Deep Learning Method to Detect the Road Cracks and Potholes for燬mart燙ities
Source abstract
Abstract
The increasing global population at a rapid pace makes road traffic dense; managing such massive traffic is challenging. In developing countries like Pakistan, road traffic accidents (RTA) have the highest mortality percentage among other Asian countries. The main reasons for RTAs are road cracks and potholes. Understanding the need for an automated system for the detection of cracks and potholes, this study proposes a decision support system (DSS) for an autonomous road information system for smart city development with the use of deep learning. The proposed DSS works in layers where initially the image of roads is captured and coordinates attached to the image with the help of global positioning system (GPS), communicated to the decision layer to find about the cracks and potholes in the roads, and eventually, that information is passed to the road management information system, which gives information to drivers and the maintenance department. For the decision layer, we projected a CNN-based model for pothole crack detection (PCD). Aimed at training, a K-fold cross-validation strategy was used where the value of K was set to 10. The training of PCD was completed with a self-collected dataset consisting of 6000 images from Pakistani roads. The proposed PCD achieved 98% of precision, 97% recall, and accuracy while testing on unseen images. The results produced by our model are higher than the existing model in terms of performance and computational cost, which proves its significance.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Geotechnical Engineering and Underground Structures
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (54)
Show source-provided references
1. Getting clever about smart cities: New opportunities require new business models
2. A Real-time smart dumpsters monitoring and garbage collection system
3. Waste management and prediction of air pollutants using iot and machine learning approach10.3390/en13153930 ↗
4. Iot-based smart waste bin monitoring and municipal solid waste management system for smart cities10.1007/s13369-020-04637-w ↗
5. Internet of things smart traffic management system for smart cities using big data analytics
6. Automated pothole distress assessment using asphalt pavement video data10.1061/(ASCE)CP.1943-5487.0000232 ↗
7. Automatic road crack detection and characterization10.1109/TITS.2012.2208630 ↗
8. Patch detection for pavement assessment10.1016/j.autcon.2015.03.010 ↗
9. Efficient pavement crack detection and classification10.1186/s13640-017-0187-0 ↗
10. Heggie · the International Bank of Reconstruction and Development · 1998 · 23 · 7
11. Leveraging deep learning and iot big data analytics to support the smart cities development: Review and future directions10.1016/j.cosrev.2020.100303 ↗
12. Skin cancer disease detection using transfer learning technique10.3390/app12115714 ↗
13. Multi-column deep neural networks for image classification
14. Multi-level deep learning model for potato leaf disease recognition10.3390/electronics10172064 ↗
15. Real-time multiple guava leaf disease detection from a single leaf using hybrid deep learning technique10.32604/cmc.2023.032005 ↗
16. Water level prediction of community secondary water supply tank based on deep learning
17. Racial identity-aware facial expression recognition using deep convolutional neural networks10.3390/app12010088 ↗
18. A survey on an emerging area: Deep learning for smart city data10.1109/TETCI.2019.2907718 ↗
19. The pascal visual object classes challenge: A retrospective10.1007/s11263-014-0733-5 ↗
20. Imagenet: A largescale hierarchical image database
21. Road crack detection using visual features extracted by gabor filters10.1111/mice.12042 ↗
22. A fast and adaptive road defect detection approach using computer vision with real time implementation10.18100/ijamec.270546 ↗
23. Deep learning-based urban big data fusion in smart cities: Towards traffic monitoring and flow preserving fusion10.1016/j.compeleceng.2020.106906 ↗
24. Convolution neural networks for pothole detection of critical road infrastructure10.1016/j.compeleceng.2022.107725 ↗
25. Detection of segregation in asphalt pavement materials using the aran profile system
26. Detection of sealed and unsealed cracks with complex backgrounds using deep convolutional neural network10.1016/j.autcon.2019.102946 ↗
27. Faster region convolutional neural network for automated pavement distress detection10.1080/14680629.2019.1614969 ↗
28. Autonomous concrete crack detection using deep fully convolutional neural network10.1016/j.autcon.2018.11.028 ↗
29. Deep learning-based crack damage detection using convolutional neural networks10.1111/mice.12263 ↗
30. Convolutional neural networks based potholes detection using thermal imaging10.1016/j.jksuci.2019.02.004 ↗
31. Image processing based automatic recognition of asphalt pavement patch using a metaheuristic optimized machine learning approach10.1016/j.aei.2019.04.004 ↗
32. Computer vision-based concrete crack detection using u-net fully convolutional networks10.1016/j.autcon.2019.04.005 ↗
33. Convolutional neural network for pothole detection in asphalt pavement10.1080/14680629.2019.1615533 ↗
34. Realtime road crack mapping using an optimized convolutional neural network10.1155/2019/2470735 ↗
35. H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama and H. Omata, “Road damage detection using deep neural networks with images captured through a smartphone,” arXiv preprint arXiv:1801.09454, 2018.
36. A transfer learning-based system of pothole detection in roads through deep convolutional neural networks
37. Intelligent deep learning based pothole detection and reporting system
38. Pavement pothole detection based on cascade and fusion convolutional neural network using 2d images under complex pavement conditions
39. Indian pothole detection based on cnn and anchor-based deep learning method10.1007/s41870-022-00881-5 ↗
40. Kavati · Edge Analytics · 2022 · 869 · 256
41. Cifar-10 python. Kaggle, 2021. [Online]. Available: https://www.kaggle.com/pankrzysiu/cifar10-python/version/1.
42. Lisa traffic light dataset. Kaggle, 2021. [Online]. Available: https://www.kaggle.com/mbornoe/lisa-traffic-light-dataset/code.
43. Data augmentation for improving deep learning in image classification problem
44. keras-team/keras: Deep learning for humans, 2022. [Online]. Available: https://github.com/keras-team/keras.
45. Welcome to colaboratory-colaboratory, 2021. [Online]. Available: https://colab.research.google.com/notebooks/intro.ipynb?utm_source = scs-index.
46. Evidence based emergency medicine; part 5 receiver operating curve and area under the curve
47. Mobilenetv2: Inverted residuals and linear bottlenecks
48. Rethinking the inception architecture for computer vision
49. Learning transferable architectures for scalable image recognition
50. Developing a prediction model for rutting depth of asphalt mixtures using gene expression programming10.1016/j.conbuildmat.2020.120543 ↗
51. Deep learning based detection of potholes in Indian roads using yolo
52. Supangkat · Data-Driven Multivalence in the Built Environment · 2020 · 22310.1007/978-3-030-12180-8_11 ↗
53. Pavement distress detection and classification based on yolo network
54. An integrated machine learning model for automatic road crack detection and classification in urban areas