Crowd Density Prediction Model Based on Image Processing and Support Vector Regression

Crowd stability is a research hotspot in the area of emergency management, while crowd density is the most direct and effective basis for crowd stability analysis. Therefore, it is significant to study the trend of crowd density and make some reliable predictions. This paper introduces advanced image processing technology, increasing the number of columns in a traditional convolutional neural network (CNN) to improve the accuracy of crowd counting, and further obtains high-precision crowd density values through image correction. Then, combined with the mature support vector regression (SVR) algorithm, this paper explores the kinematic characteristics of pedestrians, and proposes a novel crowd density prediction model. By predicting the position of group pedestrians in next few moments, the prediction of crowd density changes in public places can be achieved, which provides data support for crowd stability analysis. Finally, case study is carried out with actual scenario of Shanghai Hongqiao Airport, and the feasibility of the model is verified.