Talk · International Conference on Intelligent Data Communication Technologies and Internet of Things · January 4, 2024
DeepPave: Detection of Potholes Using Deep Learning Techniques
Tummala Varshith, Thanush S Koneri, Uppalapati Dhanush, Sriramoju Rahul, C. Jyotsna
Abstract
In a developing country like India, the major difficulty lies in identifying and addressing problems. Improving road quality is crucial for economic growth, as well-maintained roads contribute significantly. The proposed model DeepPave, a combination of Visual Geometry Group 16 (VGG 16), Convolutional Neural Network (CNN), and Multilayer Perceptron (MLP), along with regularization techniques such as dropout and L2 regularization and optimization techniques, has been developed for the detection of potholes. The aim is to enhance road infrastructure and contribute positively to the nation's economy. The proposed pothole detection system holds great potential for enhancing road safety, optimizing maintenance operations, and reducing infrastructure maintenance expenses. By promptly identifying potholes, transportation authorities can efficiently allocate resources, improve road quality, and ensure safer driving conditions for motorists.
More by Jyotsna Chandrasekharan
- Optimization of Lotka-Volterra Equations using Ant Colony OptimizationInternational Conference on Recent Advancement in Electrical, Computer and Communication Technologies · 2026
- Comparative Analysis of Deep Learning Models for Visual Classification of Terrestrial and Extraterrestrial Rock ImageIEEE International Conference on AI Engineering and Innovations · 2026 · Citations: 1
- Real Time Screen Based Gaze Estimation Using MediaPipe and Machine Learning ModelsIEEE International Conference on AI Engineering and Innovations · 2026
- ECG Analysis for Myocardial Infarction Detection via Deep LearningProcedia Computer Science · 2026