Car Safety Support System on the Base of Data Mining Algorithm

Abstract

According to the target of the 11 th Sustainable Development Goal, to reach sustainability in cities, we have to ensure the transport systems' safety. Since safety driver assistance systems play a critical role both in averting crashes and reducing the likelihood of serious injury, we suggest a Safety Support System based on machine vision and a data mining algorithm that could be used for application to decision module of fully-or semi-autonomous vehicles. The created system was tested on a simple collection of photos from a Polish two-lane road. The novelty of this system is concluded in our EAV (Entity-Attribute-Value) model based algorithm that, while providing the same level of accuracy, works faster by reducing the number of analyzed attributes.