• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Image and Vision Computing >Boosted translation-tolerable classifiers for fast object detection
【24h】

Boosted translation-tolerable classifiers for fast object detection

机译：提升翻译容忍度的分类器，可快速检测物体

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

Different classifiers show different sensitivities to translation-variance. The translation-insensitive classifiers are capable of accelerating the detection process by searching over a coarse grid as well as guaranteeing the recall rate.In this paper, we define a concept of Translation-Tolerable Region (TTR) for a classifier. The TTR is such a region that all the detection windows in it have consistent (stable) results output by the classifier. We use the classifier's Maximal Translation-Tolerable Region (MTTR) to measure its sensitivity to the translation-variance. For object detection, we propose an algorithm for training the discriminative classifiers as well as learning the associated MTTRs. The discriminative classifiers are assembled into a cascaded classifier in descending order of their MTTR sizes. To speed up the detection process, we propose a Granularity-Adaptively-Tunable (GAT) search strategy according to the classifiers' MTTRs. Furthermore, we prove that the recall rate is Probably Approximately Admissible (PAA) in the GAT search, which means that the proposed approach can theoretically guarantee the accuracy while accelerating the detection process. Based on the boosting framework with Histograms of Oriented Gradients (HOG) features, we evaluate the proposed approach on the public datasets containing both rigid and non-rigid object classes. The experimental results show that our approach achieves considerable results with a fast speed.
机译：不同的分类器对翻译差异显示出不同的敏感性。对平移不敏感的分类器能够通过搜索粗糙网格并保证查全率来加速检测过程。本文为分类器定义了平移容忍区域（TTR）的概念。 TTR是这样一个区域，其中所有检测窗口都具有分类器输出的一致（稳定）结果。我们使用分类器的最大平移容忍区域（MTTR）来衡量其对平移差异的敏感性。对于对象检测，我们提出了一种算法，用于训练区分性分类器以及学习相关的MTTR。区分性分类器按照其MTTR大小的降序组合为级联分类器。为了加快检测过程，我们根据分类器的MTTR提出了粒度自适应可调（GAT）搜索策略。此外，我们证明了GAT搜索中的召回率大约是可允许的（PAA），这意味着该方法在理论上可以保证准确性，同时可以加快检测过程。基于具有定向梯度直方图（HOG）功能的增强框架，我们在包含刚性和非刚性对象类的公共数据集上评估了提出的方法。实验结果表明，我们的方法以快速的速度获得了可观的结果。

著录项

  • 来源
    《Image and Vision Computing》 |2012年第8期|p.480-491|共12页
  • 作者

    Wei Zheng; Luhong Liang; Hong Chang; Cher-Keng Heng; Shiguang Shan; Xilin Chen;

  • 作者单位

    Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China ,Graduate School of the Chinese Academy of Sciences, Beijing, 100039, China;

    Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China;

    Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China;

    Panasonic R&D Center Singapore, Singapore;

    Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China;

    Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China;

  • 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; boosting; maximal translation-tolerable region; (MTTR); granularity-adaptively-tunable(GAT);

    机译：目标检测;增强;最大可平移区域;（MTTR）;粒度自适应（GAT）;

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