基于运动特征及位置估计的行人检测算法
|
摘要
根据行人运动的特点和行人在图像中位置与身高的对应关系,提出了一种结合运动特征与位置估计的行人检测算法。提取运动特征和聚合通道特征(ACF),将提取的特征放到Real Adaboost分类器里进行训练,并对行人可能存在的位置建立评估模型;在检测阶段,通过分类器确定行人的候选区域,然后采用非极大值抑制算法去除重叠窗口,最后对行人候选区域应用位置评估模型进一步判断,以此排除可能的非行人目标。实验采用Caltech数据集对算法进行仿真,该算法的平均对数漏检率为27.12%,与ACF算法的相比降低了5.9个百分点。实验表明运动特征在视频检测中能够与静态特征进行信息互补,同时行人的位置估计在摄像机固定的情况下,具有一定的判断能力。
According to the characteristics of the movement of pedestrians and the correspondence between position and height of pedestrians in images, the pedestrian detection algorithm combining motion feature with location estimation is proposed. The motion feature and the Aggregated Channel Features(ACF)are extracted, then these features are trained by the classifier, and an evaluation model is built on the possible position of pedestrians. In the detection stage, the candidate pedestrian areas are determined by the classifier, and then the non maximum suppression algorithm is used to eliminate redundant windows. Finally, the model of position evaluation is used to judge the pedestrian candidate regions to eliminate non-target pedestrian. In the experiment, the Caltech data set is used in the simulation of the algorithm, the results show that our algorithm achieves a Log-Average Miss Rate(LAMR)of 27.12%. Compared with the ACF algorithm, LAMR is decreased by 5.9%. The results of the experiment testify that motion feature can be used as a complementation of static feature, and location estimation of pedestrian has certain ability to distinguish when the camera is fixed.
According to the characteristics of the movement of pedestrians and the correspondence between position and height of pedestrians in images, the pedestrian detection algorithm combining motion feature with location estimation is proposed. The motion feature and the Aggregated Channel Features(ACF)are extracted, then these features are trained by the classifier, and an evaluation model is built on the possible position of pedestrians. In the detection stage, the candidate pedestrian areas are determined by the classifier, and then the non maximum suppression algorithm is used to eliminate redundant windows. Finally, the model of position evaluation is used to judge the pedestrian candidate regions to eliminate non-target pedestrian. In the experiment, the Caltech data set is used in the simulation of the algorithm, the results show that our algorithm achieves a Log-Average Miss Rate(LAMR)of 27.12%. Compared with the ACF algorithm, LAMR is decreased by 5.9%. The results of the experiment testify that motion feature can be used as a complementation of static feature, and location estimation of pedestrian has certain ability to distinguish when the camera is fixed.
引文
[1]Dollar P,Wojek C,Schiele B,et al.Pedestrian detection:an evaluation of the state of the art[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):743-761.
[2]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,2007,33(1):84-90.
[3]Geronimo D,Lopez A M,Sappa A D,et al.Survey of pedestrian detection for advanced driver assistance systems[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1239-1258.
[4]Oren M,Papageorgiou C,Sinha P,et al.Pedestrian detection using wavelet templates[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,1997:193.
[5]Wu B,Nevatia R.Detection of multiple,partially occludedè?êè?humans in a single image by bayesian combination of edgelet part detectors[C]//Proceedings of Tenth IEEEInternational Conference on Computer Vision,2005:90-97.
[6]Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:886-893.
[7]Watanabe T,Ito S,Yokoi K.Co-occurrence histograms of oriented gradients for pedestrian detection[C]//Proceedings of Pacific Rim Symposium on Advances in Image and Video Technology,2009:37-47.
[8]Ojala T,Pietikainen M,Harwood D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996,19(3):51-59.
[9]Mu Y,Yan S,Liu Y,et al.Discriminative local binary patterns for human detection in personal album[C]//IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[10]Wang X.An HOG-LBP human detector with partial occlusion handling[C]//Proc of IEEE Int Conf on Computer Vision,Kyoto,Japan,2009:32-39.
[11]Walk S,Majer N,Schindler K,et al.New features and insights for pedestrian detection[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2010:1030-1037.
[12]Wu J,Rehg J M.CENTRIST:A visual descriptor for scene categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1489-1501.
[13]Wu J,Geyer C,Rehg J M.Real-time human detection using contour cues[C]//Proceedings of IEEE International Conference on Robotics and Automation,2011:860-867.
[14]Tuzel O,Porikli F,Meer P.Pedestrian detection via classification on Riemannian manifolds[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(10):1713.
[15]Dollár P,Tu Z,Perona P,et al.Integral channel features[C]//Proceedings of British Machine Vision Conference,London,UK,September 7-10,2009.
[16]Dollár P,Belongie S,Perona P.The fastest pedestrian detector in the west[C]//Proceedings of British Machine Vision Conference,Aberystwyth,UK,August 31-September 3,2010.
[17]Benenson R,Mathias M,Tuytelaars T,et al.Seeking the strongest rigid detector[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,2013:3666-3673.
[18]Dollar P,Belongie S,Belongie S,et al.Fast feature pyramids for object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(8):1532-1545.
[19]Zhang S,Bauckhage C,Cremers A B.Informed Haar-like features improve pedestrian detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2014:947-954.
[20]Zhang S,Benenson R,Schiele B.Filtered channel features for pedestrian detection[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,2015:1751-1760.
[21]Paisitkriangkrai S,Shen C,Hengel A V D.Strengthening the effectiveness of pedestrian detection with spatially pooled features[J].Lecture Notes in Computer Science,2014,8692:546-561.
