Robust and Online Vehicle Counting at Crowded Intersections
Jincheng Lu, Meng Xia, Xu Gao, Xipeng Yang, Tianran Tao, Meng Hao, Wei Zhang, Xiao Tan, Yifeng Shi, Guanbin Li, Errui Ding
Abstract
In this paper, we propose an online movement-specific vehicle counting system to realize robust traffic flow analysis at crowded intersections. Our proposed framework adopts PP-YOLO as the vehicle detector and adapts the Deep-Sort algorithm to perform multi-object tracking. In order to realize online and robust vehicle counting, we further adopt a shape-based movement assignment strategy to differentiate movements and carefully designed spatial constraints to effectively reduce false-positive counts. Our proposed framework achieves the overall S1-score of 0.9467, ranking the first in the AICITY2021-track1 challenge.
Topics & Concepts
Computer sciencesortArtificial intelligenceComputer visionVehicle tracking systemObject detectionDetectorTracking (education)Ranking (information retrieval)Pattern recognition (psychology)SegmentationInformation retrievalTelecommunicationsPedagogyPsychologyVideo Surveillance and Tracking MethodsTraffic Prediction and Management TechniquesAnomaly Detection Techniques and Applications