Open AccessApplication of Railway Passenger Flow Statistics Based on Mask R-CNN
Author(s) -
Di Meng,
Shangzhi Xu
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/7/072050
Subject(s) - computer science , artificial intelligence , range (aeronautics) , tracking (education) , detector , computer vision , flow (mathematics) , convolutional neural network , pattern recognition (psychology) , field (mathematics) , engineering , mathematics , telecommunications , geometry , psychology , pedagogy , pure mathematics , aerospace engineering
This paper discusses and implements the application of Mask R-CNN in railway passenger flow statistics. Mask R-CNN is a target detector based on candidate region, combining deep learning, neural network and image recognition technology, and has a wide range of application value in the field of intelligent monitoring.The paper focuses on the algorithm named Mask-Flow that Mask R-CNN uses the same color for tracking on the same target, and counts the number of pedestrians. And the passenger flow statistics are compared with Retina-Net in the railway scene of the dense crowd, which proves the accuracy of the method in the paper.