摘要
由于单张图片人群计数存在严重的人群遮挡和尺度变化问题,导致人群计数算法性能明显下降。为此,提出一种基于特征金字塔网络对图片进行人群计数的算法,并给出能够处理任意图片分辨率的全卷积网络。将特征金字塔网络应用到人群计数中,通过逐层融合网络中不同尺度的特征图来解决图片中的上述问题。在人群计数数据库ShanghaiTech上对网络模型进行训练和性能评测,结果表明,与当前主流的人群计数算法相比,该算法具有更高的鲁棒性和准确性。
The single-picture crowd count has a sharp decline in performance due to severe population occlusion and scale changes.Therefore,this paper proposes an algorithm for crowd counting pictures,and gives a Full Convolution Network(FCN) capable of processing the resolution of any picture.The scale change and occlusion problems in the picture are solved by applying the feature pyramid network to the crowd count.The network model is trained and evaluated in the crowd counting database ShanghaiTech,results show that the algorithm has good robustness and accuracy compared with the current mainstream crowd counting algorithm.
引文
[1] LIN Shengfu,CHEN J Y,CHAO Huangxin.Estimation of number of people in crowded scenes using perspective transformation[J].IEEE Transactions on Systems,2001,31(6):645-654.
[2] WU Bo,NEVATIA R.Detection of multiple,partially occluded humans in a single image by Bayesian combination of edgelet part detectors[C]//Proceedings of the 10th IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2005:90-97.
[3] LI Min,ZHANG Zhaoxiang,HUANG Kaiqi,et al.Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection[C]//Proceedings of the 19th International Conference on Pattern Recognition.Tampa,USA:IEEE Press,2008:1-4.
[4] ZHAO Tao,NEVATIA R,WU Bo.Segmentation and tracking of multiple humans in crowded environments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(7):1198-1211.
[5] GE W,COLLINS R T.Marked point processes for crowd counting[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,USA:IEEE Press,2009:2913-2920.
[6] WANG Meng,WANG Xiaogang.Automatic adaptation of a generic pedestrian detector to a specific traffic scene[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Colorado Springs,USA:IEEE Press,2011:3401-3408.
[7] 李云波,唐斯琪,周星宇,等.可伸缩模块化CNN人群计数方法[J].计算机科学,2018,45(8):17-21,40.
[8] CHAN A B,LIANG Z S J,Vasconcelos N.Privacy preserving crowd monitoring:counting people without people models or tracking[C]//Proceedings of the 10th IEEE International Conference on Computer Vision and Pattern Recognition.Anchorage,USA:IEEE Press,2008:1-7.
[9] CHEN K,LOY C C,GONG S,et al.Feature mining for localised crowd counting[C]//Proceedings of BMVC’12.London,UK:[s.n.],2012:3.
[10] LEMPITSKY V,ZISSERMAN A.Learning to count objects in images[C]//Proceedings of Advances in Neural Information Processing Systems.Vancouver,Canada:[s.n.],2010:1324-1332.
[11] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Boston,USA:IEEE Press,2015:3431-3440.
[12] MAGGIORI E,TARABALKA Y,CHARPIAT G,et al.Convolutional neural networks for large-scale remote-sensing image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(2):645-657.
[13] ZHANG Cong,LI Hongsheng,WANG Xiaogang,et al.Cross-scene crowd counting via deep convolutional neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Boston,USA:IEEE Press,2015:833-841.
[14] ZHANG Yingying,ZHOU Desan,CHEN Siqin,et al.Single-image crowd counting via multi-column convolutional neural network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA:IEEE Press,2016:589-597.
[15] 吴淑窈,刘希庚,胡昌振,等.基于卷积神经网络人群计数的研究与实现[J].科教导刊,2017(9):16-17.
[16] 唐斯琪,陶蔚,张梁梁,等.一种多列特征图融合的深度人群计数算法[J].郑州大学学报(理学版),2018,50(2):1-6.
[17] MARSDEN M,McGUINESS K,LITTLE S,et al.Fully convolutional crowd counting on highly congested scenes[EB/OL].[2018-05-20].https://www.researchgate.net/publication.
[18] SINDAGI V A,PATEL V M.Cnn-based cascaded multi-task learning of high-level prior and density estimation for crowd counting[C]//Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance.Lecce,Italy:IEEE Press,2017:1-6.
[19] LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,USA:[s.n.],2017:4-7.