We construct a social media dataset, compare the effectiveness of face recog- nition, object recognition, and cascaded methods for crowd size estimation, and investigate the impact of image characteristics on the performance of selected methods. Results show that object recognition based methods, reach the highest accuracy in estimating the crowd size using social media images in city events. We also found that face recognition and object recognition methods are more suitable to estimate the crowd size for social media images which are taken in parallel view, with selfies covering people in full face and in which the persons in the background have the same distance to the camera. However, cascaded methods are more suitable for images taken from top view with gatherings distributed in gradient. The created social media dataset is essential for selecting image characteristics and evaluating the accuracy of people counting methods in an urban event context.
Bron: Gong, X., Daamen, W., Bozzon, A., & Hoogendoorn, S. P. (2021). Counting people in the crowd using social media images for crowd management in city events. Transportation. https://doi.org/10.1007/s11116-020-10159-z