Pedestrian information collation through image-based person identification for pedestrian information sharing using V2V communications

The purpose of this research is to share pedestrian information among multiple vehicles by vehicle-to-vehicle communication and detect the positions all pedestrians around vehicle. In past, we have proposed a method collating shared through image-based person Re-Identification (ReID). paper, in order improve accuracy collation, state-of-the-art ReID network adapted our scenario fine-tuning. addition, new image dataset for sharing was constructed. experiments using dataset, improved collation accuracy.