Counting with Self-Weighted Multi-Scale Fusion Networks

被引:0
|
作者
Xiong, Xin [1 ]
Shen, Jie [1 ]
Li, Ying [1 ]
He, Wei [1 ]
Li, Peng [1 ]
Yan, Wenjie [1 ]
机构
[1] Univ Elect Sci & Technol China, Chengdu, Peoples R China
关键词
Crowd counting; density estimation; multi-scale fusion; CONVOLUTIONAL NEURAL-NETWORK; CROWD; MODEL;
D O I
10.1142/S0218001423550078
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Because of the large-scale variation, counting in scenes of different densities is an extremely difficult task. In this paper, based on the attention mechanism, we propose a new self-weighted multi-scale fusion network structure named SMFNet to solve the problem of multi-scale changes and can significantly improve the effect of crowd counting in monitoring scene. The proposed SMFNet uses VGG as the backbone network to extract multi-scale features, uses a SMFNet as the neck to fuse multiple-scale features, and uses the atrous spatial pyramid pooling (ASPP) network and ordinary convolution as the head to generate both the attention map and the density map. The attention map highlighting crowd regions in the image contributes to a high-quality density map, and the density map records the crowd distribution. The number of crowd in the image can be obtained by summing the pixel values of the density map. We conduct experiments on three crowd counting datasets and one vehicle counting dataset to show that our proposed SMFNet can improve the state-of-the-art counting methods.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Self-Weighted Contrastive Fusion for Deep Multi-View Clustering
    Wu, Song
    Zheng, Yan
    Ren, Yazhou
    He, Jing
    Pu, Xiaorong
    Huang, Shudong
    Hao, Zhifeng
    He, Lifang
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 9150 - 9162
  • [2] Crowd counting based on attention-guided multi-scale fusion networks
    Zhang, Bo
    Wang, Naiyao
    Zhao, Zheng
    Abraham, Ajith
    Liu, Hongbo
    [J]. NEUROCOMPUTING, 2021, 451 : 12 - 24
  • [3] Ship detection based on multi-scale weighted fusion*
    Zhou, Weina
    Peng, Yujie
    [J]. DISPLAYS, 2023, 78
  • [4] Crowd Counting by Multi-Scale Dilated Convolution Networks
    Dong, Jingwei
    Zhao, Ziqi
    Wang, Tongxin
    [J]. ELECTRONICS, 2023, 12 (12)
  • [5] MULTI-SCALE CONVOLUTIONAL NEURAL NETWORKS FOR CROWD COUNTING
    Zeng, Lingke
    Xu, Xiangmin
    Cai, Bolun
    Qiu, Suo
    Zhang, Tong
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 465 - 469
  • [6] Multi-scale Generative Adversarial Networks for Crowd Counting
    Yang, Jianxing
    Zhou, Yuan
    Kung, Sun-Yuan
    [J]. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 3244 - 3249
  • [7] Double multi-scale feature fusion network for crowd counting
    Liu, Qian
    Fang, Jiongtao
    Zhong, Yixiong
    Wang, Cunbao
    Qi, Youwei
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 34 (81831-81855)
  • [8] The weighted multi-scale connections networks for macrodispersivity estimation
    Zhou, Zhengkun
    Ji, Kai
    [J]. JOURNAL OF CONTAMINANT HYDROLOGY, 2024, 265
  • [9] Multi-scale dilated convolution of feature Fusion Network for Crowd counting
    Liu, Donghua
    Wang, Guodong
    Zhai, Guangtao
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (26) : 37939 - 37952
  • [10] Multi-scale dilated convolution of feature Fusion Network for Crowd counting
    Donghua Liu
    Guodong Wang
    Guangtao Zhai
    [J]. Multimedia Tools and Applications, 2022, 81 : 37939 - 37952