A Survey of Pedestrian Detection Based on Deep Learning

Abstract

The purpose of pedestrian detection is to accurately locate each pedestrian belonging to the detection range from a specific scene. When combined with pedestrian recognition and pedestrian tracking technology, it has important applications in areas such as autonomous driving, human-computer interaction, intelligent video surveillance, and character object behavior analysis. The research progress of deep learning technology in the field of pedestrian detection is studied. The main problems and challenges of pedestrian detection are analyzed. The paper also summarizes the data sets and evaluation criteria of pedestrian detection. Provide reference and basis for comprehensive research in the field.