• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Proceedings 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer >Discriminative hough-voting for object detection with parts
【24h】

Discriminative hough-voting for object detection with parts

机译：区分式投票，用于零件检测

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

Many detection models rely on sliding-window methods to search all possible candidates and then localize true instances by linear classifiers. Such exhaustive search involves massive computation. Hough voting scheme provides an alternative way to localize objects. Typical voting-based approaches, casting independent votes for a hypothesis, ignore the mutual relevance of features. The weights of the features for voting are learnt in a simple way. These two weaknesses limit the detection performance of the voting scheme. This paper introduces a novel voting-based model. We group the model features into parts. The features in one part are dependent and can cast consistent votes for a given hypothesis. For a given hypothesis we introduce an overall score function whose parameters can be optimized in a discriminative way. We apply a latent learning framework to deal with part-level weak supervision. The experiments evaluate the proposed model on two standard datasets. We demonstrate significant improvements in detection performance comparing the start-of-the-art detection models.
机译：许多检测模型依赖于滑动窗口方法来搜索所有可能的候选对象，然后通过线性分类器定位真实实例。这种详尽的搜索涉及大量的计算。 Hough投票方案提供了一种定位对象的替代方法。典型的基于投票的方法（对假设进行独立投票）会忽略要素之间的相互关联性。投票功能的权重可以通过一种简单的方式来学习。这两个弱点限制了投票方案的检测性能。本文介绍了一种新颖的基于投票的模型。我们将模型特征分组。一部分特征是相关的，可以针对给定的假设投一致的票。对于给定的假设，我们引入一个总体得分函数，该函数的参数可以通过判别方式进行优化。我们采用了潜在的学习框架来处理部分级别的弱监督。实验在两个标准数据集上评估了提出的模型。与最先进的检测模型相比，我们证明了检测性能的显着提高。

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