A lightweight convolutional neural network for road surface classification under shadow interference

被引:0
|
作者
Mao, Ruichi [1 ]
Wu, Guangqiang [1 ]
Wu, Jian [1 ]
Wang, Xingyu [1 ]
机构
[1] Tongji Univ, Sch Automot Studies, Shanghai 201804, Peoples R China
基金
中国国家自然科学基金;
关键词
Road classification; Data augmentation; Computer vision; Convolution neural network;
D O I
10.1016/j.knosys.2024.112761
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The development of intelligent driving, especially in the intelligent control of active suspension, heavily relies on the predictive perception of upcoming road conditions. To achieve accurate real-time road surface classification and overcome shadow interference, a lightweight convolutional neural network (CNN) based on a novel data augmentation method is proposed and an improved cycle-consistent adversarial network (CycleGAN) is developed to generate shadowed pavement data. The CycleGAN network structure is optimized using the texture selfsupervised (TSS) mechanism and the learned perceptual image patch similarity (LPIPS) function, with label smoothing applied during training. The images produced by this data augmentation method closely resemble real-world images. Furthermore, Efficient-MBConv, which offers the advantages of fewer parameters and higher precision, is proposed. Finally, the Light-EfficientNet architecture, based on Efficient-MBConv, is developed and trained on the augmented dataset. Compared with EfficientNet-B0, the number of parameters in LightEfficientNet is reduced by 61.94 %. The Light-EfficientNet model trained with data augmentation demonstrates an average classification accuracy improvement of 5.76 % on the test set with shadows, compared with the model trained without data augmentation. This approach effectively reduces the impact of shadows on road classification at a lower cost, while also significantly reducing the computational resources required by the CNN, providing real-time and accurate road surface information for the control of active suspension height and damping.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] A lightweight convolutional neural network for myositis classification from muscle ultrasound images
    Tan, Hao
    Lang, Xun
    Wang, Tao
    He, Bingbing
    Li, Zhiyao
    Lu, Yu
    Zhang, Yufeng
    Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical Engineering, 2024, 41 (05): : 895 - 902
  • [42] Lightweight convolutional neural network for chest X-ray images classification
    Yen, Chih-Ta
    Tsao, Chia-Yu
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [43] LN-SCNet: A Lightweight Convolutional Neural Network for SAR Ship Classification
    Zhao, Shuang
    Li, Weihang
    Shen, Fangyu
    You, Ming
    IEEE ACCESS, 2025, 13 : 39394 - 39404
  • [44] A Lightweight Method for Vehicle Classification Based on Improved Binarized Convolutional Neural Network
    Zhang, Bangyuan
    Zeng, Kai
    ELECTRONICS, 2022, 11 (12)
  • [45] Smart soil image classification system using lightweight convolutional neural network
    Pandiri, D. N. Kiran
    Murugan, R.
    Goel, Tripti
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 238
  • [46] Efficient and lightweight convolutional neural network architecture search methods for object classification
    Lin, Chuen-Horng
    Chen, Tsung-Yi
    Chen, Huan-Yu
    Chan, Yung-Kuan
    PATTERN RECOGNITION, 2024, 156
  • [47] Lightweight deep convolutional neural network for background sound classification in speech signals
    Dayal, Aveen
    Yeduri, Sreenivasa Reddy
    Koduru, Balu Harshavardan
    Jaiswal, Rahul Kumar
    Soumya, J.
    Srinivas, M. B.
    Pandey, Om Jee
    Cenkeramaddi, Linga Reddy
    JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2022, 151 (04): : 2773 - 2786
  • [48] Convolutional Neural Network for Road Extraction
    Li, Junping
    Ding, Yazhou
    Feng, Fajie
    Xiong, Baoyu
    Cui, Weihong
    LIDAR IMAGING DETECTION AND TARGET RECOGNITION 2017, 2017, 10605
  • [49] PCBNet: A Lightweight Convolutional Neural Network for Defect Inspection in Surface Mount Technology
    Wu, Hongjin
    Lei, Ruoshan
    Peng, Yibing
    IEEE Transactions on Instrumentation and Measurement, 2022, 71
  • [50] A one-dimension convolutional neural network based interference classification method
    Duan, Chaowei
    Feng, Suili
    Hu, Hanwu
    Luo, Zhenjiang
    PHYSICAL COMMUNICATION, 2023, 59