首页> 外文期刊>WSEAS Transactions on Signal Processing >Context-Aware Model Applied to HOG Descriptor for People Detection
【24h】

Context-Aware Model Applied to HOG Descriptor for People Detection

机译:上下文感知模型应用于人们检测的HOG描述符

获取原文
获取原文并翻译 | 示例
           

摘要

This work proposes and implements a method based on Context-Aware Visual Attention Model(CAVAM), but modifying the method in such way that the detection algorithm is replaced by Histograms of Oriented Gradients (HOG). After reviewing different algorithms for people detection, we select HOG method because it is a very well known algorithm, which is used as a reference in virtually all current research studies about automatic detection. In addition, it produces accurate results in significantly less time than many algorithms. In this way, we show that CAVAM model can be adapted to other methods for object detection besides Scale-Invariant Feature Transform (SIFT), as it was originally proposed. Additionally, we use TUD dataset image sequences to evaluate and compare our approach with the original HOG algorithm. These experiments show that our method achieves around 2x speed-up at just 2% decreased accuracy. Moreover, the proposed approach can improve precision and specificity by more than 2%.
机译:这项工作提出并实现了一种基于上下文的视觉注意模型(CAVAM)的方法,但是通过导向梯度(HOG)的直方图所取代检测算法的方式修改方法。在审查不同算法的人检测后,我们选择HOG方法,因为它是一种非常已知的算法,其用作几乎所有当前关于自动检测的研究研究的参考。此外,它可以产生比许多算法的时间明显更少的结果。通过这种方式,除了鳞片不变特征变换(SIFT)之外,我们表明CAVAM模型可以适用于除垢特征变换(SIFT)之外的对象检测方法。此外,我们使用Tud DataSet映像序列来评估和比较我们使用原始猪算法的方法。这些实验表明,我们的方法达到了2倍的加速,仅2%降低了。此外,所提出的方法可以通过2%提高精度和特异性。

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