计算机科学 ›› 2016, Vol. 43 ›› Issue (6): 308-311.doi: 10.11896/j.issn.1002-137X.2016.06.061
甘玲,邹宽中,刘肖
GAN Ling, ZOU Kuan-zhong and LIU Xiao
摘要: 在行人检测中,针对梯度方向直方图(HOG)冗余信息过多、检测速度慢等不足,提出了运用PCA降维的多特征级联的行人检测。首先利用PCA对HOG特征进行降维,其次将HOG特征和Gabor特征、颜色特征级联作为行人检测的特征,最后使用SVM的径向基(RBF)核函数进行分类。在INRIA行人库上的实验表明,该方法不但提高了分类的速度,而且提高了检测的准确率。
[1] Haritaoglu I,Harwood D,Davis LS,et al.Real-time Surveillance of People and Their Activities[J].Transactions on PatternAnalysis and Machine Intelligence,2000,2(1):809-830 [2] Doll’ar P,Wojek C,Schiele B,et al.Pedestrian detection:anevaluation of the state of the art[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,2012,34(4):743-761 [3] Jia Hui-xing,Zhang Yu-jin.Summary of driver assistance systems based on computer vision pedestrian detection[J].Automation Journal,2007,3(1):84-90(in Chinese) 贾慧星,章毓晋.车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J].自动化学报,2007,3(1):84-90 [4] Chen Yi-ru.Research and implementation of pedestrian detection algorithm based on vision[D].Hangzhou:Zhejiang University,2014(in Chinese) 陈益如.基于视觉的行人检测算法的研究与实现[D].杭州:浙江大学,2014 [5] Wang Ning-bo.Pedestrian detection based on RGB-D[D].Hang-zhou:Zhejiang University,2013(in Chinese) 王宁波.基于RGB-D的行人检测[D].杭州:浙江大学,2013 [6] Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]∥Proc.IEEE CVPR.2005:886-893 [7] Dollar P,Wojek C,Schiele B,et al.Pedestrian detection:Abenchmark[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2009:304-311 [8] Benenson R,Omran M,Hosang J,et al.Ten Years of Pedestrian Detection,What Have We Learned?[M]∥ Computer Vision-ECCV 2014 Workshops.2015:613-627 [9] Wang Cheng-liang,Zhou Jia,Huang Sheng.Fast moving human detection based on Gauss mixture model and PCA-HOG[J].Computer Application Research,2012,9(6):2156-2160(in Chinese) 汪成亮,周佳,黄晟.基于高斯混合模型与PCA-HOG的快速运动人体检测[J].计算机应用研究,2012,9(6):2156-2160 [10] Wang X,Han T X,Yan S.An HOG-LBP human detector with partial occlusion handling[C]∥2009 IEEE 12th International Conference on Computer Vision.IEEE,2009:32-39 [11] Maji S,Berg A,Malik J.Classification using inter section kernel SVMs is efficient[C]∥Proc.IEEE CVPR.2008:1-8 |
No related articles found! |
|