• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Zhang, Qiang (Zhang, Qiang.) | Zhuo, Li (Zhuo, Li.) | Zhang, Shiyu (Zhang, Shiyu.) | Li, Jiafeng (Li, Jiafeng.) | Zhang, Hui (Zhang, Hui.) | Li, Xiaoguang (Li, Xiaoguang.)

收录:

EI Scopus

摘要:

Fine-grained vehicle recognition plays an important part in applications, such as urban traffic management, public security, and criminal investigation. It has great chanllengs due to the subtle differences among numerous subcategories. In this paper, a fine-grained vehicle recognition method using lightweight convolutional neural network with combined learning strategy is proposed. Firstly, a lightweight Convolutional Neural Network (LWCNN) is designed specially for the fine-grained vehicle recognition task. Then, a combined training strategy, including pre-training, fine-tuning training and transfer training, is proposed to optimize the LWCNN parameters. In the pre-training phase, ILSVRC-2012 dataset is adopted to train the VGG16-Net, generating an initial model. Then, in the fine-tuning phase, the vehicle dataset is used for fine-tuning the pre-trained model to avoid learning parameters from scratch. Finally, in the transfer training phase, appropriate initialization parameters of LWCNN are obtained through the analysis of the fine-tuned network parameters. LWCNN is then trained using the vehicle dataset to obtain the highly accurate and robust classification model. Compared with the state-of-the-art methods, the proposed method can effectively decrease the computational complexity while maintaining the recognition performance. © 2018 IEEE.

关键词:

Big data Classification (of information) Convolution Convolutional neural networks Deep learning Deep neural networks Learning systems Traffic control Transfer learning Vehicles

作者机构:

  • [ 1 ] [Zhang, Qiang]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, China
  • [ 2 ] [Zhang, Qiang]College of Microelectronics, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 3 ] [Zhuo, Li]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, China
  • [ 4 ] [Zhuo, Li]College of Microelectronics, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 5 ] [Zhang, Shiyu]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, China
  • [ 6 ] [Zhang, Shiyu]College of Microelectronics, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 7 ] [Li, Jiafeng]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, China
  • [ 8 ] [Li, Jiafeng]College of Microelectronics, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 9 ] [Zhang, Hui]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, China
  • [ 10 ] [Zhang, Hui]College of Microelectronics, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 11 ] [Li, Xiaoguang]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, China
  • [ 12 ] [Li, Xiaoguang]College of Microelectronics, Faculty of Information Technology, Beijing University of Technology, Beijing, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2018

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 14

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

在线人数/总访问数:690/3579636
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司