Application of Railway Passenger Flow Statistics Based on Mask R-CNN. Issue 7 (March 2020)

• Record Type: Journal Article
• Authors: Meng, Di; Xu, Shangzhi
• Is Part Of: IOP conference series. Volume 768:Issue 7(2020)
• Publication Date: 2020-03
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/768/7/072050
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: 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.