多尺度局部区域响应累积的非滑窗快速目标检测算法

胡正平, 董淑丽, 赵淑欢

胡正平, 董淑丽, 赵淑欢. 多尺度局部区域响应累积的非滑窗快速目标检测算法[J]. 信号处理, 2016, 32(1): 37-45. DOI: 10.16798/j.issn.1003-0530.2016.01.006
引用本文: 胡正平, 董淑丽, 赵淑欢. 多尺度局部区域响应累积的非滑窗快速目标检测算法[J]. 信号处理, 2016, 32(1): 37-45. DOI: 10.16798/j.issn.1003-0530.2016.01.006
HU Zheng-Ping, DONG Shu-Li, ZHAOShu-Huan. Fast object detection algorithm with non-sliding window based on accumulation of multi-scale local response[J]. JOURNAL OF SIGNAL PROCESSING, 2016, 32(1): 37-45. DOI: 10.16798/j.issn.1003-0530.2016.01.006
Citation: HU Zheng-Ping, DONG Shu-Li, ZHAOShu-Huan. Fast object detection algorithm with non-sliding window based on accumulation of multi-scale local response[J]. JOURNAL OF SIGNAL PROCESSING, 2016, 32(1): 37-45. DOI: 10.16798/j.issn.1003-0530.2016.01.006

多尺度局部区域响应累积的非滑窗快速目标检测算法

基金项目: 国家自然科学基金(61071199);河北省自然科学基金(F2010001297)
详细信息
  • 中图分类号: TP391.4

Fast object detection algorithm with non-sliding window based on accumulation of multi-scale local response

  • 摘要: 针对滑动窗口全局搜索检测目标搜索时间长的问题,提出一种多尺度局部区域响应累积的非滑窗快速目标检测算法。首先,提取检测目标多尺度可重叠局部区域作为训练样本,通过学习得到多尺度且具有判别能力的部件集,部件集中每个局部区域与检测目标有明确位置对应关系;然后,根据各投影检测器响应判断目标是否在某一区域出现,并利用多尺度目标局部区域的检测结果和位置约束进行投票,完成目标粗定位;其次,利用HOG特征提取和SVM相结合完成检测目标验证实现准确检测。该方法将多尺度部件模型、统计累积投票思想及分类器判决相结合,实现快速目标检测,大大减少滑动窗口逐像素搜索背景时所消耗时间,提高检测效率。
    Abstract: Exhaustive search method of sliding window which consumes much time in searching the location is used to detect objects. In order to solve this problem, we propose a fast object detection algorithm with non-sliding window based on accumulation of multi-scale local response. Firstly, the multi-scale and foldable local areas are extracted as the training sample, then learning them to obtain a part sets with multi-scale and discriminative ability, in which every local area and object have a definely position corresponding relationship; Secondly, the appearance of a particular area is based on every projection detector’s response and the object’s positions are determined by using voting shceme with multi-scale object detection results of the local area and the position constraint; Finally, we test the object by combining the HOG feature extraction with the classifier of SVM to realize accurate location. Experimental results show that the proposed method which combining multi-scale part model and statistics of cumulative voting and the classifier of SVM improves the detection efficiency via saving the consumed time of the sliding window pixel-by-pixel searches background.
计量
  • 文章访问数:  252
  • HTML全文浏览量:  2
  • PDF下载量:  964
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-06-03
  • 修回日期:  2015-07-04
  • 发布日期:  2016-01-24

目录

    /

    返回文章
    返回