Deep Transfer Learning Enabled High-Density Crowd Detection and Classification using Aerial Images

Automated crowd classification in aerial images finds it helpful to avoid crowd disaster in complicated situations of mass events. Earlier works have focused on crowd count and crowd density computation using regression models. But these models operate only if the proper manual count has existed for reference purposes. So, it is needed to determine the high density crowd in aerial images by the use of classification models. In this aspect, this study presents a new VGG16 with kernel extreme learning machine (KELM) model for high density crowd detection and classification. The proposed VGG16-KELM model primarily undergoes pre-processing step to boost the quality of the input images. Besides, VGG16 method was employed as a feature extractor which derives a useful group of feature vectors. In addition, KELM technique is applied as a classifier which determines the density of the crowd, shows the novelty of the work. For demonstrating the enhanced performance of the VGG16-KELM approach, a wide range of simulations were carried out and the results are assessed under several aspects. The experimental outcomes reported the enhanced performance of the VGG16-KELM technique on the other compared methods.