Welcome to Francis Academic Press

International Journal of New Developments in Engineering and Society, 2023, 7(3); doi: 10.25236/IJNDES.2023.070304.

Pavement Recognition Based on Improving VGG16 Network Model


Shuoyi Wen, Li Yang, Hailong Duan, Tingting Zhang

Corresponding Author:
Li Yang

School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin, China


In order to improve the accuracy of pavement recognition, an improved RA-VGG16 network model classification method based on VGG16 is proposed in this paper. The improvements include reducing the number of convolution cores in VGG16 to optimize the network structure, adding the improved residual attention module to achieve the extraction of road notable features, using the global average pooling layer instead of the full connection layer to significantly reduce the network parameters and prevent network over fitting. The experimental results show that the accuracy of the improved VGG16 network model is 99.36%, 15.26% higher than that of the original VGG16, and significantly higher than other models (KNN, Alex Net, VGG13, ResNet50, ResNet101).


Road surface recognition, VGG16, The residual attention module, Feature extraction

Cite This Paper

Shuoyi Wen, Li Yang, Hailong Duan, Tingting Zhang. Pavement Recognition Based on Improving VGG16 Network Model. International Journal of New Developments in Engineering and Society (2023) Vol.7, Issue 3: 21-27. https://doi.org/10.25236/IJNDES.2023.070304.


[1] Blas M R, Agrawal M, Sundaresan A, et al. Fast color/texture segmentation for outdoor robots [C] //Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ International Conference on. IEEE, 2008: 4078-4085. 

[2] Liang Minjian. Key Technology of Visual Perception of Intelligent Vehicle [D]. Riving Environment. Xi'an: Chang'an University, 2017. 

[3] KUEHNLE A, BUR {HOUT W. Image-based winter road conditionrecognition C}//Applications of Advanced Technologies inTransportation, ASCE, 1998. 

[4] Kim T Y, Sung G Y, Lyou J. Robust terrain classification by introducing environmental sensors [C] //Safety Security and Rescue Robotics (SSRR), 2010 IEEE International Workshop on. IEEE, 2010: 1-6. 

[5] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [C]. International Conference on Learning Representations, 2015. 

[6] Wu Z, Chen H, Lei Y. Recognizing Non-Collaborative Radio Station Communication Behaviors Using an Ameliorated LeNet [J]. Sensors, 2020, 20(15): 4320. 

[7] He M, Zhao X, Lu Y, et al. An improved AlexNet model for automated skeletal maturity assessment using hand X-ray images [J]. Future Generation Computer Systems, 2021, 121: 106-113. 

[8] Qiu J, Lu X, Wang X, et al. Research on Rice Disease Identification Model Based on Migration Learning in VGG Network[C]//IOP Conference Series: Earth and Environmental Science. IOP Publishing, 2021, 680(1): 012087. 

[9] Qu Z, Mei J, Liu L, et al. Crack Detection of Concrete Pavement With Cross-Entropy Loss Function and Improved VGG16 Network Model[J]. IEEE Access, 2020, PP(99):1-1.

[10] Huang Xuehua, Chen Weihong, Yang Wangdong. Improved Algorithm Based on The Deep Integration of Googlenet and Residual Neural Network[J]. Journal of Physics: Conference Series, 2021, 1757(1). 

[11] Moon J, Hossain M B, Chon K H. AR and ARMA model order selection for time-series modeling with ImageNet classification [J]. Signal Processing, 2021, 183:108026. 

[12] Mao Z , Zhao C , Zheng Y , et al. Research on detection method of pavement diseases based on Unmanned Aerial Vehicle (UAV)[C]// 2020 International Conference on Image, Video Processing and Artificial Intelligence. SPIE, 2020.

[13] Woo S, Park J, Lee J Y, et al. CBAM: Convolutional Block Attention Module[J]. 2018. 

[14] Liu Z, DuJ, Wang M et al. ADCM: Attention Dropout Convolutional Module[J]. Neurocomputing, 2020, 394. 

[15] Li X, Wang W, Hu X, et al. Selective Kernel Networks[J]. 2019. 

[16] He K, Zhanu X, Ren S, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.