期刊文献+

曲率-HOG目标检测算法研究 被引量:4

Research of Curvature-HOG Object Detection Algorithm
下载PDF
导出
摘要 HOG算法充分利用梯度方向与幅值分布信息,在行人、车辆等特定目标检测定位中得到广泛应用,针对如何在HOG算法中融合梯度信息和曲率信息,本文提出基于HOG的梯度曲率相结合的目标检测算法并将其应用于目标检测问题中。算法首先计算图像的曲率信息和梯度信息,利用梯度的幅值和方向作为约束条件,统计曲率的分布直方图;然后将曲率直方图特征与HOG特征相连接,构成新的性能更好的特征描述子,最后将这一特征描述子用于检测实验。在ETZH形状数据库和INRIA马匹数据库上的实验结果表明,本文算法能够更好地检测目标并获得较高的精度。 The HOG descriptor takes full advantage of the information of gradient direction and amplitude distribution,which is widely applied in pedestrians,vehicles and other specific object detection and location task.In order to introduce curvature information and gradient information to the HOG descriptor,this paper proposes an improved object detection algorithm based on HOG algorithm.Firstly,calculate the curvature information and gradient information,apply the gradient amplitude and direction as constraint condition to obtain curvature distribution histogram,and then build a new feature descriptor with better detection performance,finally,use the new feature vector to detect objects.Experiment results in the shape ETZH database and INRIA horse database show that the proposed algorithm can obtain better detection performance and a higher accuracy.
作者 胡正平 周爽
出处 《信号处理》 CSCD 北大核心 2013年第11期1470-1475,共6页 Journal of Signal Processing
基金 国家自然科学基金(61071199) 河北省自然科学基金(F2010001297) 中国博士后科学基金第二批特别资助(200902356)
关键词 方向梯度直方图 曲率直方图 目标检测 histogram of oriented gradient histogram of curvature object detection
  • 相关文献

参考文献11

  • 1Dalai N, Triggs B. Histograms of oriented gradients for human detection[ C]. 2005 IEEE Computer Society Con- ference on Computer Vision and Pattern Recognition,2005, 1:886-893.
  • 2欧阳毅,张三元,张引.基于窗口边缘梯度势能的人体遮挡多尺度检测算法[J].电子与信息学报,2012,34(4):858-864. 被引量:7
  • 3姚雪琴,李晓华,周激流.基于边缘对称性和HOG的行人检测方法[J].计算机工程,2012,38(5):179-182. 被引量:22
  • 4胡正平,杨建秀.HOG特征混合模型结合隐SVM的感兴趣目标检测定位算法[J].信号处理,2011,27(8):1206-1212. 被引量:8
  • 5Kojima A, Sasano Y, Kise K. Object recognition from human actions using N-grams of HOG features [ J ]. ICIC Express Letters, 2012, 6(5):1155-1160.
  • 6闻帆,屈桢深,闫纪红.基于CKPCA-HOG和支持向量机的运动目标分类算法[J].哈尔滨工程大学学报,2011,32(5):643-649. 被引量:6
  • 7Takahashi K, Kuriya Y, Morie T. Bicycle detection using pedaling movement by spatiotemporal Gabor filtering[ J]. International Journal of Innovative Computing, Informa- tion and Control, 2012, 8(6) :4059-4070.
  • 8Semeikina E V, Yurin D V, Krylov A. S, et al. Scale- space line curvature estimation for straight tine and circle detection[ J ]. Pattern Recognition and Image Analysis, 2012, 22(2) :360-370.
  • 9Fabian T, Erhardt B. Accurate eye centre localisation by means of gradients [ C ]. Proceedings of the International Conference on Computer Vision Theory and Application. Vilamoura, Algarve, Portugal, 2011 : 125-130.
  • 10Kawamura K, Ishii D, Watanabe H. Automatic scale de-tection for contour fragment based on difference of curva- ture [ J ]. IEICE Transactions on Information and Sys- tems, 2011, E94-D(10) : 1998-2005.

