A new hybrid mobile CNN approach for crosswalk recognition in autonomous vehicles

Abstract

While automobile transportation is increasing worldwide, it also negatively affects the safety of road users. Along with the neglect of traffic rules, pedestrians account for 22% of all highway traffic deaths. Millions of pedestrians suffer non-fatal injuries from these accidents. Most of these injuries and deaths occur at crosswalks, where the highway and pedestrians intersect. In this study, deep learning-based a new hybrid mobile CNN approaches are proposed to reduce injuries and deaths by automatically recognizing of crosswalks in autonomous vehicles. The first of these proposed approaches is the HMCNet approach, which is a hybrid model in which the MobileNetv3 and MNasNet CNN models are used together. This model achieves approximately 2% more accuracy than the peak performance of the lean used MobileNetv3 and MNasNet models. Another proposed approach is the FHMCNet approach, which increases the success of the HMCNet approach. In the FHMCNet approach, LSVC feature selection method and SVM classification method are used in addition to HMCNet. This approach increased the classification success of HMCNet by more than approximately 2%. Finally, the proposed FHMCNet offered approximately 3% more classification accuracy than state-of-the-art methods in the literature.