期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

联合局部专家估计目标子窗口 被引量：1

Joint local experts for measuring objectness of image proposal windows
原文传递
导出
摘要 为了提高目标检测的效率和准确率,提出一种估计目标子窗口的联合局部专家方法.首先用局部专家交并集的方法滤除明显不包含目标的子窗口;然后,用局部专家向量空间模型中余弦定理的方法估计出包含目标的子窗口;最后,用局部专家非极大值抑制的方法从包含目标的子窗口中滤除重复包含同一目标的子窗口.实验结果表明,所提出的方法能快速准确地估计出包含目标的子窗口. In order to improve the efficiency and accuracy of object detection, the joint local experts method is proposed to estimate the objective windows by measuring how likely it is for an image proposal window to contain an object. Firstly, the proposal windows that do not contain any object obviously are filtered out by the local expert inter-union set. Then, the rest proposal windows that contain the object are measured by local expert cosine similarity. Finally, the objective windows are estimated by local expert non-maximum suppression from a large number of proposal windows that repeatedly contain the same object. Experiment results show that the proposed method is able to efficiently estimate the objective windows which accurately contain the object.
作者 马娟娟 潘泉 张夷斋 赵春晖 王峰 靳珍璐
机构地区 西北工业大学信息融合技术教育部重点实验室
出处 《控制与决策》 EI CSCD 北大核心 2016年第5期805-810,共6页 Control and Decision
基金 国家自然科学基金重点项目(61135001) 国家自然科学基金项目(61473230 61403307) 航空基金项目(2014ZC53030)
关键词 目标子窗口 目标检测 交并集 余弦定理 非极大值抑制 proposal windows object detection inter-union set cosine similarity non-maximum suppression
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献18

  • 1Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
  • 2Hariharan H B, Zitnick C L, Dollar P. Detecting objects using deformation dictionaries[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. Columbus: IEEE Press, 2014: 1995-2002.
  • 3Gall J, Yao A, Razavi N, et al. Hough forests for object detection, tracking, and action recognition[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2011, 33(11): 2188-2202.
  • 4Malisiewicz T, Gupta A, Efros A A. Ensemble of exemplar-SVMs for object detection and beyond[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. Barcelona: IEEE Press, 2011: 89-96.
  • 5Mar′?n J, Vazquez D, Lopez A M, et al. Random forests of local experts for pedestrian detection[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. Sydney: IEEE Press, 2013: 2592-2599.
  • 6Alexe B, Deselaers T, Ferrari V. What is an object?[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. San Francisco: IEEE Press, 2010: 73-80.
  • 7Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2012, 34(11): 1627-1645.
  • 8Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection[C]. Proc of IEEE Int Conf on Computer Vision. Anchorage: IEEE Press, 2009: 1597-1604.
  • 9Lu S, Mahadevan V, Vasconcelos N. Learning optimal seeds for diffusion-based salient object detection[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. Columbus Ohio: IEEE Press, 2014: 2790-2797.
  • 10Uijlings J, van de Sande K, Gevers T, et al. Selective search for object recognition[J]. Int J of Computer Vision, 2013, 32(9): 1627-1645.

二级参考文献40

  • 1REN Xiao-fimg, MAI,IK J. Learning a classification model for seg- mentation[ C ]//Proc of the 9th IEEE International Conference on Computer Vision. Washington DC :IEEE Computer Society ,2(X)3 : 10-17.
  • 2FEIZENSWALB P F, HUTFENLOCHER D P. Efficient graph-based image segmentation [ J ]. International Journal of Computer Vision, 2004, 59(2):167-181.
  • 3SHI Jian-bo, MALIK J. Normalized cuts and image segmentation [C]//Proc of IEEE Computer Society Conference on Computer Vi-sion and Pattern Recognition. Washingtan DC:IEEE Camputer Socie- ty, 1997:731-737.
  • 4SHI Jian-bo, MAL1K J. Normalized cuts and image segmentation[ J ]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8) :888-905.
  • 5MOORE A, PRINCE S, WARRELI. J, et al. Superpixel lattices [ C]//Proc of IEEE Conference on Computer Vision and Pattern Rec- ognition. 2008 : 1-8.
  • 6LIU Ming-yu, TUZEL O, RAMALINGAM S,et al. Entropy rate su- perpixel segmentation [ C ]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. 2011:2097-2104.
  • 7VINCENT L, SOILLE P. Watersheds in digital spaces: an efficient algoritlml based on inlmeision simulations[ J]. IEEE Trans on Pat- tern Analysis and Machine Intelligence, 1991, 13 (6) : 583-598.
  • 8COMANICIU D, MEER P. Mean shift: a rnhust approrah toward fea- ture space analysis[ J ]. IEEE Trans on Pattern Analysis and Ma- chine Intelligence, 2002, 24(5): 603-619.
  • 9VEDALDI A, SOATTO S. Quick shift and kernel methods for mode seeking [ M ]//Computer Vision. Berlin: Springer-Verlag, 2008: 705-718.
  • 10LEVINSHTEIN A, STERE A, KUTULAKOS K N, et al. Turbotfi- xels: fast superpixels using geometric flows [ J ]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31 (12): 2290- 2297.

共引文献115

同被引文献2

引证文献1

二级引证文献7

控制与决策
2016年 第5期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部