...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Optical engineering >Unsupervised video-based lane detection using location-enhanced topic models
【24h】

Unsupervised video-based lane detection using location-enhanced topic models

机译：使用位置增强主题模型的基于视频的无监督车道检测

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

An unsupervised learning algorithm based on topic models is presented for lane detection in video sequences observed by uncali-brated moving cameras. Our contributions are twofold. First, we introduce the maximally stable extremal region (MSER) detector for lane-marking feature extraction and derive a novel shape descriptor in an affine invariant manner to describe region shapes and a modified scale-invariant feature transform descriptor to capture feature appearance characteristics. MSER features are more stable compared to edge points or line pairs and hence provide robustness to lane-marking variations in scale, lighting, viewpoint, and shadows. Second, we proposed a novel location-enhanced probabilistic latent semantic analysis (pLSA) topic model for simultaneous lane recognition and localization. The proposed model overcomes the limitation of a pLSA model for effective topic localization. Experimental results on traffic sequences in various scenarios demonstrate the effectiveness and robustness Of the proposed method.
机译：提出了一种基于主题模型的无监督学习算法，用于在未经校准的移动摄像机观察到的视频序列中进行车道检测。我们的贡献是双重的。首先，我们引入用于车道标记特征提取的最大稳定极值区域（MSER）检测器，并以仿射不变的方式派生出新颖的形状描述符以描述区域形状，并使用改进的尺度不变的特征变换描述符来捕获特征外观特征。与边缘点或线对相比，MSER功能更稳定，因此可为刻度，照明，视点和阴影中的车道标记变化提供鲁棒性。其次，我们提出了一种新颖的位置增强概率潜在语义分析（pLSA）主题模型，用于同时进行车道识别和定位。所提出的模型克服了有效主题定位的pLSA模型的局限性。在各种情况下的交通序列的实验结果证明了该方法的有效性和鲁棒性。

著录项

  • 来源
    《Optical engineering》 |2010年第10期|p.193-201|共9页
  • 作者

    Hao Sun; Cheng Wang; Boliang Wang; Naser EI-Sheimy;

  • 作者单位

    National University of Defense Technology School of Electrical Science and Engineering 47 Yanwachi Street Changsha, Hunan 410073, China;

    Xiamen University Department of Computer Science School of Information Science and Technology Xiamen, Fujian 361005, China;

    Xiamen University Department of Computer Science School of Information Science and Technology Xiamen, Fujian 361005, China;

    University of Calgary Department of Geomatics Engineering 2500 University Drive Northwest Calgary, Alberta T2N 1N4, Canada;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    lane detection; shape descriptor; unsupervised learning; topicmodels.;

    机译：车道检测;形状描述符无监督学习;主题模型。;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号