efficient weather recognition algorithm on highway roads for vehicle guidance
| Autor: | K. B. Jayanthi, K Vanitha, M Malathi, J Chandrasekar, R.G.B Khavya |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | International journal of health sciences. :1212-1223 |
| ISSN: | 2550-696X 2550-6978 |
| Popis: | Adverse weather has long been recognized as one of the major causes of motor vehicle crashes due to its negative impact on visibility and road surface. Automatic recognition of weather condition has important application value in traffic condition warning, automobile auxiliary driving, intelligent transportation system, and other aspects. Providing drivers with real- time weather information is therefore extremely important to ensure safe driving in adverse weather. Most of the Department of Transportations (DoTs) in the U.S. have installed roadside webcams mostly for operational awareness. This study leveraged these easily accessible data sources to develop affordable automatic road weather condition for vehicle guidance. The developed detection model is focused on four weather conditions; rainy, snowy, sunny and foggy. The main goal of the proposed work is to use two neural network models such as K-Nearest Neighbour and pre- trained Convolutional Neural Network (CNN) models to achieve the classified tasks. The ResNet50 issued to train and test on the “Weather Dataset” and desirable recognition results are obtained. AlexNet, GoogleNet, ResNet50 and SqueezeNet has been compared .The Result has been achieved with ResNet50. ResNet50 is proposed as higher accuracy as compared to AlexNet, GoogleNet ,ResNet and SqueezeNet. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|