据集上的成功率比Siamese网络高出约10%，总体精度比Siamese网络高出8%。
Vehicle tracking task plays an important role on the Internet of vehicles and intelligent transportation system. Beyond the traditional Global Positioning System sensor, the image sensor can capture different kinds of vehicles, analyze their driving situation, and can interact with them. Aiming at the problem that the traditional convolutional neural network is vulnerable to background interference, this article proposes vehicle tracking method based on human attention mechanism for self-selection of deep features with an inter-channel fully connected layer. It mainly includes the following contents: (1) a fully convolutional neural network fused attention mechanism with the selection of the deep features for convolution; (2) a separation method for template and semantic background region to separate target vehicles from the background in the initial frame adaptively; (3) a two-stage method for model training using our traffic dataset. The experimental results show that the proposed method improves the tracking accuracy without an increase in tracking time. Meanwhile, it strengthens the robustness of algorithm under the condition of the complex background region. The success rate of the proposed method in overall traffic datasets is higher than Siamese network by about 10%, and the overall precision is higher than Siamese network by 8%.
登录
查看更多内容
DOI：
10.1109/icme.2017.8019422
发表时间：
2017-07
期刊：
2017 IEEE International Conference on Multimedia and Expo (ICME)
影响因子：
--
作者：
Qiurui Wang;C. Yuan;Zhihui Lin
通讯作者：
Qiurui Wang;C. Yuan;Zhihui Lin
DOI：
--
发表时间：
2016-06
期刊：
ArXiv
影响因子：
--
作者：
P. H. Seo;Zhe L. Lin;Scott D. Cohen;Xiaohui Shen;Bohyung Han
通讯作者：
P. H. Seo;Zhe L. Lin;Scott D. Cohen;Xiaohui Shen;Bohyung Han
一劳永逸：用于视觉跟踪的两流卷积神经网络
DOI：
10.1109/tcsvt.2017.2757061
发表时间：
2018-12-01
影响因子：
8.4
作者：
Chen, Kai;Tao, Wenbing
通讯作者：
Tao, Wenbing
DOI：
10.1109/icinfa.2016.7832119
发表时间：
2016-08
期刊：
2016 IEEE International Conference on Information and Automation (ICIA)
影响因子：
--
作者：
Mingqiang Lin;Houde Dai
通讯作者：
Mingqiang Lin;Houde Dai
DOI：
10.1109/iccv.2017.592
发表时间：
2017-12
期刊：
2017 IEEE International Conference on Computer Vision (ICCV)
影响因子：
--
作者：
Jifei Song;Qian Yu;Yi-Zhe Song;T. Xiang;Timothy M. Hospedales
通讯作者：
Jifei Song;Qian Yu;Yi-Zhe Song;T. Xiang;Timothy M. Hospedales