计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 207-209.doi: 10.11896/j.issn.1002-137X.2016.6A.049
王坚,兰天
WANG Jian and LAN Tian
摘要： 针对行人检测技术在智能交通系统中的应用,为了提高行人检测方法的有效性、实时性和准确性,将稀疏表达应用到图像的特征压缩中,提出一种基于HOG和LTP特征训练SVM分类器进行行人检测的方法。基于HOG和LTP特征训练SVM分类器进行行人检测的方法有效地结合了图像的梯度特征和纹理特征,利用稀疏表达进行特征数据的压缩可以有效地加速算法。实验结果表明,提出的算法具有精度高、速度快等优点。
| [1] Zhou T,Tao D.Randomized low-rank & sparse matrix decomposition in noisy case[C]∥International Conference on Machine Learning.2011,3:2 [2] Zhang K,Zhang L,Yang M H.Real-time compressive tracking[M]∥Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:864-877 [3] Beleznai C,Schreiber D,Rauter M.Pedestrian detection usingGPU-accelerated multiple cue computation[C]∥2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).IEEE,2011:58-65 [4] Yan J,Lei Z,Yi D,et al.Multi-pedestrian detection in crowded scenes:A global view[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2012:3124-3129 [5] 苏松志,李绍滋,陈淑媛,等.行人检测技术综述[J].电子学报,2012,40(4):814-820 [6] Li Y,Lu W,Wang S,et al.Local Haar-like features in edge maps for pedestrian detection[C]∥2011 4th International Congress on Image and Signal Processing (CISP).IEEE,2011,3:1424-1427 [7] Baltieri D,Vezzani R,Cucchiara R.People orientation recognition by mixtures of wrapped distributions on random trees[M]∥Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:270-283 [8] Ouyang W,Wang X.A discriminative deep model for pedestrian detection with occlusion handling[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2012:3258-3265 |
| No related articles found! |
|
||
首页