计算机科学 ›› 2014, Vol. 41 ›› Issue (12): 255-259.doi: 10.11896/j.issn.1002-137X.2014.12.055
章登义,王骞,郭雷,武小平
ZHANG Deng-yi,WANG Qian,GUO Lei and WU Xiao-ping
摘要： 针对基于梯度方向直方图(Histogram of Oriented Gradient,HOG)特征和局部二值模式(Local Binary Patterns,LBP)特征的行人检测存在特征向量维度大、检测精度有待提高的问题,提出了一种分块特征收缩的行人检测方法。首先将样本图像划分成多个大小相同的重叠分块；然后提取各分块的HOG和LBP特征,并将两种特征融合作为分块的特征,通过该特征来训练分块分类器,根据分块分类器的行人检测精度对分块进行排序,选取检测精度较高的分块进行特征收缩；最后将特征收缩后的分块特征向量连接在一起作为最终用于行人检测的特征。在INRIA公共测试集合上的实验结果表明,该方法在降低了特征向量维度的同时提高了行人检测精度。
| [1] Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection[C]∥Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,CA,United states,2005:886-893 [2] Zhu Q,Avidan S,Yeh M C,et al.Fast human detection using a cascade of histograms of oriented gradients[C]∥Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.New York,NY,United states,2006:1491-1498 [3] Mu Ya-dong,Yan Shui-cheng,Liu Yi,et al.Discriminative local binary patterns for human detection in personal album[C]∥ Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition.Anchorage,AK,United states,2008 [4] Yao Wen-tao,Deng Zhi-dong.A robust pedestrian detection approach based on shapelet feature and Haar detector ensembles[J].Tsinghua Science and Technology,2012,17(1):40-50 [5] Levi K,Weiss Y.Learning object detection from a small number of examples:The importance of good features[C]∥Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington DC,United states,2004:1153-1160 [6] Wu Bo,Ram N.Detection of multiple,partially occluded humans in a single image by bayesian combination of edgelet part detectors[C]∥ Proceedings of the 10th IEEE International Conference on Computer Vision.Beijing,China,2005:90-97 [7] Wu Jian-xin,Rehg James M.CENTRIST:A visual descriptor for scene categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1489-1501 [8] Lowe D G.Distinctive image features from scale-invariant key-points[J].International Journal of Computer Vision,2004,60(2):91-110 [9] Lowe D G.Object recognition from local scale-invariant features[C]∥Proceedings of the 1999 7th IEEE International Conference on Computer Vision.Kerkyra,Greece,1999:1150-1157 [10] Sabzmeydani P,Mori Greg.Detecting pedestrians by learningshapelet features[C]∥Proceedings of the IEEE Computer Socie-ty Conference on Computer Vision and Pattern Recognition.Minneapolis,MN,United states,2007 [11] Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]∥Proceedings of the IEEE Computer Socie-ty Conference on Computer Vision and Pattern Recognition.Kauai,HI,United states,2001:1511-1518 [12] Heng C K,Yokomitsu S,Matsumoto Y,et al.Shrink boost for selecting multi-LBP histogram features in object detection[C]∥Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Providence,RI,United states,2012:3250-3257 |
| No related articles found! |
|
||
首页