Estimation of crowd density applying wavelet transform and machine learning
This incremental work addresses crowd management for pedestrian safety and comfort by providing an easier measurement approach.
The researchers tackled the problem of estimating crowd density by developing a new method that uses wavelet transform and machine learning on angular velocity data from pedestrians, finding prediction accuracy as high as with raw velocity data.
We conducted a simple experiment in which one pedestrian passed through a crowded area and measured the body-rotational angular velocity with commercial tablets. Then, we developed a new method for predicting crowd density by applying the continuous wavelet transform and machine learning to the data obtained in the experiment. We found that the accuracy of prediction using angular velocity data was as high as that using raw velocity data. Therefore, we concluded that angular velocity has relationship with crowd density and we could estimate crowd density by angular velocity. Our research will contribute to management of safety and comfort of pedestrians by developing an easy way to measure crowd density.