Dense Vehicle Counting Estimation via a Synergism Attention Network

被引:6
作者
Jin, Yiting [1 ]
Wu, Jie [1 ]
Wang, Wanliang [1 ]
Wang, Yibin [1 ]
Yang, Xi [1 ]
Zheng, Jianwei [1 ]
机构
[1] Zhejiang Univ Technol, Coll Comp Sci & Engn, Hangzhou 310014, Peoples R China
基金
中国国家自然科学基金;
关键词
synergism transformer; vehicle counting; pyramid framework; attention cumulative; convolution neural networks;
D O I
10.3390/electronics11223792
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Along with rising traffic jams, accurate counting of vehicles in surveillance images is becoming increasingly difficult. Current counting methods based on density maps have achieved tremendous improvement due to the prosperity of convolution neural networks. However, as highly overlapping and sophisticated large-scale variation phenomena often appear within dense images, neither traditional CNN methods nor fixed-size self-attention transformer methods can implement exquisite counting. To relieve these issues, in this paper, we propose a novel vehicle counting approach, namely the synergism attention network (SAN), by unifying the benefits of transformers and convolutions to perform dense counting assignments effectively. Specifically, a pyramid framework is designed to adaptively utilize the multi-level features for better fitting in counting tasks. In addition, a synergism transformer (SyT) block is customized, where a dual-transformer structure is equipped to capture global attention and location-aware information. Finally, a Location Attention Cumulation (LAC) module is also presented to explore the more efficient and meaningful weighting regions. Extensive experiments demonstrate that our model is very competitive and reached new state-of-the-art performance on TRANCOS datasets.
引用
收藏
页数:11
相关论文
共 28 条
[11]   Swin Transformer: Hierarchical Vision Transformer using Shifted Windows [J].
Liu, Ze ;
Lin, Yutong ;
Cao, Yue ;
Hu, Han ;
Wei, Yixuan ;
Zhang, Zheng ;
Lin, Stephen ;
Guo, Baining .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :9992-10002
[12]  
Ma Z., 2021, CVPR, P3205
[13]   Towards Perspective-Free Object Counting with Deep Learning [J].
Onoro-Rubio, Daniel ;
Lopez-Sastre, Roberto J. .
COMPUTER VISION - ECCV 2016, PT VII, 2016, 9911 :615-629
[14]   An Attention-Based Digraph Convolution Network Enabled Framework for Congestion Recognition in Three-Dimensional Road Networks [J].
Shen, Guojiang ;
Han, Xiao ;
Chin, KwaiSang ;
Kong, Xiangjie .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (09) :14413-14426
[15]   A survey of recent advances in CNN-based single image crowd counting and density estimation [J].
Sindagi, Vishwanath A. ;
Patel, Vishal M. .
PATTERN RECOGNITION LETTERS, 2018, 107 :3-16
[16]   Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework [J].
Song, Qingyu ;
Wang, Changan ;
Jiang, Zhengkai ;
Wang, Yabiao ;
Tai, Ying ;
Wang, Chengjie ;
Li, Jilin ;
Huang, Feiyue ;
Wu, Yang .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :3345-3354
[17]  
Sooksatra Sorn, 2019, 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), P231, DOI 10.1109/SITIS.2019.00047
[18]   TraCount: A Deep Convolutional Neural Network for Highly Overlapping Vehicle Counting [J].
Surya, Shiv ;
Babu, Venkatesh R. .
TENTH INDIAN CONFERENCE ON COMPUTER VISION, GRAPHICS AND IMAGE PROCESSING (ICVGIP 2016), 2016,
[19]  
Vaswani A., 2017, P P 31 INT C NEURAL
[20]   Kernel-Based Density Map Generation for Dense Object Counting [J].
Wan, Jia ;
Wang, Qingzhong ;
Chan, Antoni B. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (03) :1357-1370