Learning and Analysis of AusRAP Attributes from Digital Video Recording for Road Safety

Authors:

Abstract
The manual systems for road safety are inefficient, very time consuming and prone to error. Automated systems face many challenges in detecting all road safety objects accurately and accurately measuring the distance between these objects. Therefore, in this paper, a novel approach is proposed to analyze roadside video data in order to assess important attributes pertaining to road safety. The specific aim is to learn and analyse Australian Road Assessment Program (AusRAP) attributes obtained from digital video recordings (DVRs). In this work, a technique for segmentation and classification based on Fully Convolutional Network (FCN) is investigated. The proposed approach takes video frames as input, extracts features through convolutional layer and learns them to classify in fully connected layer. The novelty in our approach is learning road attributes and its application in road safety. The proposed approach is optimized using multiple image sizes and training epochs. The 411 images obtained from roadside video data provided by the Department of Transport and Main Roads (DTMR), Queensland, Australia have been used to analyze the proposed technique. The evaluation results are discussed, and a comparative analysis is presented.