方向梯度直方图及其扩展

doi:10.3969/j.issn.1000-3428.2013.05.047

计算机工程 ›› 2013, Vol. 39 ›› Issue (5): 212-217. doi: 10.3969/j.issn.1000-3428.2013.05.047

方向梯度直方图及其扩展

傅红普^1,2，邹北骥¹

(1. 中南大学信息科学与工程学院，长沙 410086；2. 湖南第一师范学院信息科学与工程系，长沙 410205)

收稿日期:2012-05-11 出版日期:2013-05-15 发布日期:2013-05-14
作者简介:傅红普(1973－)，男，副教授、博士研究生，主研方向：机器视觉；邹北骥，教授、博士
基金资助:
湖南省教育厅科学研究基金资助项目(12C0591)；湖南第一师范学院科研基金资助项目(XYS07N12)

Histogram of Oriented Gradient and Its Extension

FU Hong-pu ^1,2, ZOU Bei-ji ¹

(1. School of Information Science and Engineering, Central South University, Changsha 410086, China; 2. Department of Information Science and Engineering, Hunan First Normal University, Changsha 410205, China)

Received:2012-05-11 Online:2013-05-15 Published:2013-05-14

摘要/Abstract

摘要： 介绍方向梯度直方图(HOG)及其扩展。结合HOG的计算步骤阐述其内在理念和捕获的主要图像特征，指出其局限性，论述对HOG的重要扩展，包括多尺寸HOG、梯度方向直方图金字塔、分析降维HOG，给出对各扩展使用积分图加速计算的方法以及其他改善方法，从措施、复杂度、维数、思想等方面对各HOG改善方法进行比较，给出HOG未来的研究方向。

关键词: 局部特征描述符, 方向梯度直方图, 积分图, 梯度方向直方图金字塔, 降维分析

Abstract: This paper surveys Histogram of Oriented Gradient(HOG) and its extension. Combining with the computing step of HOG, this paper discusses its underline idea, the main image features captured by it and its limitations. It discusses several important extensions of HOG, including variable-size HOG, Pyramid of Histogram of Oriented Gradient(PHOG) and analytic dimension reduction HOG. And it also describes the way to speedup the computing of these extensions with integral image. It gives other possible ways to improve HOG and the possible directions to improve the ability of HOG, and makes the comparison of HOG improving methods with measure, complexity, dimension and idea. Several valuable research directions are proposed.

Key words: local feature descriptor, Histogram of Oriented Gradient(HOG), integral imag, Pyramid of Histogram of Oriented Gradient(PHOG), dimension reduction analysis

中图分类号:

TP391.41

傅红普, 邹北骥. 方向梯度直方图及其扩展[J]. 计算机工程, 2013, 39(5): 212-217.

FU Gong-Pu, JU Bei-Ji. Histogram of Oriented Gradient and Its Extension[J]. Computer Engineering, 2013, 39(5): 212-217.

