US 12,443,858 B2
Training method and system for passenger distribution prediction model, and passenger guiding method and system
Hui Liu, Hunan (CN); Zhu Duan, Hunan (CN); Jin Qin, Hunan (CN); Haiping Wu, Hunan (CN); Shi Yin, Hunan (CN); and Chao Chen, Hunan (CN)
Assigned to Central South University, Changsha (CN)
Appl. No. 17/776,585
Filed by CENTRAL SOUTH UNIVERSITY, Hunan (CN)
PCT Filed May 19, 2021, PCT No. PCT/CN2021/094495
§ 371(c)(1), (2) Date May 12, 2022,
PCT Pub. No. WO2022/062432, PCT Pub. Date Mar. 31, 2022.
Claims priority of application No. 202011029942.4 (CN), filed on Sep. 27, 2020.
Prior Publication US 2022/0391717 A1, Dec. 8, 2022
Int. Cl. G06N 5/022 (2023.01); G06Q 50/40 (2024.01); G06T 7/10 (2017.01)
CPC G06N 5/022 (2013.01) [G06Q 50/40 (2024.01); G06T 7/10 (2017.01); G06T 2207/20021 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A training method for a distribution prediction model of passengers in a subway car, comprising:
establishing a spatial coordinate system of the subway car, installing a collection device constituted by temperature and humidity sensors and a CO2 concentration sensor in the subway car, each collection device serving as a sample collection point, and obtaining installation coordinates of each sample collection point in the corresponding spatial coordinate system;
obtaining a temperature time series, a humidity time series, and a CO2 concentration time series at each sample collection point of the subway car during a sampling period, and obtaining an average temperature value and an average humidity value locally of a day, wherein the installation coordinates of each sample collection point, the temperature time series, the humidity time series, and the CO2 concentration time series corresponding to the sample collection point, and the average temperature value and the average humidity value constitute an environmental data sample at each sample collection point of the subway car during the sampling period;
recording passenger positions in the subway car at an end time of the sampling period, and obtaining coordinates of passengers in the corresponding spatial coordinate system, so as to obtain a passenger distribution for the subway car during the sampling period;
converting the passenger distribution for the subway car during the sampling period into a binary image, and calculating a mean value, a variance, a maximum value and a minimum value of pixels in the binary image;
calculating an amplitude and a gradient direction of each pixel in the binary image, and establishing a frequency distribution histogram with a gradient direction of all pixels as an abscissa axis and a pixel value corresponding to each pixel as an ordinate axis; extracting a frequency distribution feature of the frequency distribution histogram, the frequency distribution feature referring to a feature vector constituted by pixel values corresponding to each interval among R intervals equally divided from the abscissa axis of the frequency distribution histogram;
combining the mean value, the maximum value, the minimum value, the variance and the frequency distribution feature of the pixels in the binary image to form an original feature vector associated with the binary image, and clustering the binary images for multiple sampling periods with the associated original feature vectors as-input of a clustering algorithm to obtain image clustering results; coding a passenger distribution mode according to the image clustering results to obtain a passenger distribution code, each category of image clustering result corresponding to one passenger distribution mode, and each passenger distribution mode corresponding to one passenger distribution code; and
establishing a distribution prediction model of passengers in the subway car, and training the distribution prediction model with training samples to obtain a trained distribution prediction model, the training sample taking the environmental data sample at-each sample collection point of the subway car during the sampling period as input and the corresponding passenger distribution code as output.