基于背景抑制与上下文感知的人群计数网络

doi:10.19678/j.issn.1000-3428.0062606

摘要/Abstract

摘要： 针对图像背景噪声、透视畸变等影响人群计数网络计数精度的问题，提出一种基于背景抑制与上下文感知的新网络。利用VGG-16网络提取图像特征，并分别将特征输入密度图生成模块和背景噪声抑制（BNS）模块中进行处理，生成密度特征图和空间注意力图。使用BNS模块优化密度特征图并生成初级密度图，以抑制图像中背景噪声干扰，提高人群区域的特征权重。为减少透视畸变对人群密度估计的影响，使用上下文感知增强网络优化初级密度图，并生成预测密度图。在ShanghaiTech、UCF-CC-50及UCF-QNRF 3个公开数据集上的实验结果表明，该网络相较于MCNN、SwitchCNN、CSRNet等网络的计算准确度较高，尤其在UCF-QNRF数据集上其平均绝对误差和均方误差分别为85.8、146.0，相较于其他网络最高分别下降69.0%和67.2%，能充分抑制图像背景噪声并有效减小透视畸变引起的误差，具有良好的泛化能力和较强的鲁棒性。

关键词: 人群计数, 深度学习, 密度图, 背景噪声, 上下文感知

Abstract: To reduce the influence of background noise and perspective distortion in crowd counting tasks, a new network based on background suppression and context awareness is proposed.VGG-16 network is used to extract image features, which are input into Density Map Generation (DMG) and Background Noise Suppression(BNS) modules for processing to generate density feature and spatial attention maps.The BNS module is used to optimize a density feature map and generate a primary density map, to suppress noise information interference in the image and improve the characteristic weight of the crowd area.To reduce the influence of perspective distortion on counting density estimation, a Weight Enhancement-Context Aware Network (WE-CAN) is used to optimize the primary density map and generate the predicted density map.Experiment results on three public datasets, namely ShanghaiTech, UCF-CC-50 and UCF-QNRF show that the network has higher computational accuracy than Multi-Column Convolutional Neural Network (MCNN), Switching Convolutional Neural Network (SwitchCNN), Congested Scene Recognition Network(CSRNet) and other networks.Especially on UCF-QNRF, the Mean Absolute Error(MAE) of the proposed algorithm reach 85.8, and the Mean Square Error (MSE) reach 146.0.Compared with other algorithms, the highest decrease is 69.0% and 67.2%, respectively.The network proposed can also suppress background noise, reduce the error caused by perspective distortion, and has good accuracy and robustness.

Key words: crowd counting, deep learning, density map, background noise, context awareness

中图分类号:

TP391.41

黄奕秋, 胡晓, 杨佳信, 欧嘉敏. 基于背景抑制与上下文感知的人群计数网络[J]. 计算机工程, 2022, 48(9): 314-320.

HUANG Yiqiu, HU Xiao, YANG Jiaxin, OU Jiamin. Crowd Counting Network Based on Background Suppression and Context Awareness[J]. Computer Engineering, 2022, 48(9): 314-320.

http://www.ecice06.com/CN/Y2022/V48/I9/314

图/表 8

20221017111646

20221017111650

20221017111654

20221017111657

20221017111701

20221017111704

20221017111708

20221017111711

参考文献

[1] IDREES H, SOOMRO K, SHAH M.Detecting humans in dense crowds using locally-consistent scale prior and global occlusion reasoning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(10):1986-1998.
[2] OJALA T, PIETIKAINEN M, MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7):971-987.
[3] CHAN A B, VASCONCELOS N.Bayesian poisson regression for crowd counting[C]//Proceedings of the 12th International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2009:545-551.
[4] 冯兴杰, 张乐, 曾云泽.基于多注意力CNN的问题相似度计算模型[J].计算机工程, 2019, 45(9):284-290. FENG X J, ZHANG L, ZENG Y Z.Question similarity calculation model based on multi-attention CNN[J].Computer Engineering, 2019, 45(9):284-290.(in Chinese)
[5] CHOLLET F.Xception:deep learning with depthwise separable convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1800-1807.
[6] ZHANG C, LI H S, WANG X G, et al.Cross-scene crowd counting via deep convolutional neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:833-841.
[7] ZHANG Y Y, ZHOU D S, CHEN S Q, et al.Single-image crowd counting via multi-column convolutional neural network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:589-597.
[8] SAM D B, SURYA S, BABU R V.Switching convolutional neural network for crowd counting[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:4031-4039.
[9] LI Y H, ZHANG X F, CHEN D M.CSRNet:dilated convolutional neural networks for understanding the highly congested scenes[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:1091-1100.
[10] LIU W Z, SALZMANN M, FUA P.Context-aware crowd counting[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:5094-5103.
[11] JIANG X H, ZHANG L, XU M L, et al.Attention scaling for crowd counting[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:4705-4714.
[12] ZHU L, ZHAO Z J, LU C, et al.Dual path multi-scale fusion networks with attention for crowd counting[EB/OL].[2021-09-06].https://arxiv.org/abs/1902.01115.
[13] 马皓, 殷保群, 彭思凡.基于特征金字塔网络的人群计数算法[J].计算机工程, 2019, 45(7):203-207. MA H, YIN B Q, PENG S F.Crowd counting algorithm based on feature pyramid network[J].Computer Engineering, 2019, 45(7):203-207.(in Chinese)
[14] LIN T Y, DOLLÁR P, GIRSHICK R, et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:936-944.
[15] WANG Q L, WU B G, ZHU P F, et al.ECA-net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:11531-11539.
[16] CHEN L C, PAPANDREOU G, KOKKINOS I, et al.DeepLab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
[17] 翟强, 王陆洋, 殷保群, 等.基于尺度自适应卷积神经网络的人群计数算法[J].计算机工程, 2020, 46(2):250-254, 261. ZHAI Q, WANG L Y, YIN B Q, et al.Crowd counting algorithm based on scale adaptive convolutional neural network[J].Computer Engineering, 2020, 46(2):250-254, 261.(in Chinese)
[18] HU J, SHEN L, SUN G.Squeeze-and-excitation networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:7132-7141.
[19] IDREES H, SALEEMI I, SEIBERT C, et al.Multi-source multi-scale counting in extremely dense crowd images[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2013:2547-2554.
[20] IDREES H, TAYYAB M, ATHREY K, et al.Composition loss for counting, density map estimation and localization in dense crowds[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:544-559.
[21] CAO X K, WANG Z P, ZHAO Y Y, et al.Scale aggregation network for accurate and efficient crowd counting[C]//Proceedings of 2018 European Conference on Computer Vision.Berlin, Germany:Springer, 2018:757-773.
[22] ZHANG A R, SHEN J Y, XIAO Z H, et al.Relational attention network for crowd counting[C]//Proceedings of IEEE/CVF International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:6787-6796.
[23] TIAN Y K, LEI Y M, ZHANG J P, et al.PaDNet:pan-density crowd counting[J].IEEE Transactions on Image Processing, 2020, 29:2714-2727.
[24] JIANG X H, ZHANG L, ZHANG T Z, et al.Density-aware multi-task learning for crowd counting[J].IEEE Transactions on Multimedia, 2021, 23:443-453.
[25] YI Q S, LIU Y X, JIANG A W, et al.Scale-aware network with regional and semantic attentions for crowd counting under cluttered background[EB/OL].[2021-08-01].https://arxiv.org/abs/2101.01479.

选择文件类型/文献管理软件名称

选择包含的内容