A Deep Learning Approach for Road Damage Detection from Smartphone Images

With recent advances in technology, it is feasible to conveniently monitor urban roads using various cameras, such as surveillance cameras, in-vehicle cameras, or smartphones, and recognize their conditions by detecting specific types of road damages in order to plan maintenance resources efficiently based on the identified spots. This paper describes a road damage type detection and classification solution submitted to the IEEE BigData Cup Challenge 2018. Our solution is based on the state-of-the-art deep learning methods for an object detection task. In particular, our approach utilizes an object detection algorithm to detect various types of road damages by training the detector on different image examples categorized into a set of damages defined by Japan Road Association. We evaluated our approach thoroughly using different versions of trained models. Our experiments show that our approach was able to achieve an F1 score up to 0.62.

[1]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Bugao Xu,et al.  A real-time 3D scanning system for pavement distortion inspection , 2009 .

[3]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Yoshihide Sekimoto,et al.  Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images , 2018, Comput. Aided Civ. Infrastructure Eng..

[5]  Cyrus Shahabi,et al.  Real-Time Traffic Video Analysis Using Intel Viewmont Coprocessor , 2013, DNIS.

[6]  Mehmet Karakose,et al.  A Fast and Adaptive Road Defect Detection Approach Using Computer Vision with Real Time Implementation , 2016 .

[7]  Cyrus Shahabi,et al.  Scalable Spatial Crowdsourcing: A Study of Distributed Algorithms , 2015, 2015 16th IEEE International Conference on Mobile Data Management.

[8]  Cyrus Shahabi,et al.  Hybrid Indexes for Spatial-Visual Search , 2017, ACM Multimedia.

[9]  Bill Yu,et al.  Vibration-Based System for Pavement Condition Evaluation , 2006 .

[10]  Cyrus Shahabi,et al.  Spatial Coverage Measurement of Geo- Tagged Visual Data: A Database Approach , 2018, 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM).

[11]  Cyrus Shahabi,et al.  Geo-Spatial Multimedia Sentiment Analysis in Disasters , 2017, 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[12]  Yoshihide Sekimoto,et al.  Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images , 2018, Comput. Aided Civ. Infrastructure Eng..

[13]  Yang Liu,et al.  Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network , 2017, Comput. Aided Civ. Infrastructure Eng..

[14]  Cyrus Shahabi,et al.  Image Classification to Determine the Level of Street Cleanliness: A Case Study , 2018, 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM).

[15]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[16]  Yimin D. Zhang,et al.  Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).