IoT for measuring road network quality index

Abstract

Egypt has been fighting the issue of ensuring road safety‚ reducing accidents‚ preserving the lives of citizens since its inception. For these reasons‚ precisely identifying the road condition‚ followed by effective and timely maintenance and rehabilitation measures‚ leads to an increase in the road network's safety level and lifespan. This paper presents a multi-input deep learning framework that combines BiLSTM and Depthwise separable convolution to work in parallel for automatic recognition of road surface quality and different road anomalies. Furthermore, we performed an investigation to compare deep networks approaches against other traditional approaches using real-time data sensed and collected from the Egyptian road network. The proposed deep model has achieved an average accuracy of 93.1%‚ which is superior compared to other evaluated approaches. Finally, we utilized the proposed model to estimate a road quality index in the Egyptian cities.

Evaluation of data representation techniques for vibration based road surface condition classification

“…Due to the varying lengths of road sections with different surface conditions, raw vibration data is often segmented into windows for analysis. Techniques like GPS timestamps or signal characteristics are used for segmentation 4 , 11 .…”

“…Road surface quality detection can be achieved through three main techniques: (a) laser scanning, (b) computer vision, and (c) sensor-based 4 . Each of these techniques has its own strengths and weaknesses, making them appropriate for different situations and environments.…”

SCD-YOLO: A Novel Object Detection Method for Efficient Road Crack Detection

“…As computer vision advances, deep learning has become increasingly dominant, excelling at managing complex data and tasks by enabling highly automated feature extraction and pattern recognition through multi-layer neural networks. Deep learning is pivotal in detecting road cracks, utilizing techniques such as BiLSTM, depthwise separable convolution [11], and SWARA [12]. These methods facilitate the efficient evaluation of road quality and identification of safety risks.…”