In crowd surveillance systems, it is important to select the proper analysis algorithm considering the properties of the video content. The inappropriate algorithm selection may result in performance degradation and generation of false alarms. An important feature of crowd videos is the density of the crowd. While object detection and tracking based algorithms are feasible for low density crowds, holistic approaches are preferable for high density crowds. In this paper, we studied the problem of crowd density classification and reported the accuracy rates and execution times in comparison with the studies in the literature.