http://www.ecice06.com/CN/Y2013/V39/I5/212

参考文献

[1] Freeman W T, Roth M. Orientation Histograms for Hand Gesture Recognition[C]//Proc. of International Workshop on Automatic Face and Gesture Recognition. Zurich, Switzerland: [s. n.], 1995.
[2] Mikolajczyk K, Schmid C. Scale and Affine Invariant Interest Point Detectors[J]. International Journal of Computer Vision, 2004, 60(1): 63-86.
[3] David G L. Distinctive Image Features from Scale- invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[4] Navneet D, Triggs B. Histograms of Oriented Gradients for Human Detection[C]//Proc. of CVPR’05. San Diego, USA: [s. n.], 2005.
[5] Yi Yang, Ramanan D. Articulated Pose Estimation with Flexible Mixtures-of-parts[EB/OL]. (2011-11-21). http:// vision.ics.uci.edu/papers/YangR_CVPR_2011/.
[6] Sapp B, Toshev A, Taskar B. Cascaded Models for Articu- lated Pose Estimation[EB/OL]. (2010-11-21). http://vision. grasp.upenn.edu/cgi-bin/index.php?n=VideoLearning.CascadedModelsForArticulatedPoseEstimation.
[7] Moeslund T, Hilton A, Sigal L. Visual Analysis of Humans[M]. [S. l.]: Springer, 2011.
[8] Felzenszwalb P F, Girshick R B, McAllester D, et al. Object Detection with Discriminatively Trained Part Based
Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[9] Doersch C. Improving the HoG Descriptor[EB/OL]. (2012-01-21). http://www.cs.cmu.edu/~cdoersch/projects/ hogimprove/.
[10] Guruprasad S, Vassilios M, Papanikolopoulos N. Deploy- ment of Practical Methods for Counting Bicycle and Pedestrian Use of a Transportation Facility[EB/OL]. (2010-11-21). http://www.its.umn.edu/Publications/Resea rchReports/reportdetail.html?id=2088.
[11] Grabner H. On-line Boosting and Vision[EB/OL]. (2010- 05-21). http://www.graz.ac.at/Members/hgrabner/pub_ hgrabner/grabner2006OnlineBoosting.pdf/at_download/ file.
[12] Zhu Qiang, Avidan S, Yeh Mei-Chen, et al. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients[C]//Proc. of IEEE Computer Society Conference on Computer Vision and Pattern. Washington D. C., USA: IEEE Computer Society, 2006.
[13] Viola P, Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features[C]//Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE Press, 2001.
[14] Freund Y, Schapire R E. A Decision-theoretic Generali- zation of On-line Learning and an Application to Boosting[C]//Proc. of the 2nd European Conference on Computational Learning Theory. [S. l.]: IEEE Press, 1995.
[15] Laptev I. Improvements of Object Detection Using Boosted Histograms[EB/OL]. (2010-11-21). http://www.irisa.fr/ vista/Papers/2006_bmvc_laptev.pdf.
[16] Shet V D, Neumann J, Ramesh V, et al. Bilattice-based Logical Reasoning for Human Detection[C]//Proc. of IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE Press, 2007.
[17] Zhang Li, Wu Bo, Nevatia R. Detection and Tracking of Multiple Humans with Extensive Pose Articulation[C]// Proc. of IEEE the 11th International Conference on Computer Vision. [S. l.]: IEEE Press, 2007.
[18] Subhransu M, Alexander C B, Jitendra M. Classification Using Intersection Kernel Support Vector Machines is Efficient[C]//Proc. of IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE Press, 2008.
[19] Wang Peng, Shen Chunhua, Barnes N, et al. Fast and Robust Object Detection Using Asymmetric Totally- corrective Boosting[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(1): 33-46.
[20] Bosh A, Zisserman A, Munoz X. Representing Shape with a Spatial Pyramid Kernel[C]//Proc. of the 6th ACM International Conference on Image and Video Retrieval. New York, USA: ACM Press, 2007.
[21] Liu Tie, Sun Jian, Zheng Nanning, et al. Learning to Detect A Salient Object[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 353-367.
[22] Alireza F, Mori G. Action Recognition by Learning Mid- level Motion Features[EB/OL]. (2010-11-21). http://libra. msra.cn/Publication/4704657/action-recognition-by-learning- mid-level-motion-features.
[23] Sabzmeydani P, Mori G. Detecting Pedestrians by Learning Shapelet Features[EB/OL]. (2009-11-21). http://arnetminer.
org/publication/detecting-pedestrians-by-learning-shapelet- features-129744.html.
[24] Prisacariu V A, Reid I. FastHOG——A Real-time GPU Implementation of HOG[EB/OL]. (2009-01-21). http:// www.robots.ox.ac.uk/~lav/Papers/prisacariu_reid_tr2310_09/prisacariu_reid_tr2310_09.html.
[25] Schwartz W R, Kembhavi A, Harwood D, et al. Human Detection Using Partial Least Squares Analysis[C]//Proc. of IEEE the 12th International Conference on Computer Vision. [S. l.]: IEEE Press, 2009.
[26] Haralick R, Shanmugam K, Dinstein I. Texture Features for Image Classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, 3(6): 610-621.
[27] 郭立君, 刘曦, 赵杰煜, 等. 结合运动信息与表观特征的行人检测方法[J]. 软件学报, 2012, 23(2): 299-309.
[28] Pedersoli M, Vedaldi A, Gonzalez J. A Coarse-to-fine Approach for Fast Deformable Object Detection[C]//Proc. of IEEE Conference on Computer Vision and Pattern Recognition. Barcelona, Spain: IEEE Press, 2011.
[29] Felzenszwalb P F, Girshick R B, McAllester D, et al. Articulated Pose Estimation with Flexible Mixtures-of- parts[C]//Proc. of IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE Press, 2011.
编辑刘冰

选择文件类型/文献管理软件名称

选择包含的内容

方向梯度直方图及其扩展

Histogram of Oriented Gradient and Its Extension

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	胡冉冉,刘志刚. 高铁接触网悬挂装置的等电位线故障检测方法[J]. 计算机工程, 2018, 44(1): 252-257.
[2]	李熙莹,袁敏贤,吕硕,江倩殷. 基于LLC与加权SPM的车辆品牌型号识别[J]. 计算机工程, 2017, 43(5): 210-216.
[3]	周文谊,王吉源. 一种模糊森林学习方法及其行人检测应用[J]. 计算机工程, 2017, 43(3): 304-308，315.
[4]	何希平,张琼华,刘波. 基于HOG的目标分类特征深度学习模型[J]. 计算机工程, 2016, 42(12): 176-180,187.
[5]	徐渊,许晓亮,李才年,姜梅,张建国. 结合SVM分类器与HOG特征提取的行人检测[J]. 计算机工程, 2016, 42(1): 56-60,65.
[6]	贺建峰,符增,相艳,易三莉,崔锐. 基于灰度空间相关性最大类间方差的图像分割[J]. 计算机工程, 2015, 41(11): 280-286.
[7]	罗嗣卿,贾子书. 基于动态规划的快速立体匹配算法[J]. 计算机工程, 2015, 41(11): 224-231.
[8]	杨先凤,杨燕. 一种基于HOG-LBP 的高效车辆检测方法[J]. 计算机工程, 2014, 40(9): 210-214.
[9]	张羽立, 戴麟, 周薇娜, 邹垚, 曾晓洋. 一种积分图的分治计算方法[J]. 计算机工程, 2012, 38(22): 232-235.
[10]	王志明, 张丽, 包宏. 基于神经网络的双通道视频融合人员入侵检测[J]. 计算机工程, 2012, 38(19): 183-187.
[11]	陆蓓, 陈法叶, 姚金良. 一种改进的敏感图像过滤方法[J]. 计算机工程, 2011, 37(21): 202-204.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

方向梯度直方图及其扩展

Histogram of Oriented Gradient and Its Extension

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价