REAL TIME PEDESTRIAN ALERT SYSTEM FOR VEHICLES

Abstract

In this study, we have developed a pre-collision alert system for vehicles in terms of detection pedestrians in road. The system is consisting from deep learning models and transfer learning methodologies. For this purpose, pre-trained convolutional models was considered to detect pedestrian and road. Finally, the segmented road mask and pedestrian mask was utilized to reveal the intersection of these two masks. The system generates an alert if the number of pixels is higher than predefined threshold value. By considering the visual results, the proposed system gives valuable detection results to avoid collision.