Smart City Gnosys

Smart city article details

Title	Participatory Sensing Based Urban Road Condition Classification Using Transfer Learning
ID_Doc	41378
Authors	Jana S.; Middya A.I.; Roy S.
Year	2024
Published	Mobile Networks and Applications, 29, 1
DOI	http://dx.doi.org/10.1007/s11036-023-02118-6
Abstract	Road surfaces can contain a lot of anomalies such as potholes. Understanding and detecting such irregularities are a key towards building a safe road transport system and a step towards building a smart city. This paper makes an attempt to classify road surface images using transfer learning on pre-trained convolution neural network (CNN) based models. In this work, two types of transfer learning approaches namely fine tuning and feature extraction are employed on various state-of-the-art CNN architectures of recent past such as VGG-16 (by Visual Geometry Group), VGG-19, Inception, ResNet-50 (Residual Network), Xception, DenseNet-121, SEResNet-50 (Squeeze-and-Excitation ResNet model), and EfficientNet-B3. The performance of the models are evaluated based on real-world dataset of road surface images collected by the participants. The evaluation metrics considered are test accuracy, precision, recall, F1-score, specificity, area under the receiver operating characteristic curve (ROC-AUC) and also training and inference time measurements. It is observed that among all the deep CNN models, SEResNet-50 (F1-score = 0.954, ROC-AUC = 0.993), Xception (F1-score = 0.943, ROC-AUC = 0.987) and DenseNet-121 (F1-score = 0.941, ROC-AUC = 0.987) achieve the best performance in terms of the evaluation metrics while fine tuning is considered with data augmentation. Effectiveness of the deep CNN models are also evaluated on various benchmark datasets, namely Road Traversing Knowledge (RTK) dataset and pothole dataset. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
Author Keywords	Convolutional neural networks; Deep learning; Participatory sensing; Transfer learning

Similar Articles

Id	Similarity	Authors	Title	Published
44480	0.876	Srikanth M.; Krishna N.S.V.S.S.J.; Krishna S.J.S.; Irfan S.; Venkat T.G.	Real-Time Vehicle Detection And Road Condition Prediction For Smart Urban Areas	Proceedings of the 4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024 (2024)
13429	0.876	Vasudha E.; Chilukuri B.R.	Carriageway Edge Detection For Unmarked Urban Roads Using Deep Learning Techniques	2023 Smart Cities Symposium Prague, SCSP 2023 (2023)
46779	0.872	Kumar K.M.	Roadtransnet: Advancing Remote Sensing Road Extraction Through Multi-Scale Features And Contextual Information	Signal, Image and Video Processing, 18, 3 (2024)
44340	0.872	Mehajabin N.; Ma Z.; Wang Y.; Tohidypour H.R.; Nasiopoulos P.	Real-Time Deep Learning Based Road Deterioration Detection For Smart Cities	International Conference on Wireless and Mobile Computing, Networking and Communications, 2022-October (2022)
16106	0.871	Lakshminarayanan S.; Konidhala J.	Convolutional Neural Network For Pothole Identification In Urban Roads	International Journal Of Advances In Signal And Image Sciences, 10, 1 (2024)
44435	0.869	Kulambayev B.; Gleb B.; Katayev N.; Menglibay I.; Momynkulov Z.	Real-Time Road Damage Detection System On Deep Learning Based Image Analysis	International Journal of Advanced Computer Science and Applications, 15, 9 (2024)
58038	0.868	Mehta S.; Singh A.	Towards Autonomous Road Maintenance: Cnn-Fl Integration For Pothole Detection Systems	2024 4th Asian Conference on Innovation in Technology, ASIANCON 2024 (2024)
46762	0.866	Tiwari S.; Bhandari R.; Raman B.	Roadcare: A Deep-Learning Based Approach To Quantifying Road Surface Quality	COMPASS 2020 - Proceedings of the 2020 3rd ACM SIGCAS Conference on Computing and Sustainable Societies (2020)
42510	0.865	Singh S.; Arora J.; Sethi M.	Pothole Classification Using Densenet Model: An Empirical Analysis With Cnn And Inceptionresnetv2	Lecture Notes in Networks and Systems, 1076 LNNS (2024)
789	0.865	Zhou H.; He H.; Xu L.; Ma L.; Zhang D.; Chen N.; Chapman M.A.; Li J.	A Comparative Study Of Deep Learning Methods For Automated Road Network Extraction From High-Spatial-Resolution Remotely Sensed Imagery	Photogrammetric Engineering and Remote Sensing, 91, 3 (2025)