Crowd counting has drawn increasing attention across various fields. However, existing crowd counting tasks primarily focus on estimating the overall population, ignoring the behavioral and semantic information of different social groups within the crowd. In this paper, we aim to address a newly proposed research problem, namely fine-grained crowd counting, which involves identifying different categories of individuals and accurately counting them in static images. In order to fully leverage the categorical information in static crowd images, we propose a two-tier salient feature propagation module designed to sequentially extract semantic information from both the crowd and its surrounding environment. Additionally, we introduce a category difference loss to refine the feature representation by highlighting the differences between various crowd categories. Moreover, our proposed framework can adapt to a novel problem setup called few-example fine-grained crowd counting. This setup, unlike the original fine-grained crowd counting, requires only a few exemplar point annotations instead of dense annotations from predefined categories, making it applicable in a wider range of scenarios. The baseline model for this task can be established by substituting the loss function in our proposed model with a novel hybrid loss function that integrates point-oriented cross-entropy loss and category contrastive loss. Through comprehensive experiments, we present results in both the formulation and application of fine-grained crowd counting.

In recent years, floods have caused significant casualties and property damage worldwide. To investigate the evacuation dynamics of pedestrian in subway stations under flood invasion conditions, an evacuation model for pedestrian under flood situations is established by incorporating a cellular automata model and a hydrodynamic model. The effects of water depth, flow speed and flow direction on pedestrian movement and behavioral characteristics in subway stations are quantified. Crowd evacuation with the flood spreading process under various scenarios is simulated, and the egress time and pedestrian distribution are analyzed. It is found that the existence of flood reduces the evacuation speed and delays the evacuation process. With the increase of water depth and intake flow, it becomes more challenging for passengers to evacuate successfully. Under this circumstance, adding the number of safety exits and widening the exit width can significantly reduce the evacuation time. Besides, the pre-evacuation behavior hinders the movement process, and the rapid evacuation becomes more difficult due to the flood spreading during this period. The evacuation efficiency can be improved if the pre-evacuation time reduces. The study is useful to design evacuation plans and improve the emergency management level of subway stations under sudden flood disasters.