跳到主要导航 跳到搜索 跳到主要内容

Detecting unsafe driving patterns using discriminative learning

  • Zhou Yue
  • , Xu Wei
  • , Ning Huazhong
  • , Gong Yihong
  • , Thomas S. Huang
  • University of Illinois at Urbana-Champaign
  • INEC Laboratories America, Inc.

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

14 引用 (Scopus)

摘要

We propose a discriminative learning approach for fusing multichannel sequential data with application to detect unsafe driving patterns from multi-channel driving recording data. The fusion is performed using a discriminatively trained graphical model - conditional random field (CRF). The proposed approach offers several advantage over existing information fusing approaches. First, it derives its classification power by directly modelling and maximizing the conditional probability. Second, it represents the variable dependency in an undirected graph, which is very efficient in inference. Third, it does not require to label all the training data and utilizes both labelled and unlabelled data efficiently by semi-supervised learning algorithms. The proposed approach is evaluated on driving recording data collected from driving simulator - STISIM. Experiments show it outperforms the simple discriminative classifier (SVM) and generative model (HMM).

源语言英语
主期刊名Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
页1431-1434
页数4
出版状态已出版 - 2007
已对外发布是
活动IEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, 中国
期限: 2 7月 2007 → 5 7月 2007

丛书

姓名Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

会议

会议IEEE International Conference onMultimedia and Expo, ICME 2007
国家/地区中国
市Beijing
时期2/07/07 → 5/07/07

学术指纹

探究 'Detecting unsafe driving patterns using discriminative learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此