计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1573-1580.DOI: 10.11772/j.issn.1001-9081.2020121915

所属专题: 2020年全国开放式分布与并行计算学术年会(DPCS 2020)

• 2020年全国开放式分布与并行计算学术年会(DPCS 2020) • 上一篇    下一篇

基于多尺度特征提取的交通模式识别算法

刘世泽1, 秦艳君2, 王晨星2, 高存远2, 罗海勇3, 赵方2, 王宝会1   

  1. 1. 北京航空航天大学 软件学院, 北京 100191;
    2. 北京邮电大学 计算机学院, 北京 100876;
    3. 中国科学院 计算技术研究所, 北京 100190
  • 收稿日期:2020-11-04 修回日期:2021-04-02 出版日期:2021-06-10 发布日期:2021-06-21
  • 通讯作者: 罗海勇
  • 作者简介:刘世泽(1988-),男,辽宁抚顺人,硕士,主要研究方向:大数据挖掘、智能感知;秦艳君(1991-),女,山西长治人,博士研究生,CCF会员,主要研究方向:城市计算、交通模式识别;王晨星(1997-),男,河北衡水人,硕士研究生,主要研究方向:城市计算、交通模式识别、交通流预测;高存远(2000-),男,云南昆明人,主要研究方向:城市计算、交通模式识别;罗海勇(1967-),男,湖北麻城人,副研究员,博士,CCF会员,主要研究方向:移动智能、普适计算;赵方(1968-),女,河南开封人,教授,博士,CCF会员,主要研究方向:移动互联网、大数据挖掘;王宝会(1973-),男,江苏滨海人,教授级高级工程师,硕士,主要研究方向:软件工程。
  • 基金资助:
    国家自然科学基金资助项目(61872046);北京邮电大学提升科技创新能力行动计划项目(2019XD-A06)。

Transportation mode recognition algorithm based on multi-scale feature extraction

LIU Shize1, QIN Yanjun2, WANG Chenxing2, GAO Cunyuan2, LUO Haiyong3, ZHAO Fang2, WANG Baohui1   

  1. 1. College of Software, Beihang University, Beijing 100191, China;
    2. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;
    3. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  • Received:2020-11-04 Revised:2021-04-02 Online:2021-06-10 Published:2021-06-21
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61872046), the Scientific and Technological Innovation Ability Improvement Action Program of Beijing University of Posts and Telecommunications (2019XD-A06).

摘要: 针对普适交通模式的场景感知功耗高、场景复杂的问题,提出一种融合残差网络(ResNet)和带孔卷积的交通模式识别算法。首先,使用快速傅里叶变换(FFT)将一维传感器数据转换为二维频谱图像;然后,使用主成分分析(PCA)算法对频谱图像降采样;最后,使用ResNet挖掘交通模式的局部特征,使用带孔卷积挖掘交通模式的全局特征,从而实现对八种交通模式进行识别。与决策树、随机森林、AlexNet等八种算法在实验中的对比评估结果显示,融合ResNet和带孔卷积的交通模式识别算法在静止、走路、跑步等八类交通模式上均有最高准确率。该算法具有良好识别精度和鲁棒性。

关键词: 行为识别, 交通模式识别, 残差网络, 带孔卷积, 低功耗

Abstract: Aiming at the problems of high power consumption and complex scene for scene perception in universal transportation modes, a new transportation mode detection algorithm combining Residual Network (ResNet) and dilated convolution was proposed. Firstly, the 1D sensor data was converted into the 2D spectral image by using Fast Fourier Transform (FFT). Then, the Principal Component Analysis (PCA) algorithm was used to realize the downsampling of the spectral image. Finally, the ResNet was used to mine the local features of transportation modes, and the global features of transportation modes were mined with dilated convolution, so as to detect eight transportation modes. Experimental evaluation results show that, compared with 8 algorithms including decision tree, random forest and AlexNet, the transportation mode recognition algorithm combining ResNet and dilated convolution has the highest accuracy in eight traffic patterns including static, walking and running, and the proposed algorithm has good identification accuracy and robustness.

Key words: activity recognition, transportation mode recognition, Residual Network (ResNet), dilated convolution, low power consumption

中图分类号: