Vanrajkumar Dineshkumar Baria
Vanrajkumar Dineshkumar Baria has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Ashok K Rathva
Assistant Professor, Computer Engineering Department, Government Engineering College, Dahod
1 shared publication- Jwalant Babubhai Baria
Assistant Professor, Computer Engineering Department, Government Engineering College, Dahod
1 shared publication - Karan P Bhatt
Assistant Professor, Computer Engineering Department, Vishwakarma Government Engineering College, Chandkheda
1 shared publication - Shivangkumar R Patel
Assistant Professor, Computer Engineering Department, Government Engineering College, Modasa
1 shared publication Yagnik A Rathod
Assistant Professor, Computer Engineering Department, Government Engineering College, Dahod
1 shared publication
Latest Publications
- Open Access
- 10 February 2026
- Published by XLESCIENCE in International Journal of Advances in Signal and Image Sciences
- Vol. 12 (2s) , 688-705
Deep Learning-Based Road Surface Defect Detection Using Image Processing Techniques
The importance of detecting road surface defects (cracks and potholes) promptly is crucial to transportation safety, minimisation of maintenance plans and minimisation of infrastructure deterioration costs. Conventional inspection techniques are time-consuming, subjective, and can hardly be used to offer scalable solutions to large road networks. The recent developments in deep learning and computer vision have shown that automated pavement distress detection is highly promising. The proposed research is a deep learning framework of road surface defect detection that combines image preprocessing with the lightweight object detection networks. The suggested methodology will also use contrast enhancement, noise reduction, and data augmentation to enhance the model's strength when faced with different illuminations and environmental conditions. Real-time defect localisation and classification make use of a convolutional neural network-based detection architecture, which is based on the state-of-the-art object detection models. The evaluation of the performance is based on typical measures such as precision, recall, F1-score, and the mean Average Precision (mAP). The superiority in accuracy of detection and the computational efficiency is proven by the comparisons with the already developed deep learning methods. The findings show that the combination of image enhancement methods and optimised deep neural networks can help a great deal to achieve detection reliability in real-world scenarios. The suggested architecture offers a highly scalable and low-cost solution to an intelligent pavement monitoring system and smart infrastructure management.
- 10 February 2026
- Published by XLESCIENCE in International Journal of Advances in Signal and Image Sciences
- Vol. 12 (2s) , 688-705
Open AccessDeep Learning-Based Road Surface Defect Detection Using Image Processing Techniques
The importance of detecting road surface defects (cracks and potholes) promptly is crucial to transportation safety, minimisation of maintenance plans and minimisation of infrastructure deterioration costs. Conventional inspection techniques are time-consuming, subjective, and can hardly be used to offer scalable solutions to large road networks. The recent developments in deep learning and computer vision have shown that automated pavement distress detection is highly promising. The proposed research is a deep learning framework of road surface defect detection that combines image preprocessing with the lightweight object detection networks. The suggested methodology will also use contrast enhancement, noise reduction, and data augmentation to enhance the model's strength when faced with different illuminations and environmental conditions. Real-time defect localisation and classification make use of a convolutional neural network-based detection architecture, which is based on the state-of-the-art object detection models. The evaluation of the performance is based on typical measures such as precision, recall, F1-score, and the mean Average Precision (mAP). The superiority in accuracy of detection and the computational efficiency is proven by the comparisons with the already developed deep learning methods. The findings show that the combination of image enhancement methods and optimised deep neural networks can help a great deal to achieve detection reliability in real-world scenarios. The suggested architecture offers a highly scalable and low-cost solution to an intelligent pavement monitoring system and smart infrastructure management.