A two-way crowd-counting network with a multiscale attention mechanism was proposed for the problem of semantic dissonance caused by large-scale variation of the crowd, background interference, and feature fusion in dense crowd-counting tasks.The network consisted of a backbone network, a scale enhancement module, a multi-scale module, a context attention module, and an attention mask branch network. Firstly, the scale enhancement module captured the crowd features at different scales and learns the importance of each feature on the image,the refore,adaptation to rapid scale changes arreenhanced. Secondly, the multi-scale module transformed the feature map at multiple scales while maintaining the original size of the feature map, so that different crowd densities can be adapted by network. Thirdly, the context attention module adaptively weighted local and global context information to optimize feature fusion and mitigate semantic inconsistency caused by features at different levels. Finally, the attention mask branch network generates masks related to the input image scale,the influence of background interference on network performance was reduced. The coordinated use of these four modules effectively,the accuracy and stability of dense crowd counting tasks are improved. Experimental results on multiple datasets demonstrate the effectiveness and feasibility of the proposed method.
WangC, ZhangH, YangL,et al.Deep people counting in extremely dense crowds[C]//Proceedings of the 23rd ACM international conference on Multimedia.Brisbane,Australia.New York,USA:ACM,2015:1299-1302.
[2]
ZhangY Y, ZhouD S, ChenS Q,et al.Single-image crowd counting via multi-column convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,USA:IEEE,2016:589-597.
[3]
LiY H, ZhangX F, ChenD M.CSRNet:dilated convolutional neural networks for understanding the highly congested scenes[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake,USA:IEEE,2018:1091-1100.
[4]
ZhuL, ZhaoZ J, LuC,et al.Dual path multi-scale fusion networks with attention for crowd counting[EB/OL].(2019-02-04)[2023-01-06].
[5]
HossainM, HosseinzadehM, ChandaO,et al.Crowd counting using scale-aware attention networks[C]//2019 IEEE Winter Conference on Applications of Computer Vision (WACV).Waikoloa,USA:IEEE,2019:1280-1288.
[6]
SimonyanK, ZissermanA.Very deep convolutional networks for large-scale image recognition[EB/OL].(2014-09-04)[2023-01-06]2014:arXiv:1409.1556.
[7]
CipollaR, GalY, KendallA.Multi-task learning using uncertainty to weigh losses for scene geometry and semantics[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake,USA:IEEE,2018:7482-7491.
[8]
SamD B, SuryaS, BabuR V.Switching convolutional neural network for crowd counting[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,USA:IEEE,2017:4031-4039.
[9]
SunZ Y.Coarse-to-fine network for crowd counting[C]//2022 IEEE International Conference on Electrical Engineering,Big Data and Algorithms (EEBDA).Changchun,China:IEEE,2022:1342-1346.
[10]
LiuW Z, SalzmannM, FuaP.Context-aware crowd counting[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach,USA:IEEE,2020:5094-5103.
[11]
KalyaniG, JanakiramaiahB, Narasimha PrasadL V,et al.Efficient crowd counting model using feature pyramid network and ResNeXt[J].Soft Computing,2021,25(15):10497-10507.
[12]
ZhugeJ C, DingN N, XingS J,et al.An improved deep multiscale crowd counting network with perspective awareness[J].Optoelectronics Letters,2021,17(6):367-372.
[13]
ZhouJ T, ZhangL, DuJ W,et al.Locality-aware crowd counting[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(7):3602-3613.
IdreesH, SaleemiI, SeibertC,et al.Multi-source multi-scale counting in extremely dense crowd images[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition.Portland,USA:IEEE,2013:2547-2554.
[16]
IdreesH, TayyabM, AthreyK,et al.Composition loss for counting,density map estimation and localization in dense crowds[C]//European Conference on Computer Vision.Cham,Switzerland:Springer,2018:544-559.
OhM H, OlsenP, RamamurthyK N.Crowd counting with decomposed uncertainty[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):11799-11806.