Evaluation of crowd counting models in term of prediction performance and computational requirement

With the increasing of human population and the development of technology, crowd counting models are needed to estimate people in certain areas. This research paper compares the prediction performance and computational requirement of four state of the art crowd counting models: M-SFAnet, DM-Count, Context-Aware Crowd Counting (ECAN), and Supervised Spatial Divide-and-Conquer (SS-DCNet). The evaluations were performed to find the most high-performance model in term of prediction performance and computational requirement. The computational requirement is being compared and considered because of the development of Internet of Things devices, crowd counting models that have good prediction performance and low computational requirements can be implemented in low-compute devices. We evaluated the models on four different datasets. From the evaluation we found that SS-DCNet approach achieved the most favorable results.