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
[1]  
Bas E, 2007, 2007 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3, P1085
[2]  
Dosovitskiy A, 2020, ARXIV
[3]   ICIF-Net: Intra-Scale Cross-Interaction and Inter-Scale Feature Fusion Network for Bitemporal Remote Sensing Images Change Detection [J].
Feng, Yuchao ;
Xu, Honghui ;
Jiang, Jiawei ;
Liu, Hao ;
Zheng, Jianwei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[4]   3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples [J].
Feng, Yuchao ;
Zheng, Jianwei ;
Qin, Mengjie ;
Bai, Cong ;
Zhang, Jinglin .
REMOTE SENSING, 2021, 13 (21)
[5]   Extremely Overlapping Vehicle Counting [J].
Guerrero-Gomez-Olmedo, Ricardo ;
Torre-Jimenez, Beatriz ;
Lopez-Sastre, Roberto ;
Maldonado-Bascon, Saturnino ;
Onoro-Rubio, Daniel .
PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2015), 2015, 9117 :423-431
[6]   Real-Time Traffic Flow Parameter Estimation From UAV Video Based on Ensemble Classifier and Optical Flow [J].
Ke, Ruimin ;
Li, Zhibin ;
Tang, Jinjun ;
Pan, Zewen ;
Wang, Yinhai .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2019, 20 (01) :54-64
[7]  
Khairdoost N., 2013, Signal Image Process, V4, P31, DOI 10.5121/sipij.2013.4403
[8]   Edge Computing for Internet of Everything: A Survey [J].
Kong, Xiangjie ;
Wu, Yuhan ;
Wang, Hui ;
Xia, Feng .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (23) :23472-23485
[9]   Deep Reinforcement Learning-Based Energy-Efficient Edge Computing for Internet of Vehicles [J].
Kong, Xiangjie ;
Duan, Gaohui ;
Hou, Mingliang ;
Shen, Guojiang ;
Wang, Hui ;
Yan, Xiaoran ;
Collotta, Mario .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (09) :6308-6316
[10]  
Lin H., 2022, P IEEECVF C COMPUTER, P19628