All-day perception for intelligent vehicles: switching perception algorithms based on WBCNet

被引:1
作者
Xie, Hongbin [1 ]
Zhao, Haiyan [1 ]
Xu, Chengcheng [1 ]
Chen, Hong [2 ]
机构
[1] Jilin Univ, Coll Commun Engn, Changchun 130025, Peoples R China
[2] Tongji Univ, Coll Elect & Informat Engn, Shanghai 201804, Peoples R China
关键词
driving scene classification; intelligent vehicle; safe driving; convolutional neural network; attention mechanism; OBJECT DETECTION; MODEL;
D O I
10.1007/s11432-023-4116-5
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A weather- and brightness-based classification network (WBCNet) is proposed for driving scene classification to address the decreased accuracy in perception caused by weather and environment changes. To facilitate its applicability in vehicles and minimize computational demands on vehicle chips, WBCNet has been designed with special modules, including attention mechanisms and dilated convolutions. Dilated convolutions combined with residual connections empower WBCNet to concurrently handle information at various scales. This aids in simplifying the training and optimization of deep networks, consequently enhancing the model's performance and mitigating the risk of overfitting. The outstanding feature association capability originating from the fusion of channel attention and spatial attention enables WBCNet to focus more on the sky, lanes, and other traffic information features within the image. This design enables WBCNet to use only images as input, making it highly suitable for engineering applications. The output of WBCNet provides the basis for the downstream perception model selection algorithm, allowing it to choose the appropriate perception model for different scenes accurately. A dataset with complex scenes based on Carla is constructed for comparison to verify WBCNet's performance. Finally, a real-world driving dataset is used to validate the effectiveness and real-time performance of WBCNet.
引用
收藏
页数:16
相关论文
共 39 条
  • [21] Lane-keeping System of Intelligent Vehicles Based on Extension Switching Control Method
    Cai Y.-F.
    Zang Y.
    Sun X.-Q.
    Chen X.-B.
    Chen L.
    [J]. Zhongguo Gonglu Xuebao/China Journal of Highway and Transport, 2019, 32 (06): : 43 - 52
  • [22] Soft Actor-Critic-Based Multilevel Cooperative Perception for Connected Autonomous Vehicles
    Xie, Qi
    Zhou, Xiaobo
    Qiu, Tie
    Zhang, Qingyu
    Qu, Wenyu
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (21): : 21370 - 21381
  • [23] Photovoltaic-based energy system coupled with energy storage for all-day stable PEM electrolytic hydrogen production
    Gu, Xufei
    Ying, Zhi
    Zheng, Xiaoyuan
    Dou, Binlin
    Cui, Guomin
    [J]. RENEWABLE ENERGY, 2023, 209 : 53 - 62
  • [24] An intelligent vehicle environment perception and situation cognition model based on hierarchical factor graph
    Yin H.-L.
    Wu S.-L.
    Wang Y.-W.
    Wang J.
    [J]. Kongzhi yu Juece/Control and Decision, 2020, 35 (10): : 2528 - 2534
  • [25] Day-Ahead Forecasting of Hourly Photovoltaic Power Based on Robust Multilayer Perception
    Huang, Chao
    Cao, Longpeng
    Peng, Nanxin
    Li, Sijia
    Zhang, Jing
    Wang, Long
    Luo, Xiong
    Wang, Jenq-Haur
    [J]. SUSTAINABILITY, 2018, 10 (12)
  • [26] Key Indicators to Assess the Performance of LiDAR-Based Perception Algorithms: A Literature Review
    Karri, Chiranjeevi
    da Silva, Jose Machado
    Correia, Miguel Velhote
    [J]. IEEE ACCESS, 2023, 11 : 109142 - 109168
  • [27] Machine Learning-Based Radar Perception for Autonomous Vehicles Using Full Physics Simulation
    Sligar, Arien P.
    [J]. IEEE ACCESS, 2020, 8 (08): : 51470 - 51476
  • [28] Slim-FCP: Lightweight-Feature-Based Cooperative Perception for Connected Automated Vehicles
    Guo, Jingda
    Carrillo, Dominic
    Chen, Qi
    Yang, Qing
    Fu, Song
    Lu, Hongsheng
    Guo, Rui
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (17): : 15630 - 15638
  • [29] UIEGAN: Adversarial Learning-Based Photorealistic Image Enhancement for Intelligent Underwater Environment Perception
    Han, Guangjie
    Wang, Min
    Zhu, Hongbo
    Lin, Chuan
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [30] Intelligent Monitoring of Concrete Vibration Quality Based on Space-Air-Ground Integrated Perception
    Wang D.
    Guan T.
    Yang S.
    Wang X.
    Zhai H.
    Ren B.
    [J]. Kuei Suan Jen Hsueh Pao/Journal of the Chinese Ceramic Society, 2023, 51 (05): : 1219 - 1227