[22]Viola P,Jones M J.Snow D.Detecting pedestrians using patterns of motion and appearance[J].International Journal of Computer Vision,2003,63(2):153-161.
[23]Dalal N,Triggs B,Schmid C.Human detection using oriented histograms of flow and appearance[C]//Proceedings of European Conference on Computer Vision,2006:428-441.
[24]Horn B K P,Schunck B G.Determining optical flow[J].Artificial Intelligence,1981,17(1/3):185-203.
[25]Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]//Proceedings of International Joint Conference on Artificial Intelligence,1981:674-679.
[26]Shapire R E,Singer Y.Improved boosting algorithms using confidence-ratedpredictions[J].Machine Learning,1999,37(3):297-336.
[27]Park D,Zitnick C L,Ramanan D,et al.Exploring weak stabilization for motion feature extraction[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2013:2882-2889.
[28]庞彦伟,尚楚博,何宇清.基于尺度不变特征和位置先验的行人检测算法[J].天津大学学报(自然科学与工程技术版),2017,50(9):946-952.
[29]Walk S,Majer N,Schindler K,et al.New features and insights for pedestrian detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2010:1030-1037.
[30]Ouyang W,Wang X.Single-pedestrian detection aided by multi-pedestrian detection[C]//Proceedings of Confrence on Computer Vision and Pattern Recognition,2013:3198-3205.
[2]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,2007,33(1):84-90.
[3]Geronimo D,Lopez A M,Sappa A D,et al.Survey of pedestrian detection for advanced driver assistance systems[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1239-1258.
[4]Oren M,Papageorgiou C,Sinha P,et al.Pedestrian detection using wavelet templates[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,1997:193.
[5]Wu B,Nevatia R.Detection of multiple,partially occludedè?êè?humans in a single image by bayesian combination of edgelet part detectors[C]//Proceedings of Tenth IEEEInternational Conference on Computer Vision,2005:90-97.
[6]Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:886-893.
[7]Watanabe T,Ito S,Yokoi K.Co-occurrence histograms of oriented gradients for pedestrian detection[C]//Proceedings of Pacific Rim Symposium on Advances in Image and Video Technology,2009:37-47.
[8]Ojala T,Pietikainen M,Harwood D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996,19(3):51-59.
[9]Mu Y,Yan S,Liu Y,et al.Discriminative local binary patterns for human detection in personal album[C]//IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[10]Wang X.An HOG-LBP human detector with partial occlusion handling[C]//Proc of IEEE Int Conf on Computer Vision,Kyoto,Japan,2009:32-39.
[11]Walk S,Majer N,Schindler K,et al.New features and insights for pedestrian detection[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2010:1030-1037.
[12]Wu J,Rehg J M.CENTRIST:A visual descriptor for scene categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1489-1501.
[13]Wu J,Geyer C,Rehg J M.Real-time human detection using contour cues[C]//Proceedings of IEEE International Conference on Robotics and Automation,2011:860-867.
[14]Tuzel O,Porikli F,Meer P.Pedestrian detection via classification on Riemannian manifolds[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(10):1713.
[15]Dollár P,Tu Z,Perona P,et al.Integral channel features[C]//Proceedings of British Machine Vision Conference,London,UK,September 7-10,2009.
[16]Dollár P,Belongie S,Perona P.The fastest pedestrian detector in the west[C]//Proceedings of British Machine Vision Conference,Aberystwyth,UK,August 31-September 3,2010.
[17]Benenson R,Mathias M,Tuytelaars T,et al.Seeking the strongest rigid detector[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,2013:3666-3673.
[18]Dollar P,Belongie S,Belongie S,et al.Fast feature pyramids for object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(8):1532-1545.
[19]Zhang S,Bauckhage C,Cremers A B.Informed Haar-like features improve pedestrian detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2014:947-954.
[20]Zhang S,Benenson R,Schiele B.Filtered channel features for pedestrian detection[C]//Proceedings of Conference on Computer Vision and Pattern Recognition,2015:1751-1760.
[21]Paisitkriangkrai S,Shen C,Hengel A V D.Strengthening the effectiveness of pedestrian detection with spatially pooled features[J].Lecture Notes in Computer Science,2014,8692:546-561.
[22]Viola P,Jones M J.Snow D.Detecting pedestrians using patterns of motion and appearance[J].International Journal of Computer Vision,2003,63(2):153-161.
[23]Dalal N,Triggs B,Schmid C.Human detection using oriented histograms of flow and appearance[C]//Proceedings of European Conference on Computer Vision,2006:428-441.
[24]Horn B K P,Schunck B G.Determining optical flow[J].Artificial Intelligence,1981,17(1/3):185-203.
[25]Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]//Proceedings of International Joint Conference on Artificial Intelligence,1981:674-679.
[26]Shapire R E,Singer Y.Improved boosting algorithms using confidence-ratedpredictions[J].Machine Learning,1999,37(3):297-336.
[27]Park D,Zitnick C L,Ramanan D,et al.Exploring weak stabilization for motion feature extraction[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2013:2882-2889.
[28]庞彦伟,尚楚博,何宇清.基于尺度不变特征和位置先验的行人检测算法[J].天津大学学报(自然科学与工程技术版),2017,50(9):946-952.
[29]Walk S,Majer N,Schindler K,et al.New features and insights for pedestrian detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2010:1030-1037.
[30]Ouyang W,Wang X.Single-pedestrian detection aided by multi-pedestrian detection[C]//Proceedings of Confrence on Computer Vision and Pattern Recognition,2013:3198-3205.