二级参考文献43

  • 1王和勇,姚正安,李磊.基于聚类的核主成分分析在特征提取中的应用[J].计算机科学,2005,32(4):64-66. 被引量:20
  • 2Kim S, Park S, Kim M. Central object extraction for ob- ject-based image retrieval [ C ]. Urbana-Champaign, IL, USA: Proceedings of the 2nd International Conference on Image and Video Retrieval, 2003:39-49.
  • 3Hua G, Liu Z, Zhang Z, et al. Iterative local-global ener- gy minimization for automatic extract object of interest [ J ]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2006, 28 ( 10 ) : 1701 - 1706.
  • 4Lowe D. Distinctive image features from scale-invariant key- points [ J ]. International Journal of Computer Vision, 2004, 60(2) : 91-110.
  • 5Dalai N, Triggs B. Histograms of oriented gradients for hu- man detection[C]. San Diego, CA, United states: Pro- ceedings of IEEE Computer Society Conference on Com- puter Vision and Pattern Recognition, 2005:886-893.
  • 6Shashua A, Gdalyahu Y, Hayun G. Pedestrian detection for driving assistance systems: Single-frame classification and system level performance [ C ]. Parma, Italy : Proceedings of IEEE Intelligent Vehicles Symposium, 2004 : 1 - 6.
  • 7Zhu Q, Avidan S, Yeh M C, et al. Fast human detection using a cascade of histograms of oriented gradients [ C ]. New York, NY, United states : Proceedings of IEEE Com- puter Society Conference on Computer Vision and Pattern Recognition, 2006, 2:1491-1498.
  • 8Opelt A, Pinz A. Fusing shape and appearance informa- tion for object category detection [ C ]. Edinburgh, UK : Proceedings of British Machine Vision Conference, 2006 : 117-126.
  • 9Felzenszwalb, P., et al., Object Detection with Discrimi- natively Trained Part Based Models. IEEE Transactions on Pattern Analysis And Machine Intelligence, 2010, 32 (9) :1627-1645.
  • 10Bai, X., et al. Active Skeleton for Non-rigid Object Detec- tion. in International Conference on Computer Vision. 2009. Kyoto, Japan.

共引文献38

同被引文献64

  • 1王鼎,沈辉,娄海涛.一种基于H-CrCb颜色空间的肤色检测算法研究[J].计算机科学,2012,39(S2):223-226. 被引量:6
  • 2Dalai N, Triggs B. Histograms of oriented gradients fi~r hu- man detection [ C 1//Computer Vision and Pattern Rec.<~li- tion, 2005 IEEE Conference on. IEEE 2005 : 886-893.
  • 3Felzenszwalb P, McAllester D, Ramanan D. A discrimina- tively trained, muhiscale, deformable part model ~ C ] // C~mlputer Vision and Pattern Recognition, ;2008. CVPR2008. IEEE Conference on. IEEE, 2008: 1-8.
  • 4(;'all J, LempitskyV. Class-specilic hough forests for object detection[ C ]//Computer Vision and Pattern Recognition, 2009 IEEE Conference on. IEEE, 2009: 1022-1029.
  • 5S('hulter S, l,eistner C, ~'ohlhart P, el al. Accurate Ob- ject Detection with Joint Classification-Regression Ran- dom Forests[ C] S/Computer Vision and Pattern Ree~gni- tion. IEEE, 2014: 923-930.
  • 6Xia L, Chen C C, Aggarwal J K. Human detection using depth inf()rmation by kinect [ C ]//Computer Visinn and Pattern Recognition Workshops (CVPRW), 2011 IEEE Conference on. IEEE, 2011 : 15-22.
  • 7Tang S, Wang X, Lv X, et al. Histogram of oriented norn'.al vectors for object recognition with a depth sensor[ C]//Asi- an Conference on Computer Vision, 2013: 525-538.
  • 8Oreifej O, Liu Z. Hon4d: Histogram of oriented 4(t nor- mals for activity recognition fi'om depth sequences [ C ]// Computer Vision and Pattern Recognition, 2013 IEEE Conference on. IEEE, 2013: 716-723.
  • 9Gupta S, Girshick R, Arl)el~iez P, et al. l,earning rich fea- tures from RGB-D images for object detection and segmen- tation [ C ] //European Conference oll Computer Vision 2014. Springer International Publishing, 2014: 345-360.
  • 10Alexe B, Deselaers T, [ C] //Computer Vision IEEE Conference on. IE Hongwen Kang, Hebert, Driven Objectness[ J ]. P telligence, 2015, 37(1.

引证文献4

二级引证文献20

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