It is the Project assigned by Dphi as the final submission for the Deep Learning for the Bootcamp. I have secured 36th position out of 586 submission as per the public Leaderboard.
Time and again, countless instances of accidents caused by unfavourable weather conditions around the world have surfaced. Plane crash , Ship collision, train derailment and car accidents are just a few of the tragic events that have been a part of the headlines in recent times. This grave problem of safety and security in adverse conditions has piqued the public's interest and numerous studies have been done in past to reveal the susceptibility of functioning of transportation services owing to weather conditions.
With the advancement in technology and emergence of a new field, intelligent transportation, automated determination of weather condition has become more relevant. Present systems either rely on series of expensive sensors or human assistance to identify the weather conditions. Help the meteorologist’s to channel their research in a direction where computer vision techniques have been used to classify the weather condition using a single image.
The dataset features 5 different classes of weather. The dataset contains about 1500 labelled images including the validation images. Each image has only one weather category and are saved in separate folders of the labelled classes
Dataset Link : https://dphi-live.s3.eu-west-1.amazonaws.com/dataset/weather.zip