摘要: 针对HOG特征检测准确率高、计算量大的特点,通过对HOG特征的结构进行调整,提出了使用Fisher特征挑选准则来挑选出有区别能力的行人特征块,得到MultiHOG特征。该算法结合线性SVM二值分类器,实现行人滑动窗口检测。用Inria标准数据集和自行拍摄数据集进行了测试,结果证明该算法较HOG在准确率及实时性上都有很大的提高。
[1] Geronimo D,Lopez A.Survey of pedestrain detection for ada-vanced driver assistance systems[J].IEEE Trans.On Pattern Analysis and Machine Intelligence,2010,2(7):1239-1258 [2] Luo R C,Chen O.Wireless and Pyroelectric Sensory Fusion System for Indoor Human/Robot Localization and Monitoring[J].IEEE/ASME Transactions on Mechatronics,2013,18(3):845-853 [3] Uddin M-Z,Kim D-H,Kim J T,et al.An Indoor Human Activity Recognition System for Smart Home Using Local Binary Pattern Features with Hidden Markov Models[J].Indoor and Built Environment,2013,22(1):289-298 [4] Dalai N,Tfiggs B.Histograms of Oriented Gradients for Hu-manDetection[C]∥Proceedings of IEEE Computer Society Conference On Computer Vision and Pattern Recognition.IEEE Press,2005:886-893 [5] Ding Jian-hao,Wang Yi-gang,Geng Wei-dong.An HOG-CT human detector with histogram-based search[J].Multimedia Tools and Applications,2013,63(3):791-807 [6] Dohi K,Negi K,Shibata Y,et al.FPGA Implementation of Human Detection by HOG Features with AdaBoost[J].IEICE Transactionson Information and Systems,2013,96(8):1676-1684 [7] Cristina C,Daniela M,De Diego M,et al.HoGG:Gabor andHoG-based human detection for surveillance in non-controlled environments[J].Neurocomputing,2013,100:19-30 [8] Walk S.New Features and Insights for Pedestrian Detection[C]∥2010 IEEE Conference on Computer Vision and Pattern Recognition.2010:1030-1037 [9] Zeng Cheng-bin,Ma Hua-dong.Robust Head-Shoulder Detec-tion by PCA-Based Multilevel HOG-LBP Detector for People Counting[C]∥Proceedings of the 2010 20th International Conference on Pattern Recognition.2010:2069-2072 [10] Wojek C,Schiele B.A performance evaluation of single andmulti-featrue people detection[C]∥Proc.DAGMJ.2008 [11] Ojala T,Pietikainen M.A comparetive study of texture meas-ures with classification based on feature distributions[J].Pattern Recognition,1996,19(3):51-59 [12] Mu Y,Yan S,Liu Y.Discriminative local binary patterns for pedestrain detection in personal album[C]∥Proc.IEEE CVPR.2008 [13] MIT Database.http://db.csail.mit.edu/.MIT-CBCL Pedestrian Database [14] INRIA Database.http://pascal.inrialpes.fr/data/human/ [15] CASIA GAIT.http://www.cbsr.ia.ac.cn/english/Gait%20Databases.asp |
No related articles found! |
|