• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Fast and Robust Object Detection Using Asymmetric Totally Corrective Boosting
【24h】

Fast and Robust Object Detection Using Asymmetric Totally Corrective Boosting

机译：使用非对称完全校正增强的快速和鲁棒对象检测

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

Boosting-based object detection has received significant attention recently. In this paper, we propose totally corrective asymmetric boosting algorithms for real-time object detection. Our algorithms differ from Viola and Jones' detection framework in two ways. Firstly, our boosting algorithms explicitly optimize asymmetric loss of objectives, while AdaBoost used by Viola and Jones optimizes a symmetric loss. Secondly, by carefully deriving the Lagrange duals of the optimization problems, we design more efficient boosting in that the coefficients of the selected weak classifiers are updated in a totally corrective fashion, in contrast to the stagewise optimization commonly used by most boosting algorithms. Column generation is employed to solve the proposed optimization problems. Unlike conventional boosting, the proposed boosting algorithms are able to de-select those irrelevant weak classifiers in the ensemble while training a classification cascade. This results in improved detection performance as well as fewer weak classifiers in the learned strong classifier. Compared with AsymBoost of Viola and Jones, our proposed asymmetric boosting is nonheuristic and the training procedure is much simpler. Experiments on face and pedestrian detection demonstrate that our methods have superior detection performance than some of the state-of-the-art object detectors.
机译：最近，基于增强的对象检测受到了广泛的关注。在本文中，我们提出了用于实时目标检测的完全矫正非对称提升算法。我们的算法在两个方面不同于Viola和Jones的检测框架。首先，我们的增强算法显式优化了目标的非对称损失，而Viola和Jones使用的AdaBoost优化了对称损失。其次，通过仔细推导优化问题的拉格朗日对偶，我们设计了更有效的增强算法，与大多数增强算法通常使用的阶段性优化相比，所选弱分类器的系数以完全纠正的方式进行更新。使用列生成来解决所提出的优化问题。与传统的增强算法不同，提出的增强算法能够在训练分类级联的同时取消选择那些不相关的弱分类器。这样可以提高检测性能，并在学习到的强分类器中减少弱分类器。与Viola和Jones的AsymBoost相比，我们提出的非对称增强是非启发式的，并且训练过程要简单得多。面部和行人检测实验表明，我们的方法比某些最新的物体检测器具有更高的检测性能。

著录项

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