计算机科学 ›› 2017, Vol. 44 ›› Issue (Z6): 173-178.doi: 10.11896/j.issn.1002-137X.2017.6A.040
高飞,丰敏强,汪敏倩,卢书芳,肖刚
GAO Fei, FENG Min-qiang, WANG Min-qian, LU Shu-fang and XIAO Gang
摘要： 行人统计在智能监控领域中具有重要意义,但复杂背景环境以及行人运动过程中出现的遮挡现象导致当前方法的准确率并不高。此外,传统过线统计人数的方式的实际适用范围有限。考虑到现有方法的不足,提出了一种基于热点区域定义的人数统计方法。首先,利用自适应学习率背景建模提取运动目标前景,得到前景区域的位置和大小,扫描计算运动目标前景范围内的HOG特征,并判别是否存在头肩目标；然后,利用基于KCF的目标匹配算法跟踪头肩目标；最后,结合目标运动轨迹与提出的区域人数统计算法进行行人人数统计。采用 24fps的手机拍摄 的长度为10min、分辨率为960×720像素 的视频做人数统计实验。实验结果表明,所提算法在统计人数时正确率可达到93.1%,能满足实时性要求。该方法结合了检测效率和准确率,在背景环境复杂的场景下具有良好的效果,能适应各类人数统计的实际应用场景。
| [1] HASHEMZADEH M,FARAJZADEH N.Combining keypoint-based and segment-based features for counting people in crowded scenes[J].Information Sciences An International Journal,2016,5(C):199-216. [2] 常庆龙,夏洪山,黎宁.一种基于归一化前景和角点信息的复杂场景人数统计方法[J].电子与信息学报,2014,36(2):312-317. [3] CONG Y,GONG H,ZHU S C,et al.Flow mosaicking:Real-time pedestrian counting without Scene-specific learning[C]∥IEEE Conference on Computer Vision & Pattern Recognition.2009:1093-1100. [4] CHEN C L,CHEN K,GONG S,et al.Crowd Counting and Profiling:Methodology and Evaluation[M]∥Modeling,Simulation and Visual Analysis of Crowds.Springer New York,2013:347-382. [5] DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2005:886-893. [6] FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object Detection with Discriminatively Trained Part-Based Models[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,32(9):1627-1645. [7] HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]∥IEEE Conference on Computer Vision & Pattern Recognition.2016:770-778. [8] REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]∥IEEE Confe-rence on Computer Vision & Pattern Recognition.2016:779-788. [9] 唐春晖.一种基于梯度方向直方图的俯视行人的检测方法[J].模式识别与人工智能,2015,28(1):19-26. [10] 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. [11] 徐超,高梦珠,查宇锋,等.基于HOG和SVM的公交乘客人流量统计算法[J].仪器仪表学报,2015,36(2):446-452. [12] 周治平,许伶俐,李文慧.特征回归与检测结合的人数统计方法[J].计算机辅助设计与图形学学报,2015,27(3):425-432. [13] LIU J,ZHANG M.A detection and tracking based method for real-time people counting[C]∥Chinese Automation Congress.2013:470-473. [14] 郑翔翔,张怡.基于头部检测和跟踪的人数统计方法[J].计算机应用与软件,2011,28(2):44-46. [15] 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. [16] 夏菁菁,高琳,范勇,等.基于骨架特征的人数统计[J].计算机应用,2014,34(2):585-588. [17] HENRIQUES J F,RUI C,MARTINS P,et al.High-SpeedTracking with Kernelized Correlation Filters[J].IEEE Transa-ctions on Pattern Analysis & Machine Intelligence,2015,37(3):583-596. [18] ZHANG K,ZHANG L,YANG M H.Real-time compressivetracking[M]∥Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:864-877. [19] KALAL Z,MIKOLAJCZYK K,MATAS J.Tracking-learning-detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(7):1409-1422. [20] HARE S,SAFFARI A,TORR P H S.Struck:Structured output tracking with kernels[C]∥International Conference on Computer Vision.IEEE Trans Pattern Anal Mach Intell,2011:263-270. |
| No related articles found! |
|
||
首页