Abstract：Aiming at the problem that the traditional video monitoring method can not divide the dense foreground objects accurately, a multi-target video monitoring method based on Adaboost and codebook model was proposed. Firstly, the Adaboost human head classifier was obtained by training, and the background model was established for the vertical elevator image by the codebook algorithm. The foreground image was extracted and heads were detected and tracked. After that, the pedestrian targets were removed to get the object targets, and the object targets were tracked. Finally, the movement of pedestrians and objects was monitored. The experimental results on 12 entrance area videos show that the method can track pedestrians and objects accurately and stably. It can accomplish the monitoring tasks of retrograde detection, passenger statistics, pedestrian congestion and object retention. With the processing speed of 36 frames per second, the tracking-accuracy rate is above 94% and the monitoring-accuracy rate is 95.8%. The proposed algorithm meets robustness, real-time and accuracy requirements of the intelligent video monitoring system.
杜启亮, 黎浩正, 田联房. 基于Adaboost和码本模型的手扶电梯出入口视频监控方法[J]. 计算机应用, 2017, 37(9): 2610-2616.
DU Qiliang, LI Haozheng, TIAN Lianfang. Video monitoring method of escalator entrance area based on Adaboost and codebook model. Journal of Computer Applications, 2017, 37(9): 2610-2616.
[1] 潘浩,高枝宝,何小海,等.基于计算机视觉的公交系统人流量检测算法[J].计算机工程,2007,33(11):216-218.(PAN H, GAO Z B, HE X H, et al. Pedestrian flow detection algorithm in public transport system based on computer vision[J]. Computer Engineering, 2007, 33(11):216-218.) [2] 顾德军,伍铁军.一种基于人头特征的人数统计方法研究[J].机械制造与自动化,2010,39(4):134-138.(GU D J, WU T J. Pedestrian count method based on head feature[J]. Machine Building & Automation, 2010, 39(4):134-138.) [3] 张姗姗,景文博,刘学,等.一种基于深度信息的人头检测方法[J].长春理工大学学报(自然科学版),2016,39(2):107-111.(ZHANG S S, JING W B, LIU X, et al. A head detection method based on depth information[J]. Journal of Changchun University of Science and Technology (Natural Science), 2016, 39(2):107-111.) [4] 文嘉俊,徐勇,战荫伟.基于AdaBoost和帧间特征的人数统计[J].中国图象图形学报,2011,16(9):1729-1735.(WEN J J, XU Y, ZHAN Y W. People counting based on AdaBoost and inter-frame features[J]. Journal of Image and Graphics, 2011, 16(9):1729-1735.) [5] LI B, ZHANG J, ZHANG Z, et al. A people counting method based on head detection and tracking[C]//Proceedings of the 2014 International Conference on Smart Computing. Washington, DC:IEEE Computer Society, 2014:136-141. [6] 朴春赫,潘怡霖,赵海,等.基于改进ViBe的多行人检测方法[J].东北大学学报(自然科学版),2016,37(4):481-485.(PAK C H, PAN Y L, ZHAO H, et al. Multi-pedestrian detection approach based on improved ViBe algorithm[J]. Journal of Northeastern University (Natural Science), 2016, 37(4):481-485.) [7] ZHAO L, THORPE C E. Stereo-and neural network-based pedestrian detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2000, 1(3):148-154. [8] KIM K, CHALIDABHONGSE T H, HARWOOD D, et al. Real-time foreground-background segmentation using codebook model[J]. Real-Time Imaging, 2005, 11(3):172-185. [9] KIM K, CHALIDABHONGSE T H, HARWOOD D, et al. Background modeling and subtraction by codebook construction[C]//Proceedings of the 2004 International Conference on Image Processing. Piscataway, NJ:IEEE, 2004, 5:3061-3064. [10] 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. Washington, DC:IEEE Computer Society, 2005, 1:886-893. [11] KÉGL B. The return of AdaBoost.MH:multi-class Hamming trees[EB/OL].[2016-12-20]. https://core.ac.uk/download/pdf/24989526.pdf. [12] KELLY A. A 3D state space formulation of a navigation Kalman filter for autonomous vehicles[EB/OL].[2016-12-20]. http://frc.ri.cmu.edu/users/alonzo/pubs/reports/kalman_V2.pdf. [13] POWERS D M W. Evaluation:from precision, recall and F-measure to ROC, informedness, markedness and correlation[J]. Journal of Machine Learning Technologies, 2011, 2(1):37-63.
2017, Vol. 37 
