MobileCrack: Object Classification in Asphalt Pavements Using an Adaptive Lightweight Deep Learning

Journal of Transportation Engineering Part B Pavements, vol. 147, pp. 04020092

Abstract

One of the key steps in pavement maintenance is the fast and accurate identification of the distresses, defects, and pavement markings and ability to conduct the maintenance before the irreversible damages. Recently, convolution neural network (CNN) has emerged as a powerful tool to automatically identify the pavement cracks, where many of the CNN models take long computation time. To solve the problem, an adaptive lightweight model, named MobileCrack, is proposed in this study. MobileCrack realizes the fast computation using the following settings: (1) reduce input image size, where besides the original input images, images with a side length of 1/2,1/4,1/8… of that of the original square images are also input into the model by using the resize command; (2) group convolution is used; and (3) global average pooling is used because it normally has less parameters compared with the fully connected layer. MobileCrack will then compute the combinations of different resized input images and different neural network structures, to find the optimal reduced image size and neural network structure with satisfactory accuracy using reasonable computation time. To verify the applicability of MobileCrack, 10,000 input images with size 400×400 are trained for the classification task of crack, sealed crack, pavement marking, and pavement matrix. Based on the computation results of combinations of images with different sizes (400×400, 200×200, 100×100, and 50×50) and different stacking numbers of core modules n (3, 4, 5, and 6), the optimal model is determined as image size 200×200 and n=4, where the test accuracy is 0.865 within reasonable computation time (runtime=47 ms to test one image). This optimal model will be automatically used for further tests with image size 400×400 for a fast computation, which realizes the lightweight adaptive goal. Results also show that the test accuracy of MobileCrack is higher than that of the AlexNet and visual geometry group (VGG), and the parameters of MobileCrack are approximately 1/4 of that of the classic lightweight CNN model MobileNet, which saves the storage space. It is concluded that that the proposed adaptive lightweight CNN model, MobileCrack, can be used for the fast object classification on asphalt pavement crack images.

Authors 7

1. Yue Hou

   Beijing University of Technology

   Affiliation as printed

   Associate Professor, Beijing Key Laboratory of Traffic Engineering, Beijing Univ. of Technology, 100 Pingleyuan, Chaoyang District, Beijing 100124, China

2. Qiuhan Li

   Beijing Jiaotong University · Beijing University of Technology

   Affiliation as printed

   Graduate Research Assistant, Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Beijing Jiaotong Univ., Beijing 100044, China; Beijing Key Laboratory of Traffic Engineering, Beijing Univ. of Technology, 100 Pingleyuan, Chaoyang District, Beijing 100124, China

   Beijing Key Laboratory of Traffic Engineering, Beijing Univ. of Technology, 100 Pingleyuan, Chaoyang District, Beijing 100124, China

3. Qiang Han corresponding

   Beijing University of Technology

   Affiliation as printed

   Professor, Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education, Beijing Univ. of Technology, Beijing 100124, China (corresponding author)

4. Bo Peng

   Autodesk (United States)

   Affiliation as printed

   Software Engineer and Data Scientist, Autodesk Inc., 1 Market St., San Francisco, CA 94105

5. Linbing Wang

   Virginia Tech

   Affiliation as printed

   Professor, Dept. of Civil and Environmental Engineering, Virginia Tech, Blacksburg, VA 24061

6. Xingyu Gu

   Southeast University

   Affiliation as printed

   Professor, School of Transportation, Southeast Univ., Nanjing 211189, China

7. Dawei Wang Aachen Professor Institute of Highway Engineering

   Harbin Institute of Technology · Beijing University of Technology · RWTH Aachen University

   Affiliation as printed

   Professor, School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin, Heilongjiang Province 150090, China; Professor, Institute of Highway Engineering, Rheinisch-Westfälische Technische Hochschule Aachen Univ., D52074 Aachen, Germany; Adjunct Professor, Beijing Key Laboratory of Traffic Engineering, Beijing Univ. of Technology, 100 Pingleyuan, Chaoyang District, Beijing 100124, China. ORCID:

   Professor, School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin, Heilongjiang Province 150090, China

   Professor, School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin, Heilongjiang Province 150090, China; Professor, Institute of Highway Engineering, Rheinisch-Westfälische Technische Hochschule Aachen Univ., D52074 Aachen, Germany; Adjunct Professor, Beijing Key Laboratory of Traffic Engineering, Beijing Univ. of Technology, 100 Pingleyuan, Chaoyang District, Beijing 100124, China. ORCID: