...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Optical engineering >REBoost: probabilistic resampling for boosted pedestrian detection
【24h】

REBoost: probabilistic resampling for boosted pedestrian detection

机译：REBoost：概率重采样以增强行人检测

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

Cascaded object detectors have demonstrated great success in fast object detection, where image regions can quickly be rejected us-ing a cascade of increasingly complex rejectors/detectors. Although such cascaded detectors typically are fast and require minimal computation, they usually require iterative training, where classifiers are retrained to optimize rejection thresholds after testing on a validation set. We propose a cascaded object detector that uses probabilistic resampling for boosting reweighting, which has the advantage that only a single training step is required. Decision thresholds can be tuned on a validation set without the need for classifier retraining. Empirical results on a pedestrian detection task demonstrate that this reweighting results in a strong classifier that quickly rejects image regions and offers higher accuracy than other com-peting approaches.
机译：级联物体检测器在快速物体检测中已显示出巨大的成功，在快速物体检测中，可以使用级联的日益复杂的剔除器/检测器快速剔除图像区域。尽管这样的级联检测器通常很快并且需要最少的计算，但是它们通常需要迭代训练，其中在对验证集进行测试后，对分类器进行重新训练以优化拒绝阈值。我们提出了一种级联对象检测器，该检测器使用概率重采样来增强重加权，其优点是只需要单个训练步骤。决策阈值可以在验证集上进行调整，而无需分类器重新训练。关于行人检测任务的经验结果表明，这种重新加权可以产生强大的分类器，该分类器可以快速拒绝图像区域并提供比其他竞争方法更高的准确性。

著录项

  • 来源
    《Optical engineering》 |2011年第12期|p.127203.1-127203.7|共7页
  • 作者

    Shiming Lai; Yu Liu; Maojun Zhang; Barry-John Theobald;

  • 作者单位

    National University of Defense Technology College of Information System and Management Yanwachi Zheng Street Changsha, Hunan 410073, China;

    National University of Defense Technology College of Information System and Management Yanwachi Zheng Street Changsha, Hunan 410073, China University of East Anglia School of Computing Sciences Norwich, NR4 7TJ United Kingdom;

    National University of Defense Technology College of Information System and Management Yanwachi Zheng Street Changsha, Hunan 410073, China;

    University of East Anglia School of Computing Sciences Norwich, NR4 7TJ United Kingdom;

  • 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

    object detection; cascaded detector; boosting; pedestrian detection;

    机译：物体检测级联检测器;促进行人检测;

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